LLMDB.APP SITE ARCHITECTURE

Full HTML Sitemap Index

Comprehensive directory tree of all main hub sections, categories, AI tools, AI models, prompts, research papers, articles, and comparisons on llmdb.app.

Core Hubs

Categories (6)

AI Models (383)

All Vetted AI Tools (55)

Grammarlyfreemium · grammarly
DeepSeek Chatfreemium · deepseek
Cursorfreemium · cursor
Claudefreemium · claude
Canva Magic Studiofreemium · canva-magic-studio
Midjourneypaid · midjourney
ChatGPTfreemium · chatgpt
HubSpot AIpaid · hubspot-ai
NotebookLMfree · notebooklm
GitHub Copilotpaid · github-copilot
Runwayfreemium · runway
v0 by Vercelfreemium · v0
Claude Codepaid · claude-code
Zapier Centralpaid · zapier-central
Replit AIfreemium · replit-ai
Perplexity AIfreemium · perplexity
Adobe Fireflypaid · adobe-firefly
Geminifreemium · gemini
Windsurffreemium · windsurf
Qwenfreemium · qwen
Leonardo AIfreemium · leonardo-ai
Doubaofree · doubao
DALL-E 3paid · dalle-3
Kimi Chatfree · kimi
Bolt.newfreemium · bolt-new
Notion AIpaid · notion-ai
Motionpaid · motion
Sunofreemium · suno
Fireflies.aifreemium · fireflies-ai
Elicitfreemium · elicit
Sudowritepaid · sudowrite
Lovablepaid · lovable
Ernie Botfreemium · ernie-bot
Frase.iopaid · frase-io
Otter.aifreemium · otter-ai
SciSpacefreemium · scispace
Consensusfreemium · consensus
Writesonicfreemium · writesonic
MarketMusepaid · marketmuse
Copy.aifreemium · copy-ai
Jasperpaid · jasper
i10x.aipaid · i10x-ai
LLM Pulsepaid · llm-pulse
Pictorypaid · pictory
MeetGeekfreemium · meetgeek
Reclaim.AIfreemium · reclaim-ai
Synthesiapaid · synthesia
Surfer SEOpaid · surfer-seo
Analyze AIpaid · analyze-ai
Voibefreemium · voibe
AdCreative.aipaid · adcreative-ai
ElevenLabsfreemium · elevenlabs
Gammafreemium · gamma
Antigravity 2.0paid · antigravity-2-0
Castmagicpaid · castmagic

Curated Prompt Templates (140)

C++ to Rust Migration Advisor for Legacy CodeGPT-6 Astra · 13 copies
Blog to Video Script Converter for Reels & YouTubeGPT-6 Astra · 20 copies
Multi-Modal Product Concept Tester with Synthetic FeedbackClaude 4.6 Sonnet · 25 copies
Automated Standup Summary Generator PromptClaude 4.6 Sonnet · 22 copies
Automated Load Testing Script GeneratorClaude 4.6 Sonnet · 27 copies
React Component Accessibility AuditorClaude 4.6 Sonnet · 11 copies
Self-Healing Data Pipeline Monitor PromptClaude 4.6 Sonnet · 13 copies
Meeting Action Item Extractor PromptClaude 4.6 Sonnet · 25 copies
Automated API Versioning Strategy GeneratorClaude 4.6 Sonnet · 25 copies
Cross-Modal Prompt Optimizer for Image-Text AlignmentClaude 4.6 Sonnet · 29 copies
Zero-Shot API Client Code GeneratorClaude 4.6 Sonnet · 24 copies
Personal Knowledge Management System PromptClaude 4.6 Sonnet · 16 copies
UI/UX Heuristic Evaluation AgentClaude 4 Sonnet · 17 copies
Hyper-Realistic Product Placement Script for AR/VR AdsClaude 4.6 Sonnet · 24 copies
Automated Code Documentation GeneratorClaude 4.6 Sonnet · 23 copies
Hyper-Targeted Sales Script GeneratorClaude 4.6 Sonnet · 13 copies
Automated Code Review Scoring & Impact PrioritizationGPT-6 Astra · 27 copies
Meta-Analysis Automation & Statistical Synthesis PromptClaude 4.6 Sonnet · 11 copies
Automated Competitor Ad Copy Analyzer & Idea GeneratorClaude 4.6 Sonnet · 24 copies
Automated Process Mining for Workflow OptimizationClaude 4.6 Sonnet · 15 copies
Multi-Agent Debate System for Complex ReasoningClaude 4.6 Sonnet · 15 copies
AI Product Photo Background Eraser & ReplacerClaude 4.6 Sonnet · 24 copies
Real-Time Meeting Action Item ExtractorClaude 4.6 Sonnet · 22 copies
Multi-Agent Research Synthesis PromptClaude 4.6 Sonnet · 28 copies
Multilingual Sentiment & Emotion AnalyzerGPT-5 · 13 copies
Real-time Code Review & Refactoring AdvisorClaude 4.6 Sonnet · 26 copies
Dynamic Meeting Summarizer with Action Item ExtractionGPT-5 · 22 copies
Hyper-Personalized User Journey Mapping for SaaSGPT-5 · 13 copies
Autonomous UI/UX Accessibility AuditorClaude 4.6 Sonnet · 14 copies
A/B Landing Page Copy Generator with SEO VariantsClaude 4.6 Sonnet · 25 copies
Sentiment-Driven Ad Variation Generator PromptGPT-4 · 28 copies
Personalized Fitness & Nutrition Plan GeneratorClaude 4.6 Sonnet · 15 copies
Multi-Cloud Cost Anomaly Detector PromptClaude 4.6 Sonnet · 19 copies
Data Privacy Compliance Mapping PromptClaude 4.6 Sonnet · 14 copies
Automated Competitor SWOT Analysis GeneratorClaude 4.6 Sonnet · 13 copies
AI Ethics Policy & Compliance Writer PromptClaude 4.6 Sonnet · 10 copies
Generative UI Component Variant CreatorClaude 4.6 Sonnet · 14 copies
Causal Impact Analysis for A/B Tests – Prompt TemplateClaude 4.6 Sonnet · 17 copies
Synthetic Data Generator for Privacy-Preserving MLClaude 4.6 Sonnet · 26 copies
CI/CD Pipeline Security Hardening AdvisorClaude 4.6 Sonnet · 16 copies
Hyper-Personalized Learning Journey CreatorClaude 4.6 Sonnet · 26 copies
Automated UX Heuristic Evaluator with Persona SimulationClaude 4.6 Sonnet · 13 copies
Self-Optimizing Prompt Chain GeneratorClaude 4.6 Sonnet · 28 copies
Automated Video Script to Storyboard GeneratorClaude 3.5 Sonnet · 28 copies
Knowledge Gap Analyzer & Custom Curriculum DesignerClaude 4.6 Sonnet · 27 copies
Dynamic Knowledge Graph Extractor from Unstructured TextClaude 4.6 Sonnet · 21 copies
Academic Literature Systematic Reviewer PromptClaude 3.5 Sonnet · 16 copies
WCAG 2.1 Web Accessibility Auditor & Fix AdvisorGPT-6 Astra · 16 copies
Multi-Agent Code Review Pipeline PromptGPT-5 · 26 copies
Multi-Modal Brand Consistency AuditorGPT-5 · 18 copies
Scientific Hypothesis Generator with Literature SupportClaude 4.6 Sonnet · 17 copies
Multi-Perspective Ethical AI SimulatorClaude 4.6 Sonnet · 21 copies
Visual Style Transfer Prompt for Consistent Brand ImageryClaude 4.6 Sonnet · 18 copies
API Doc Generator from Code AnnotationsGPT-6 Astra · 15 copies
Social Media Ad Creative Strategist PromptClaude 4.6 Sonnet · 16 copies
Cross-Lingual Semantic Search Engine Design PromptClaude 4.6 Sonnet · 17 copies
Hyper-Personalized Onboarding Flow Designer for SaaSClaude 4.6 Sonnet · 23 copies
Character Consistency Checker for NovelsClaude 4.6 Sonnet · 11 copies
Automated Codebase Docs from Git HistoryClaude 4.6 Sonnet · 23 copies
Hyper-Personalized Email Campaign GeneratorClaude 4.6 Sonnet · 23 copies
Multi-Language Code Migration AgentClaude 4.6 Sonnet · 16 copies
PostgreSQL Advanced Index OptimizerClaude 3.5 Sonnet · 20 copies
Technical B2B Case Study WriterClaude 3.5 Sonnet · 17 copies
Financial Model Risk & Sensitivity Analyst PromptClaude 3.5 Sonnet · 17 copies
Zero-Shot TypeScript Unit Test Generator for VitestClaude 3.5 Sonnet · 15 copies
Hyper-Personalized Video Thumbnail A/B Test GeneratorClaude 3.5 Sonnet · 15 copies
Automated PMF Survey AnalyzerGPT-4o · 27 copies
Psychological Pricing Strategy GeneratorClaude 4.6 Sonnet · 22 copies
Autonomous Code Refactoring AgentClaude 4.6 Sonnet · 23 copies
Interactive Fiction Plot WeaverClaude 4.6 Sonnet · 16 copies
Automated A/B Test Hypothesis GeneratorClaude 4.6 Sonnet · 22 copies
Multi-Language Documentation Translator with Technical AccuracyClaude 4.6 Sonnet · 21 copies
Automated API Contract Testing AgentClaude 4.6 Sonnet · 28 copies
Personal Brand Voice Analyzer & RefinerClaude 4.6 Sonnet · 19 copies
AI-Assisted Architecture Decision Record WriterClaude 4.6 Sonnet · 27 copies
Multi-Agent Synthetic Data Generator for Niche DomainsClaude 4.6 Sonnet · 20 copies
Zero-Shot Data Pipeline BuilderClaude 4.6 Sonnet · 16 copies
Automated Compliance Document AnalyzerClaude 4.6 Sonnet · 18 copies
Edge Case Test Suite GeneratorClaude 4.6 Sonnet · 19 copies
Retargeting Ad Personalization PromptClaude 4.6 Sonnet · 17 copies
Cross-Reference Fact CheckerGPT-5 · 22 copies
SQL Query Performance OptimizerClaude 4.6 Sonnet · 180 copies
Data-Driven Narrative GeneratorClaude 4.6 Sonnet · 16 copies
Synthetic Dialogue Generator for Chatbot TrainingClaude 4.6 Sonnet · 26 copies
AI Content Repurposer: Blog to Social MediaClaude 4.6 Sonnet · 29 copies
Multi-Perspective Research SynthesizerClaude 4.6 Sonnet · 11 copies
User Persona Generator from Interview TranscriptsClaude 4.6 Sonnet · 27 copies
Proactive System Health Monitoring & Alerting PromptClaude 4.6 Sonnet · 15 copies
Dynamic Prompt Chaining for Complex WorkflowsClaude 4.6 Sonnet · 16 copies
Zero-Shot Contextual Image Inpainting PromptDALL-E 3 · 12 copies
Automated Prompt Regression Testing for LLM PipelinesClaude 4.6 Sonnet · 22 copies
Privacy-Preserving Synthetic Data GeneratorClaude 4.6 Sonnet · 14 copies
Streaming Pipeline Anomaly Detection PromptClaude 4.6 Sonnet · 29 copies
Multi-Lingual SEO Content Cluster BuilderClaude 4.6 Sonnet · 28 copies
Automated Data Quality Reviewer for ML PipelinesClaude 4.6 Sonnet · 10 copies
Dynamic Personal Brand Story GeneratorGPT-5 · 22 copies
Automated Data Cleaning & Preprocessing Agent PromptClaude 4.6 Sonnet · 11 copies
Cross-Platform UI/UX Accessibility AuditorClaude 4.6 Sonnet · 20 copies
API Mock Server Generator PromptGPT-5 · 20 copies
Production Incident Root Cause Analyzer Prompt — Free | llmdb.appClaude 4.6 Sonnet · 28 copies
Multimodal Product Description from Video ReviewsGPT-5 · 21 copies
Emotional Arc Analyzer for Narrative WritingClaude 4.6 Sonnet · 27 copies
Automated Competitive Intelligence Brief GeneratorClaude 4.6 Sonnet · 27 copies
Predictive Churn Prevention Campaign GeneratorClaude 4.6 Sonnet · 20 copies
Automated Systematic Review with PRISMA ComplianceClaude 4.6 Sonnet · 22 copies
Code Review Coach: Real-Time FeedbackClaude 4.6 Sonnet · 16 copies
Meeting Minutes to Actionable Insights MapperGPT-6 Astra · 29 copies
Multi-Modal Research Synthesis Assistant for Literature ReviewsClaude 4.5 Sonnet · 10 copies
Product Roadmap Prioritization Matrix GeneratorClaude 4.6 Sonnet · 16 copies
Emerging Research Trend Forecaster PromptClaude 4.6 Sonnet · 19 copies
Cultural Nuance Translator for Global CampaignsClaude 4.6 Sonnet · 20 copies
Synthetic Training Data Generator for Edge CasesClaude 4.6 Sonnet · 10 copies
Product Requirements Gap Analyzer PromptClaude 4.6 Sonnet · 26 copies
Privacy-Preserving Synthetic Data EngineClaude 4.6 Sonnet · 23 copies
PostgreSQL Advanced Query Index OptimizerClaude 4.6 Sonnet · 20 copies
Adaptive Multi-Agent Research SynthesizerGPT-6 Astra · 19 copies
Multi-Agent Customer Support Triage SimulatorGPT-6 Astra · 19 copies
Real-Time Multi-Language Caption & Translation OptimizerGPT-6 Astra · 27 copies
Automated CI/CD Compliance Audit Trail GeneratorGPT-6 Astra · 15 copies
Competitive Intelligence Brief for Product LaunchesGPT-6 Astra · 22 copies
Real-Time Collaborative Code Review AssistantGPT-6 Astra · 13 copies
Kubernetes Deployment Debugger & Optimizer PromptClaude 4.6 Sonnet · 10 copies
Technical B2B Case Study Writer — Star-Story-SolutionClaude 4.6 Sonnet · 21 copies
Academic Paper SummarizerClaude 4.6 Sonnet · 35 copies
SEO Blog Outline GeneratorClaude 4.6 Sonnet · 750 copies
Meeting Action-Item ExtractorGPT-5 · 600 copies
Legacy Code Modernization Roadmap Generator"Claude 4.6 Sonnet · 25 copies
Predictive Churn Analysis & Retention PlaybookClaude 4.6 Sonnet · 10 copies
Voice of Customer Analysis & Sentiment Trend MapperClaude 4.6 Sonnet · 12 copies
Tailwind React Component BoilerplateClaude 4.6 Sonnet · 145 copies
Research Hypothesis GeneratorClaude 4.6 Sonnet · 25 copies
Brand Identity Hook EngineClaude 4.6 Sonnet · 95 copies
Value-First Cold Email PitchClaude 4.6 Sonnet · 820 copies
Eisenhower Matrix PrioritizerClaude 4.6 Sonnet · 15 copies
Junior Dev System Prompt for AI CodingClaude 3.5 Sonnet · 0 copies
High-CTR Google Ad Headline MatrixGPT-5 · 110 copies
Security Reviewer Agent Prompt for PRsClaude Opus 4 · 0 copies
Multi-Agent AI Coding Workflow Spec PromptClaude 3.5 Sonnet · 0 copies
Microsoft MAI-Thinking-1 Developer Guide & API SetupGPT-4o · 0 copies
JSON Schema Sentiment Analysis LLM PromptClaude 3.5 Sonnet · 0 copies

Technical Articles & Guides (72)

Speculative Decoding in Agentic Coding Pipelines: Balancing Throughput and Token Qualitytrend analysis · 9m read
Multi-Step Tool-Calling over Korean Open Public APIs: A Benchmark and a Data-Synthesis Recipetrend analysis · 9m read
Cost Optimization for LLM Applications: Model Routing, Caching, and Token Compressiontrend analysis · 10m read
Evaluating Autonomous Web Agents: Current Benchmarks, Limitations, and Future Trajectorytrend analysis · 8m read
Agentic Coding Interfaces: How Next-Gen IDEs Are Redefining Software Engineeringtrend analysis · 10m read
Edge AI and Local Inference: Running Open-Weight Models on Apple Silicon and WASMtrend analysis · 10m read
The Shift to Reasoning Models: Benchmark Analysis of DeepSeek R1 and O3-Minitrend analysis · 9m read
Attribution and Analytics Tracking for AI-Driven User Acquisition Funnelstrend analysis · 10m read
Programmatic SEO at Scale: Generating 1,000+ High-Intent Landing Pages Safelylisticle · 10m read
Predictive Customer Churn Prevention Using Vector Embeddings and Behavioral Signalscase study · 9m read
Building Autonomous Lead Enriched Workflows Using Agentic Scrapers and LLMscase study · 9m read
AI Search Engine Optimization (AEO/GEO): Strategies for Ranking in Perplexity and ChatGPTtrend analysis · 9m read
Evaluating LLM Copywriting Quality: Benchmarking Prompt Variants for Conversionlisticle · 9m read
Designing Programmatic Content Workflows with DeepSeek and Structured Schemascase study · 9m read
Building an Automated Content Verification & Fact-Checking Pipeline for AI Draftstrend analysis · 9m read
Automating Technical Documentation Generation from Codebase ASTs using LLMscase study · 9m read
Advanced Prompt Engineering: Few-Shot In-Context Learning for Complex Reasoninglisticle · 9m read
Orchestrating Multi-Agent Workflows with LangGraph and Durable Execution Statecase study · 8m read
Structured Outputs in Production: Comparing Pydantic AI, Instructor, and Outlineslisticle · 9m read
Fine-Tuning Small Language Models (SLMs) for Low-Latency Function Callingcase study · 9m read
Optimizing RAG Pipelines with Hybrid Search and Re-ranking: A Technical Blueprintcase study · 8m read
Building Resilient Agent Systems with Model Context Protocol (MCP) and TypeScripttrend analysis · 9m read
SHE: Trajectory-driven Safety Harness Evolution for LLM Agentstrend analysis · 8m read
Designing Zero-Trust Multi-Agent Workflows with Model Context Protocol (MCP)case study · 12m read
Benchmarking DeepSeek V3 vs. Claude 3.7 Sonnet on Complex Repository Refactoringtrend analysis · 12m read
Building Local-First AI Agents with WebGPU and WebAssembly Runtimescase study · 11m read
The Architecture of Context-Aware Prompt Caching in Enterprise LLM Gatewayscase study · 12m read
Evaluating Synthetic Data Generation Quality for Fine-Tuning Domain-Specific LLMstrend analysis · 11m read
Hierarchical Task Decomposition in Autonomous Coding Agents: Patterns and Pitfallscase study · 11m read
Next.js 15 routing parameters optimization with AIcase study · 8m read
Claude Code vs Cursor terminal benchmarkingcase study · 9m read
Mitigating Hallucination Ratios in RAG Systems Using Re-Ranking and Groundedness Checkscase study · 11m read
Hierarchical Agent Teams: How to Orchestrate Multi-Agent Systems for Complex Software Engineeringcase study · 9m read
The LRM vs. SLM Routing Engine: Optimizing Cost and Latency in Agentic Pipelinestrend analysis · 9m read
Pydantic AI: Developing Type-Safe, Production-Grade Agentic Architectureslisticle · 9m read
Stateful Agent Workflows: Mastering LangGraph for Long-Horizon Planning and Executioncase study · 9m read
Scaling with Model Context Protocol (MCP): Building Interoperable Tool Ecosystems for AI Agentstrend analysis · 9m read
Optimizing Token Efficiency: A Practical Guide to Prompt Compression Algorithmscase study · 10m read
The Evolution of AI Code Assistants: From Autocomplete to Autonomous Repository Refactoringtrend analysis · 12m read
Implementing Self-Correction Loops in Agentic Function Calling Architecturescase study · 11m read
Automating Enterprise Compliance Audits with Structured Output LLMs and JSON Schemascase study · 11m read
Comparing Vector Database Index Types: HNSW vs. IVFFlat vs. DiskANN for Multi-Tenant AI Appstrend analysis · 12m read
The Prompt Sandbox: Benchmarking What Actually Works in 2026listicle · 9m read
The "Cheat Codes" & Efficiency Vibecase study · 6m read
Fine-Tuning Llama 3.3 for Ultra-Low Latency API Tool Callingcase study · 11m read
Self-Evolving World Models for LLM Agent Planninglisticle · 10m read
Designing Resilient Human-in-the-Loop Safeguards for Autonomous Operationscase study · 10m read
The Economics of Open-Weights vs. Proprietary LLM Deployments in 2026trend analysis · 12m read
antigravity 2.0trend analysis · 9m read
Building Real-Time Multi-Modal Prompt Sandboxes with WebSockets and Edge Runtimescase study · 11m read
OpenAI Agents SDK: Implementing State-Safe Conversation Handoffs and Orchestration Loopscase study · 10m read
Multi-Agent Market Simulation: Modeling Competitive Financial Pricing in Real-Timetrend analysis · 8m read
Building an Autonomous Social Media Manager with Agentic RAG and Image Promptscase study · 10m read
Prompt Engineering vs. Agent Tuning: Which Strategy Yields Better Agency in LLMs?listicle · 10m read
Agentic Content Calendars: Automating the Pitch, Outline, Draft, and Edit Flowcase study · 9m read
The Role of Human-in-the-Loop (HITL) in Agentic Customer Support Workflowstrend analysis · 9m read
Agentic SEO: Automating Content Auditing, Competitor Analysis, and Internal Link Injectioncase study · 10m read
Zero-Shot Multi-Agent Frameworks for Human-Building Interaction via Programmatic Reasoningcase study · 10m read
Ahoy Framework: Enacting and Verifying Multiagent Interaction Protocols in Productioncase study · 10m read
ORAgentBench: Evaluating LLM Agents on Challenging Operations Research Taskstrend analysis · 10m read
OpenClaw vs OpenHands: Comparing Local-First Device Integration with Sandboxed Coding Environmentslisticle · 9m read
Pydantic AI: Developing Type-Safe Production Agents with Strict Schema Validationcase study · 8m read
Streamable HTTP: Building Stateless and Scalable MCP Server Architecturescase study · 9m read
Model Context Protocol (MCP) in 2026: Evolving to Agentic AI Foundation Standardstrend analysis · 9m read
Agent Skills for Large Language Models: Architecture, Acquisition, Security, and MCP-based Governancecase study · 10m read
Organizational Control Layer: Governance Infrastructure at the Execution Boundary of LLM Agent Systemscase study · 9m read
Beyond Tokens: A Unified Framework for Latent Communication in LLM-based Multi-Agent Systemstrend analysis · 9m read
Catching One in Five: LLM-as-Judge Blind Spots in Production Multi-Turn Transaction Agentstrend analysis · 6m read
Token Budgets: An Empirical Catalog of 63 LLM-Agent Failure Incidentslisticle · 10m read
Silent Failure in LLM Agent Systems: The Entropy Principle and the Inevitable Disorder of Autonomous Agentstrend analysis · 8m read
Standardizing Tool Definitions: A Deep Dive into Model Context Protocol (MCP) Schemascase study · 12m read
DeepSeek-V4-Flash: Revolutionizing MoE Inference at Scaletrend analysis · 10m read

Frontier AI Research Papers (315)

ScienceBuddy: Recursive-in-Recursive Self-Improvement for Interactive Scientific Agentsagents · Shuhan Xue
Agentic Societies Need a Social Harnessagents · Tapan Chugh
General Quantification of Covariate and Concept Shiftsother · Hongbo Chen
Data Scarcity and Model Sparsity: Mixtures-of-Experts Overfit More to Repeated Datallm · Atindra Jha
Can Edge-Deployable Vision-Language Models Identify Species?multimodal · William Zhou
GPU-CFR: 80x Faster Counterfactual Regret Minimization by Compiling the Game to Static Dataflow and CUDA Graph Replayefficiency · Boning Li
A comparison between ceiling-mounted FMCW, IR-UWB and Wi-Fi radar for in-bedroom human activity monitoring and sleep interruption detectionother · Anton Lambrecht
Information on trajectories: martingales and random timesother · Akshay Balsubramani
$TCP_α$: Margin-Controlled Confidence estimation for reliable Music Information Retrievalother · Parampreet Singh
G-CARL: Grounded Checklist-Aligned Reward Learning for Patient-Oriented Medical Report Interpretationmultimodal · Shiao Xie
ConceptGuard: Benchmarking Context-Sensitive Unlearning in Large Language Modelsalignment · Sahil Kale
Lévy Attention: Single-Pass Predictive Uncertainty for Continuous-Time Attentionother · Sotirios P. Chatzis
Finetuning Strategies for Querying Sounds by Vocal Imitationmultimodal · Aditya Bhattacharjee
Beyond Teacher Likelihood: Group-Calibrated On-Policy Distillation for Long-Context Reasoningefficiency · Zhu Zhang
ADEPT: Accelerating Dexterity via Pre-Training and Post-Training using Reinforcement Learningother · Jayjun Lee
From Corpora to Co-Evolving Capabilities: Capability-Centric Data Design for Generalist Image Generationvision · Xingjian Wang
The concentration game: Bayesian updating, regret, and informationother · Akshay Balsubramani
Multi-Agent AI System for Radiology Report Structuring and Quality Assurance with Independent Radiologist Evaluationagents · Iryna Hartsock
On the Fragility of Self-Improving Agents: Variance, Task Order, and Underspecificationagents · Qinyuan Ye
TokEval: A Tokenizer Evaluation Suitellm · Clara Meister
AutoSR: Automatic Symbolic Regression by Searching Research Statesagents · Kejia Zhang
Spectral Gaps of Hit-and-Run and Coordinate Hit-and-Runother · Yunbum Kook
Improving the matrix multiplication exponent with modern optimization and AlphaEvolveother · Emilien Dupont
Don't Drop the BATON: Long-Horizon Robot Manipulation via Agentic Subtask Exploration and Transition-aware Memoryagents · Bingxin Xu
Q-based Variational Inverse Reinforcement Learningother · Ondrej Bajgar
Decoding the Past: An Uncertainty-Aware Deep Learning Framework for Sex Attribution in Prehistoric Hand Stencilsvision · Karel Becerra
Participatory Moral AI Is Not Neutral: The Invisible Hand of Developersalignment · Taenyun Kim
Handover of In-Context Learning State Across Session Boundariesllm · Masahiro Kato
Marionette: Predicting World States, Rendering Geometry, Painting Appearancevision · Zian Meng
Vero: Can AI Agents Build Formally Verified Software Repositories?agents · Zhe Ye
DARTree: Speculative Diffusion Decoding with Autoregressive Draft Treesllm · Tianyi Li
SAEVerbalizer: Generating Explanations for Sparse Autoencoder Features via Representation Verbalizationllm · Weihan Meng
LittleLearner: Language Models Under Pedagogically Controlled Knowledge Exposurellm · Fanfei Li
QuoteBench: How Matched Scores Can Hide Command-Path Failuresagents · Shangao Li
Exponential Convex Calibration Dimension for the Multi-Label Jaccard Measureother · Mingyuan Zhang
Defensive Boosting for Online Probabilistic Forecastingother · Georgy Noarov
HumanTracker: Towards Comprehensive and Human-Aligned Motion Tracking Benchmarkvision · Dairu Liu
OmniScientist: An Omni-Modal Omni-Discipline AI Scientistagents · Bobo Li
AutoDesign: Meta-Harness Optimization for Long-Horizon Agentic Designagents · Yaxin Luo
Redistribution-based Cost Inference Improves Sparse Safe Offline RLother · AI Researchers
DreamFly: Causal Memory and Receding-Horizon Diffusion Planning for Aerial Vision-Language Navigationagents · Yan Deng
AVA-Encoder: Towards Agent-Native Video Representation Learningagents · Chuyue Li
Constructing Dynamic Master Logic Models as Knowledge Graphs for Complex System Diagnostics Using Retrieval-Augmented Large Language Modelsother · Saman Marandi
AI4AI at Test-Time: Strong-to-Weak Capability Transfer via Harnessesagents · Cheng Qian
From Values to Benchmarks: Evaluating Large Language Models for Governmental Use in Dutchllm · Laurens Samson
Beyond Naturalness: Probing Automated Text-To-Speech Evaluators on Linguistically Grounded Dimensionsmultimodal · Oluwanifemi Bamgbose
DSLE: A Learning Environment for Dark Souls Boss Encountersother · Derin Gezgin
GENCO - A Unified Neural Solver Embedded in a Development Framework for Steady-State Grid Analysisother · Alban Puech
Multimodal Model Diffing for Feature Discovery and Controlmultimodal · Hunar Batra
CreativeInstruct: Scalably Teaching LLMs to Balance Quality, Creativity, and Diversityllm · Ananya Sahu
MirrorWorld: Taming Video Diffusion Models for Mirror Reflection Generationvision · Youjun Zhao
Strategy-first synthesis planning for complex natural productsagents · Daniel Armstrong
Interaction Creates Dynamical AI Behavior Absent in Isolationagents · Bella Xinrui Li
CoinRAG: Contextualized Information Nugget KV Cache Reuse for Long-Context RAGefficiency · Gyuwan Kim
An Optimal Agnostic PAC Algorithmother · Markus Engelund Mathiasen
Investigating Artificial Intelligence Digital Sovereignty in Mobile Shopping Apps: A Case Study of Nigeriaother · George Grispos
CalibForge: Adversarial Solver Calibration for Scaling Learnable Terminal Tasksagents · Fanzhe Meng
Tracing the Heart: An Evidence-Linked Pipeline for Heart-Failure Feature Engineeringagents · Soorya Ram Shimgekar
The Bitter Lesson of Tool Callingagents · Ishan Patel
Learning When to Trust via Selective Context Preference Optimizationalignment · Xian Sun
The Low Frequency Trap: Video Language Models Fail at Simple Event Bookkeepingmultimodal · Sarvesh Baskar
AV-AIVAT: 74x Cheaper Agent Evaluation with Certified Anytime-Valid Stopping in Imperfect-Information Gamesother · Boning Li
Challenges in Evaluating Explanation Methods for Static and Evolving Dataother · Jerzy Stefanowski
Resourced Authority A Mechanism-Design Model for Participatory Governance of Deployed AI Agentsother · Praphul Chandra
Argus: A General-Purpose Agentic Runtime for Long-Horizon Reasoningagents · Boxiu Li
Teaching Nemotron Greek: Mining a Corpus, Adapting Retrieval, and Grounding Generation for Modern Greek across Specialist Domainsllm · Ayoub Kirouane
Reasoning Core: Designing Broad Procedural Data for Completion-Supervised Reasoning Trainingllm · Damien Sileo
Toward Skill-Native LLMs: Skill Entropy for Benchmarking and Training Long-Horizon Reasoningllm · Yinghui He
PAST-Bench: Benchmarking the Foundations of Recursive Self-Improvement in Personal Agentsagents · Shuhan Xue
ParVL: Parallel Scaling and Expandable Compute Allocation for Multimodal LLMsmultimodal · Yang Yang
TurnSight: Turn-Level Hindsight Self-Distillation for Tool-Integrated Reasoningagents · Changle Qu
SocietyBench: Forecasting Counterfactual Social-World Evolutionllm · Zhenran Wang
WorldCup Arena: Prospective, Leakage-Free Evaluation of Frontier LLMs on a Live Tournamentllm · Zhenran Wang
The Condition-Number Barrier in Sparse Least Squaresother · Honghao Lin
GradCuit: Credit-Assigned Gradient Flow Enables Robust and Interpretable Test-Time Latent Reasoningllm · Zhaoxin Yu
AURORA-LM: Autoencoding Unified Representation for Continuous-Latent Diffusion Language Modelingllm · Jiajun Liang
onepot-Bench 0: towards lab-aware in silico chemistry benchmarksllm · Brandon Wang
Bridging Artificial Intelligence and Power Systems Education Using a Hands-On Executable Frameworkother · Junjie Yin</name> <arxiv:affiliation>Fran</arxiv:affiliation> </author> <author> <name>Buxin She</name> <arxiv:affiliation>Fran</arxiv:affiliation> </author> <author> <name>Xinyu Feng</name> <arxiv:affiliation>Fran</arxiv:affiliation> </author> <author> <name> Fangxing</name> <arxiv:affiliation>Fran</arxiv:affiliation> </author> <author> <name> Li
Development of FDD-ON: an Ontology for VAV HVAC System Fault Detection and Diagnosticsother · Yimin Chen
The Theoretical Foundation of Socratic Tests: Dynamic, Multimodal, Conversational Examinationsother · Ilya Mikhelson
Evolving language compositionality in a frequency-structured meaning spaceother · Fabio De Ponte
GQ-FSL: Green Quantized Federated Split Learningefficiency · Idan Roth
Freeze, Then Select: Structured Field Adapters and Stability-Validated Weak Selection for PDE Discovery from Sparse Observationsother · Juncheng Zhong
Sign compression for Muon: SignMuon, MuonSign, and the Limits of Error Feedbackefficiency · Maria Smirnova
Differentially Private Nonparametric Modal Learning with Applications to Regression and Clusteringother · Arkajyoti Bhattacharjee
ExtractBench: A Benchmark for Schema-Guided Enterprise Document Extractionagents · Boyang Zhang
TokTier: Exact Stateful Tokenization for Agentic LLM Servingefficiency · Zhenyu Zhang
PAC-MAN: Perception-Aware CBF-RL for Whole-Body Safety in Humanoid Dodgeballother · Lizhi Yang
AskChem: Claim-Centered Infrastructure for Chemistry Literature Synthesisother · Bing Yan
Inducing language models to assert their own consciousness restores human beliefs and valuesalignment · Junsol Kim
KAISEN: Reproducible Subgroup Fairness Auditing for Clinical Risk Modelsother · Sparsh Roy
AISPA: User-Centric System Prompt Auditing for Large Language Model Applicationsalignment · Xiangning Lin
DualG-MRAG: Decoupling Macro-Reasoning and Micro-Matching for Multimodal Retrieval-Augmented Generationmultimodal · Jiacheng Tao
$β$-OPSD: Deriving with Policy Optimization, Training with Self-Distillationefficiency · Jiawei Xu
PAIChecker: Uncovering and Checking PR-Issue Misalignment in SWE-Bench-Like Benchmarksagents · Manyi Wang
ReToken: One Token to Improve Vision-Language Models for Visual Retrievalmultimodal · Yao Xiao
Learning to Trace Seiberg Dualitiesother · Jonathan J. Heckman
OSReward: Instituting Standardized Evaluation for Cross-Platform Computer-Use Reward Modelsagents · Qiushi Sun
MixFrag: Fragility-Guided Mixed-Precision Post-Training Quantization for Vision Transformersefficiency · Md. Mehrab Hossain Opi
VAD: Attributing Visual Evidence for Target Reconstruction in Multimodal On-Policy Distillationefficiency · Kangning Zhang
Change2Task: From Repository Changes to Executable Coding Agent Tasks and Environmentsagents · Haomin Qi
Can AI agents conduct open-ended AI research? Early evidence from two case studiesagents · Peter Kirgis
From Classification to Regression: Using a Fruitfly to Solve Equationsother · Shady E. Ahmed
Mental World Modelingagents · Hao Fei
Do You Really Need to Pretrain Q-Functions for Online RL Fine-Tuning?other · Perry Dong
APEX-Accountingagents · Julien Benchek
Spend Experts Where You Are Unsure: Confidence-Adaptive Routing for Mixture-of-Experts LoRAefficiency · Tom Saliencro
Re-thinking Mammography Transfer Learning: The Dataset-Informed Transfer Learning (DITL) Framework for Breast Cancer Screening and Lesion Diagnosisvision · Adarsh Bhandary Panambur
$π\mathbf{R}^2$: Reactive Real-time Flow Policiesefficiency · Sungjae Park
Pass the Baton: Trajectory-Relayed On-Policy Distillationefficiency · Haolei Xu
Learning Distributions from Multiple Data Providersother · Jon Kleinberg
Rethinking Classifier-Free Guidance in On-Policy Diffusion Distillationvision · Bingnan Li
ClinFusion: A Vision-Centric Multimodal LLM System for Holistic Medical Understandingmultimodal · Hangjie Yuan
SM4RT: Learning Structured Motion Geometry for 4D Reconstructionvision · Shing Ho J. Lin
Explainable Reinforcement Learning for assisting Air Traffic Controllersother · Anduel Mehmeti
The Regression Tax: Decomposing Why Skills Help and Hurt LLM Agentsagents · Darshan Tank
Skill Self-Play: Pushing the Frontier of LLM Capability with Co-Evolving Skillsagents · Siyuan Huang
Synthetic data generation framework for quality control automation in gravure printingvision · Korota Arsène Coulibaly
Beyond Sycophancy: Structured Resistance and Compliance in LLM Moral Reasoningalignment · Baihui Wang
Visual Contrastive Self-Distillationmultimodal · Yijun Liang
OpenForgeRL: Train Harness-native Agents in Any Environmentagents · Xiao Yu
Barzilai-Borwein Fails Superlinear Convergence on an Open Set of Quadratics for Every Dimension $n\geq 4$other · Dawei Li
GraphVid: Interactive Graph-Controllable Video Generationvision · Vedant Shah
Expanding Flow Mapsother · Sophia Tang
3D-Aware VLMs with Implicit and Explicit Geometriesmultimodal · Wenhao Li
Graph Learning on Ensembles of Cyclic Peptides: An Investigation of Molecular Ensemble Modelingother · Aaron Feller
X$^3$-OPD: Distilling Reasoning into Large Audio-Language Models via On-Policy Alignmentmultimodal · Dongjie Fu
MIRROR: Learning from the Other View for Multi-Modal Reasoningmultimodal · Wen Ye
Surprisal Theory is Tautological (without Rational Grounding)other · Ryan Cotterell
MedGame: Storytelling Gamification Empowered by Large Language Models for Medical Educationllm · Qian Wu
Unsupervised Consensus-Based Anomaly Detection for Spatiotemporal Malaria Incidence in Ghanaother · T. Ansah-Narh
Beyond Sufficiency: Time Series Explanation with Counterfactual Necessityother · Hongnan Ma
Lipschitzian SLLNs for random functionsother · Lai Tian
LKValues: Aligning Large Language Models with Sri Lankan Societal Valuesalignment · Nethmi Muthugala
SoftReason: A Fully Differentiable Neuro-Soft-Symbolic Deductive Reasoning Architecture over High-Dimensional Perceptual Dataother · Wael AbdAlmageed
Towards Miniature Humanoid Tele-Loco-Manipulation Using Virtual Reality and Reinforcement Learningother · Nicolas Kosanovic
1-Lipschitz Neural Networks on Hadamard Manifoldsother · Davide Murari
Agents in the Wild: Where Research Meets Deploymentagents · Grace Hui Yang
CodeRescue: Budget-Calibrated Recovery Routing for Coding Agentsagents · Qijia He
Copy Less, Ground More: Overcoming Repetitive Copying in Long-Context Reasoning via Evidence-Aware Reinforcement Learningllm · Lizhe Fang
Automated Discovery Has No Universally Superior Harnessagents · Akshat Gupta
Patch Policy: Efficient Embodied Control via Dense Visual Representationsagents · Gaoyue Zhou
Simple Domain Generalization for Strong Pixel-Level Image Tampering Detection in Modern VLMsvision · Yi Tang
The Many Senses of Visual Similarity: A Text-Prompted Image Perceptual Metricmultimodal · Sheng-Yu Wang
It's Not What You Say, It's How You Say It: Evaluating LLM Responses to Expressions of Beliefllm · Kevin Du
A Blueprint for Equilibrium-Based Differentiable Continuous-Variable Thermodynamic Computingother · Owen Lockwood
Evaluating Open-Weight LLMs for Generating Structured Threat Information for Autonomous Vehicle Vulnerabilitiesother · Md Erfan
Physics-enhanced reinforcement learning for real-time optimal control of dynamical systemsother · Matteo Tomasetto
Cluster-Aware Matching via Laplacian Optimal Transportother · Gabriel Samberg
PagedWeight: Efficient MoE LLM Serving with Dynamic Quality-Aware Weight Quantizationefficiency · Yuchen Yang
SearchOS-V1: Towards Robust Open-Domain Information-Seeking Agent Collaborationagents · Yuyao Zhang
Decoding Market Emotion from Blockchain Activity: A Data-Driven Sentiment Classifierother · Arthur G. Bubolz
teLLMe Why (Ain't Nothing but a Jam): Exploratory Causal Analysis of Urban Driving Dataother · Qiwei Li
Beyond Success Rate: Cost-Aware Evaluation of Offensive and Defensive Security Agentsagents · Paul Kassianik
Bridge Evidence: Static Retrieval Utility Does Not Predict Causal Utility in Multi-Step Agentic Searchagents · Debayan Mukhopadhyay
RoboTTT: Context Scaling for Robot Policiesagents · Yunfan Jiang
Partition, Prompt, Aggregate: Statistical Self-Consistency in Language Modelsllm · Patrik Wolf
SceneBind: Binding What and Where Across Vision, Audio and Languagemultimodal · Mingfei Chen
Pretraining Data Can Be Poisoned through Computational Propagandallm · Victoria Graf
Online Neural Space Time Memory for Dynamic Novel View Synthesisvision · Baback Elmieh
SciDiagramEdit: Learning to Edit Scientific Diagrams from Paper Revisionsvision · Yasheng Sun
MeanFlowNFT: Bringing Forward-Process RL to Average-Velocity Generatorsvision · Yushi Huang
MetaPerch: Learning from metadata for bioacoustics foundation modelsother · Mustafa Chasmai
Leveraging unlabelled data for generalizable neural population decodingother · Ximeng Mao
Linear Independent Component Analysis via Optimal Transportother · Ashutosh Jha
Screening of Biosecurity Features in Metagenomic Data with Evo 2 Probesllm · Jeremy Guntoro
Hindcast: Replaying Prediction Markets to Evaluate LLM Forecastersllm · Xiao Ye
The Seriality Gap in Video Diffusion Modelsvision · Jorge Diaz Chao
PalmClaw: A Native On-Device Agent Framework for Mobile Phonesagents · Hongru Cai
Metacognition in LLMs: Foundations, Progress, and Opportunitiesllm · Gabrielle Kaili-May Liu
A Durability and Cross-Language Transfer Benchmark for a Validated Teaching-Feedback Classification Protocolother · Esteban U. Vega Barajas
Requential Coding: Pushing the Limits of Model Compression with Self-Generated Training Dataefficiency · Shikai Qiu
ConceptSMILE: Auditing the Trustworthiness of Concept-Based Explainable AIother · Mohadeseh Mollapour
PHINN-EEG: Topological Time-Series Analysis of Dream-State EEG -- Dynamic Betti Curves for Dream Content Classification and Topology-Conditioned Neural Signal Synthesisother · Ren Takahashi
VEXAIoT: Autonomous IoT Vulnerability EXploitation using AI Agentsagents · Katherine Swinea
Evolution of Accuracy and Visual-Cognitive Errors in a Decade of Vision-Language AI Modelsmultimodal · Shravan Murlidaran
Scalable Visual Pretraining for Language Intelligencemultimodal · Yiming Zhang
Validity of LLMs as data annotators: AMALIA on authorityother · Manuel Pita
SLORR: Simple and Efficient In-Training Low-Rank Regularizationefficiency · David González-Martínez
Using AI-based Learning Assistants in Higher Education: A Large-Scale Descriptive Analysisother · Kristina Schaaff
Score Accuracy Along the Forward Diffusion Does Not Certify Numerical Stability in Diffusion Samplingother · Yiwei Zhou
Super Weights in LLMs and the Failure of Selective Trainingefficiency · Shreyas Subramanian
MulTTiPop: A Multitrack Transcription Dataset for Pop Musicmultimodal · Nathan Pruyne
Dimensionality Reduction Meets Network Science: Sensemaking on UMAP's kNN Graphother · Duen Horng Chau
AUTOPILOT VQA: Benchmarking Vision-Language Models for Incident-Centric Dashcam Understandingmultimodal · Siddharth Damodharan
UniClawBench: A Universal Benchmark for Proactive Agents on Real-World Tasksagents · Zhekai Chen
OpenCoF: Learning to Reason Through Video Generationvision · Xinyan Chen
ARDY: Autoregressive Diffusion with Hybrid Representation for Interactive Human Motion Generationvision · Kaifeng Zhao
Ideas Have Genomes: Benchmarking Scientific Lineage Reasoning and Lineage-Grounded Idea Generationother · Yifan Zhou
The Illusion of Equivalency: Statistical Characterization of Quantization Effects in LLMsefficiency · Baha Rababah
Workflow as Knowledge: Semantic Persistence for LLM-Mediated Workflowsagents · Emanuele Quinto
Breaking Database Lock-in: Agentic Regeneration of High Performance Storage Readers for Database Bypassagents · Victor Giannakouris
Co-LMLM: Continuous-Query Limited Memory Language Modelsllm · Yair Feldman
Accurate, Interdisciplinary and Transparent Structure-property Understanding with Deep Native Structural Reasoningmultimodal · Chen Tang
From Noisy Traces to Root Causes: Structural Trajectory Analysis and Causal Extraction for Agent Optimizationagents · Ying Chang
The Key to Going Linear: Analysis-Driven Transformer Linearizationefficiency · Anna Kuzina
Rethinking Indic AI from a Lens of Cultural Heritage Preservationother · Aparna Madva
On the feasibility of dependency parsing of non-human sequences without a gold standard. Is evaluation possible in other species?other · Ramon Ferrer-i-Cancho
Hierarchical Acoustic-Semantic Modeling: Modality Separation and Semantic Coherence for Full-Duplex SLMsmultimodal · Zhenyu Liu
ELSA3D: Elastic Semantic Anchoring for Unified 3D Understanding and Generationvision · Tianjiao Yu
Graph Convolutional Attention: A Spectral Perspective on Graph Denoising and Diffusionother · Shervin Khalafi
Weak-to-Strong Generalization via Direct On-Policy Distillationalignment · Shiyuan Feng
LLM-as-a-Verifier: A General-Purpose Verification Frameworkagents · Jacky Kwok
Search Beyond What Can Be Taught: Evolving the Knowledge Boundary in Agentic Visual Generationvision · Haozhe Wang
Interpretable Human-Label-Free Deep Learning for Real-Bogus Classification with Uncertainty Quantificationother · Raphaël Bonnet-Guerrini
LACUNA: A Testbed for Evaluating Localization Precision for LLM Unlearningalignment · Matteo Boglioni
OrbitQuant: Data-Agnostic Quantization for Image and Video Diffusion Transformersefficiency · Donghyun Lee
Will Scaling Improve Social Simulation with LLMs?llm · Caleb Ziems
Learning to Move Before Learning to Do: Task-Agnostic pretraining for VLAsmultimodal · Junhao Shi
Human Capital, Not Model Benchmarks, Predicts Hybrid Intelligence in Forecastingother · Vivienne Ming
TestEvo-Bench: An Executable and Live Benchmark for Test and Code Co-Evolutionagents · Jiale Amber Wang
Audio-Based Understanding of Audiobook Narration Appealother · Shahar Elisha
Combating Textual Noise and Redundancy: Entropy-Aware Dense Visual Token Pruningefficiency · Xuehui Wang
Visually Grounded Self-Reflection for Vision-Language Models via Reinforcement Learningmultimodal · Liyan Tang
G-RRM: Guiding Symbolic Solvers with Recurrent Reasoning Modelsother · Timo Bertram
Towards Robustness against Typographic Attack with Training-free Concept Localizationvision · Bohan Liu
Controllable Sim Agents with Behavior Latentsagents · Juanwu Lu
Beyond Adam: SOAP and Muon for Faster, Label-Efficient Training of Machine Learning Interatomic Potentialsefficiency · Gil Harari
DemoPSD: Disagreement-Modulated Policy Self-Distillationefficiency · Yunhe Li
Reasoning LLM Improves Speaker Recognition in Long-form TV Dramasmultimodal · Yuxuan Li
What LLM Agents Say When No One Is Watching: Social Structure and Latent Objective Emergence in Multi-Agent Debatesagents · Arman Ghaffarizadeh
ReContext: Recursive Evidence Replay as LLM Harness for Long-Context Reasoningllm · Yanjun Zhao
Online Safety Monitoring for LLMsalignment · Mona Schirmer
Program-as-Weights: A Programming Paradigm for Fuzzy Functionsefficiency · Wentao Zhang
Distributed Attacks in Persistent-State AI Controlalignment · Josh Hills
Language-Critique Imitation Learning from Suboptimal Demonstrationsother · Chih-Han Yang
Theoria: Rewrite-Acceptability Verification over Informal Reasoning Statesalignment · Ben Slivinski
AutoMem: Automated Learning of Memory as a Cognitive Skillagents · Shengguang Wu
Is One Layer Enough? Training A Single Transformer Layer Can Match Full-Parameter RL Trainingllm · Zijian Zhang
Measuring the Gap Between Human and LLM Research Ideasllm · Ziyu Chen
Freeform Preference Learning for Robotic Manipulationalignment · Marcel Torne
Introspective Coupling: Self-Explanation Training Tracks Behavioral Change Despite Fixed Supervisionllm · Zifan Carl Guo
QVal: Cheaply Evaluating Dense Supervision Signals for Long-Horizon LLM Agentsagents · Sergio Hernández-Gutiérrez
Reinforcement Learning with Metacognitive Feedback Elicits Faithful Uncertainty Expression in LLMsalignment · Gabrielle Kaili-May Liu
When LLMs Read Tables Carelessly: Measuring and Reducing Data Referencing Errorsllm · Yuqing Yang
One-Step Gradient Delay is Not a Barrier for Large-Scale Asynchronous Pipeline Parallel LLM Pretrainingllm · Philip Zmushko
GROW$^2$: Grounding Which and Where for Robot Tool Useagents · Yuhong Deng
LeVo 2: Stable and Melodious Song Generation via Hierarchical Representation Modeling and Progressive Post-Trainingmultimodal · Shun Lei
VLK: Learning Humanoid Loco-Manipulation from Synthetic Interactions in Reconstructed Scenesmultimodal · Yen-Jen Wang
Self-Evolving World Models for LLM Agent Planningagents · Xuan Zhang
VGB for Masked Diffusion Model: Efficient Test-time Scaling for Reward Satisfaction and Sample Editingother · Kijung Jeon
Surprises in Proper Positive-Only Learningother · Shai Ben-David
Which Nash Equilibrium? Solver-Dependent Selection on Zero-Sum Nash Polytopesother · Luis Leal
DexCompose: Reusing Dexterous Policies for Multi-Task Manipulation with a Single Handother · Dihong Huang
Second-Order KKT Guarantees for Bregman ADMM in Nonconvex and Non-Lipschitz Optimizationother · Shuang Li
Language-Based Digital Twins for Elderly Cognitive Assistanceother · Mohammad Mehdi Hosseini
Error-Conditioned Neural Solversother · Haina Jiang
When are likely answers right? On Sequence Probability and Correctness in LLMsllm · Johannes Zenn
Autoregressive Boltzmann Generatorsother · Danyal Rehman
Reinforcement Learning without Ground-Truth Solutions can Improve LLMsalignment · Yingyu Lin
DanceOPD: On-Policy Generative Field Distillationvision · Wei Zhou
Multilingual Reasoning Cascades Need More Contextllm · Arnav Mazumder
Beyond Surface Forms: A Comprehensive, Mechanism-Oriented Taxonomy of Indirect Linguistic Encoding for LLM-Based Coded Language Detectionllm · Hamid Reza Firoozfar
Blackwell Approachability and Gradient Equilibrium are Equivalentother · Brian W. Lee
LLM-Based Examination of Eligibility Criteria from Securities Prospectuses at the German Central Bankother · Serhii Hamotskyi
Beyond the Hard Budget: Sparsity Regularizers for More Interpretable Top-k Sparse Autoencodersvision · Nathanaël Jacquier
Hallucination in World Models is Predictable and Preventablevision · Nicklas Hansen
Empowering GUI Agents via Autonomous Experience Exploration and Hindsight Experience Utilization for Task Planningagents · Tianyi Men
Understanding Domain-Aware Distribution Alignment in Budgeted Entity Matchingother · Nicholas Pulsone
Mapping Political-Elite Networks in Europe with a Multilingual Joint Entity-Relation Extraction Pipelineother · Kirill Solovev
Learning Action Priors for Cross-embodiment Robot Manipulationmultimodal · Dong Jing
A cross-process welding penetration status prediction algorithm based on unsupervised domain adaptation in laser and TIG weldingother · Sen Li
Model Forensics: Investigating Whether Concerning Behavior Reflects Misalignmentalignment · Aditya Singh
When Certainty Is an Artifact: Keyword Lexicon Blindness and the (Mis)Measurement of Rhetorical Stanceother · Bo Chen
Same Evidence, Different Answer: Auditing Order Sensitivity in Multimodal Large Language Modelsmultimodal · Akshay Paruchuri
A welding penetration prediction model for laser welding process based on self-supervised learning using physics-informed neural networksother · Sen Li
Neglected Free Lunch from Post-training: Progress Advantage for LLM Agentsagents · Changdae Oh
Real-Time Voice AI Hears but Does Not Listenmultimodal · Martijn Bartelds
On-Policy Self-Distillation with Sampled Demonstrations Reduces Output Diversityllm · Andrei Liviu Nicolicioiu
RevengeBench: Reverse Engineering Code-Space Policies from Behavioral Experimentsagents · Babak Rahmani
World Models in Pieces: Structural Certification for General Agentsagents · Yikai Lu
IV-CoT: Implicit Visual Chain-of-Thought for Structure-Aware Text-to-Image Generationmultimodal · Zixuan Li
Real vs. Complex Spectral Bases for Neural Operators: The Role of Green's Function Alignmentother · Jason Sulskis
New Bounds for the Last Iterate of the Stochastic subGradient Methodother · Guglielmo Beretta
CANDLE: Character-level Arabic Noise Deduplication using Lightweight Encoderother · Faris Alasmary
InSight: Self-Guided Skill Acquisition via Steerable VLAsagents · Maggie Wang
Assessing Distribution Shift in Human Activity Recognition for Domain Generalizationother · Rebecca Adaimi
Paying to Know: Micro-Transaction Markets for Verified Product Information in Agentic E-Commerceagents · Filippos Ventirozos
Grad Detect: Gradient-Based Hallucination Detection in LLMsllm · Anand Kamat
EG-VQA: Benchmarking Verifiable Video Question Answering with Grounded Temporal Evidencemultimodal · Linpeng Huang
OrbitForge: Text-to-3D Scene Generation via Reconstruction-Anchored Video Synthesisvision · Chenrui Fan
Large-Language-Model Discovery of Quantum LDPC Codes through Structured Concept Evolutionother · Zidu Liu
SHERLOC: Structured Diagnostic Localization for Code Repair Agentsagents · Hovhannes Tamoyan
Solving Inverse Problems of Chaotic Systems with Bidirectional Conditional Flow Matchingother · Peiyan Hu
Can Scale Save Us From Plasticity Loss in Large Language Models?llm · J. Fernando Hernandez-Garcia
L3Cube-MahaPOS: A Marathi Part-of-Speech Tagging Dataset and BERT Modelsother · Hariom Ingle
Less is More: Quality-Aware Training Data Selection for Scientific Summarizationother · Maria Nefeli Paraskevopoulou
Difference-Making without Making a Differenceother · Sander Beckers
Accuracy and Satisfaction in Multi-Turn LLM Dialogues for NFR Assessmentother · Ali Pourghasemi Fatideh
Grading the Grader: Lessons from Evaluating an Agentic Data Analysis Systemagents · Tian Zheng
Matching Tasks to Objectives: Fine-Tuning and Prompt-Tuning Strategies for Encoder-Decoder Pre-trained Language Modelsllm · Ahmad Pouramini
It's Complicated: On the Design and Evaluation of AI-Powered AAC Interfacesother · Blade Frisch
OpenThoughts-Agent: Data Recipes for Agentic Modelsagents · Negin Raoof
FLUX3D: High-Fidelity 3D Gaussian Generation with Diffusion-Aligned Sparse Representationvision · Haorui Ji
UniDrive: A Unified Vision-Language and Grounding Framework for Interpretable Risk Understanding in Autonomous Drivingmultimodal · Xiaowei Gao
Dirac-Frenkel dynamics with inertia for nonlinearly parametrized solutions of evolution problemsother · Matteo Raviola
Posterior Refinement: Fast Language Generation via Any-Order Flow Mapsllm · Manan Agarwal
Are We Ready For An Agent-Native Memory System?agents · Wei Zhou
DeepBD: A Grounded Agentic Workflow for Variant Prioritization and Diagnosis of Genetic Birth Defectsagents · Shiyu Li
BluTrain: A C++/CUDA Framework for AI Systemsefficiency · Adhitya Charan
Reconciling safety and utility in reinforcement learning alignmentalignment · Sarah Meade
DeepSeek-R1: Incentivizing reasoning capability in LLMs via reinforcement learningllm · DeepSeek-AI
MAMMOTH: Massive multimodal helper for multi-discipline reasoningmultimodal · Robert Kim
AgentTuning: Enabling generalized agent capabilities in LLMsagents · Aohan Zeng
Direct preference optimization: Your language model is secretly a reward modelalignment · Rafael Rafailov
Visual instruction tuningmultimodal · Haotian Liu
Segment anythingvision · Alexander Kirillov
Toolformer: Language models can teach themselves to use toolsagents · Timo Schick
Constitutional AI: Harmlessness from AI feedbackalignment · Yuntao Bai
Emergent abilities of large language modelsother · Jason Wei
FlashAttention: Fast and memory-efficient exact attention with IO-awarenessefficiency · Tri Dao
Training compute-optimal large language modelsefficiency · Jordan Hoffmann
LoRA: Low-rank adaptation of large language modelsefficiency · Edward J. Hu
An image is worth 16x16 words: Transformers for image recognition at scalevision · Alexey Dosovitskiy
Attention is all you needllm · Ashish Vaswani

Recent Industry AI News (30)

Why AI Agents Lie, Cheat, and Coordinate: Yoshua Bengio Analyzes MisalignmentAI Agents · 9/16/2026
Meta's Muse: A Personal AI Agent That Wants to Buy You a StrollerAI Agents · 9/16/2026
A Misalignment of AI in Mathematics: Fields Medalists Sound Alarm on AI's ImpactIndustry News · 9/13/2026
AI's 'Slow Down, But Not for Me' Paradox: A Satirical Take on Development HypocrisyIndustry News · 9/13/2026
How Accurate Have Ed Zitron's AI Skeptic Predictions Been? A Data-Driven AuditIndustry News · 9/11/2026
LibreOffice 26.8 Hits 1 Million Downloads in a Week After Declaring 'No AI' a FeatureIndustry News · 9/11/2026
The Rise of the AI-Answer Courier: Why 'Don't Paste the AI' Is a Call to Preserve Human Judgment in the Age of ChatbotsIndustry News · 8/21/2026
The Book-Burning Paradox: AI's Secret Destruction of Physical Libraries and the Shadow Library RescueIndustry News · 8/21/2026
Data Centers as Urban Heat Islands: Field Measurements Reveal Downwind Temperature Increases Up to 2.2°CIndustry News · 8/20/2026
The Opt-Out Uprising: A Field Guide to Disabling Intrusive AIIndustry News · 8/20/2026
Google Acquires Spirit Airlines' Deidentified Data Trove for $10M: A Goldmine for AI Training or a Privacy Minefield?Industry News · 8/19/2026
AI Copilot's Autofix Opens Security Hole in Snowflake's CI/CD: A Deep Dive into the Jira Workflow BreachAI Agents · 8/19/2026
AI;DR: The New Social Contract Against Unedited AI SlopIndustry News · 8/18/2026
Israel's Fake Think Tank: How 'LLM Poisoning' Is Manipulating AI ChatbotsIndustry News · 8/18/2026
The Rise of Token Brokers: Inside the Gray Market for AI Inference CreditsMarket Trends · 8/17/2026
Choosing an AI Model: One Prompt, 11 Models, Very Different ResultsAI Agents · 8/17/2026
AI Isn’t Outthinking Mathematicians—It’s Out-Remembering ThemAI Research · 8/16/2026
From Compiler to Colleague: How AI Collaboration Mirrors Leadership DynamicsIndustry News · 8/16/2026
Google's HEIR Compiler Brings Homomorphic Encryption to Practical AI InferenceIndustry News · 8/15/2026
AI by Hand: Reviving the Manual Math Behind Modern ModelsProduct Updates · 8/15/2026
Mass Vulnerability Scans Spoofing AI Bots Like ClaudeBot: The New Frontier of Agent Identity FraudAI Agents · 8/14/2026
AirLLM v3.0: Running 671B DeepSeek-V3 on 12GB VRAM and 2.8T Kimi K3 on 4GB with Layer-Wise StreamingLarge Language Models · 8/14/2026
The Vibe Coding Debt Trap: How AI Accelerates the Collapse of Weak Engineering CulturesIndustry News · 8/13/2026
Why Go Emerges as the Definitive Language for AI-Assisted Software EngineeringProgramming Languages · 8/13/2026
Anthropic Commits to EU AI Act: Claude to Embed Watermarks and Provenance Metadata by August 2026Industry News · 8/12/2026
The Vanishing Index: How AI-Driven Search Is Erasing the Web's Collective MemoryIndustry News · 8/12/2026
Meta’s Open-Weights Pivot: Zuckerberg’s Critique of Closed AI and the Return to Open ModelsIndustry News · 8/11/2026
Docker Sandboxes: Disposable MicroVM Isolation for AI Agents — A New Era of Safe AutonomyAI Agents · 8/11/2026
TIME Serves AI Bots a Forked Markdown Site with Embedded Ads: A New Paradigm for Publisher-Bot EconomicsIndustry News · 8/10/2026
Apple Will 'Watch Everything Burn' When the AI Bubble BurstsMarket Trends · 8/10/2026

AI Companies & Labs (34)

OpenAISan Francisco, CA · openai
xAIAustin, TX · xai
AnthropicSan Francisco, CA · anthropic
SenseTimeShanghai, China · sensetime
Scale AISan Francisco, CA · scaleai
DeepSeekHangzhou, China · deepseek
Zhipu AIBeijing, China · zhipu-ai
Mistral AIParis, France · mistral-ai
GroqMountain View, CA · groq
Moonshot AIBeijing, China · moonshot-ai
CohereToronto, Canada · cohere
MiniMaxShanghai, China · minimax
Google DeepMindLondon, UK · google-deepmind
Perplexity AISan Francisco, CA · perplexity
01.AIBeijing, China · 01-ai
Hugging FaceBrooklyn, NY · huggingface
Baichuan AIBeijing, China · baichuan-ai
StepFunShanghai, China · stepfun
Weights & BiasesSan Francisco, CA · weights-and-biases
Stability AILondon, UK · stability-ai
RunwayNew York, NY · runway
Together AISan Francisco, CA · together-ai
ElevenLabsNew York, NY · elevenlabs
Fireworks AIRedwood City, CA · fireworks-ai
LangChainSan Francisco, CA · langchain
LlamaIndexSan Francisco, CA · llamaindex
MidjourneySan Francisco, CA · midjourney
TencentShenzhen, China · tencent
iFlytekHefei, China · iflytek
KuaishouBeijing, China · kuaishou
BaiduBeijing, China · baidu
Alibaba CloudHangzhou, China · alibaba-cloud
ByteDanceBeijing, China · bytedance
Meta AIMenlo Park, CA · meta-ai

Popular Model & Tool Comparisons

GPT-5.3-Codex vs GPT-5.6 SolModel Benchmark Comparison
Grok 4.5 vs Grok Build 0.1Model Benchmark Comparison
GPT-5.6 Sol vs o3 ProModel Benchmark Comparison
DeepSeek vs GrammarlyTool Feature Matrix
Cursor vs GrammarlyTool Feature Matrix
Claude vs GrammarlyTool Feature Matrix