Coverage, Not Targeting: A Structural Regime in Multi-Turn Agent Credit Assignment
Explorar
Noticias de IA
27413 elementos — filtrados, clasificados y sin duplicados
Sparse Readout Prism: Explaining Logit-Lens Scores in Features Instead of Tokens
Fair Stable Matching: A Nash Social Welfare Approach
Disease Burden over Skin Tone: Decomposing the Dermatology-AI Generalization Gap
Training a coding model to paint watercolours with TRL and OpenEnv
Fine-tuning a 350M Model for Better Structured Outputs in 100 GRPO Steps
These Russian Mathematicians Taught AI Models How to Talk to Each Other Without Using Wor…
Motional and MIT AI explains self-driving car decisions
Three sites made 215,128 “best software” pages for AI. Perplexity cites them
ConvDeck: Conversational Paper-to-Slide Generation via Stage-Specific User Feedback
Figures as Programs: Recursive Generation of Editable Scientific Figures
AI Should Not Only Be Helpful. It Should Be Contingent. Artificial Intimacy, Sycophancy, …
Escaping Redundant Reasoning: Structure-Aware Search for Inference-Time LLMs
Autoresearch for Marketplace Catalogs: From Legacy Forms to AI-Native Matching
One Prompt Is Enough: Watermark Laundering Through Foundation Image Models
ReDeck: Step-Level Render-Grounded Refinement for Document-to-Slide Generation
Causal Probing for Internal Visual Representations in Multimodal Large Language Models
SlideBank: A Persistent Hierarchical Evidence Bank for Consistent Whole-Slide Reasoning
FractalNet-Based Heterogeneous Federated Learning for Orbital Edge Intelligence in Satell…
Think Like a Doctor: Conversational Diagnosis through the Exploration of Diagnostic Knowl…
LLM-Driven Autonomous Vehicles Inherit Human Driver Biases in Pedestrian Yielding: Result…
Value Over Language Model: Detecting Original Contribution in Writing
Compositional Machine Design as Program Synthesis with LLMs
Ontology-Guided Neuro-Symbolic Inference: Grounding Language Models with Mathematical Dom…
Making Prospective Memory SLM-Shaped: Typed Intention Stores for Small-Model Agents
Harness-of-Harness: Multi-Day Autonomous Software Development with Continual Improvement
Rethinking Learnability in Offline Data-driven Optimization
TempCloze: Can Video-LLMs Identify the Missing Middle?
KGFR: A Foundation Retriever for Generalized Knowledge Graph Question Answering
Provably Safe Sim-to-Real Transfer