(V)LMs generalize beyond surface co-occurrence: Evidence from cross-modal number agreement
Explorar
Noticias de IA
27413 elementos — filtrados, clasificados y sin duplicados
REFACTOR-VLA: Unsupervised Library Learning of Typed Motor Programs
The efficient frontier of LLM inference
BenchMIRT: What are LLM benchmarks actually measuring?
MiniMax Eyes AGI Milestone Tied to 1% of Global GDP Output
Hyper3-CLIP: Hierarchy-Conditioned Hyperbolic Vision-Language Training
AI Scientist Mission Control (AIMC): Visual Analytics for Human Oversight of Autonomous S…
AutoScientist-Quant: Self-Evolving Coding Agents for Automatic Research in Quantitative I…
SGE: Semantically-Guided Exploration for Unstructured Environments via Image-Space Waypoi…
Reward-Oracle MCTS for Formal Theorem Proving: Sample-Efficient Search and the Need for K…
Self-Specialized Teachers for Domain Post-Training
InternReviewer & InternAdvocate: Objective Reward and Evaluation for Agentic Reinforcemen…
Preference Elicitation for Policy Optimization and Application to Aligning Heart Transpla…
Arabic Safety Alignment as Selective Refusal: An Empirical Study of SFT, DPO, and Guard C…
VFR-Audit: Verdict-Level Reliability for Fairness Audits in Hospital Length-of-Stay Predi…
Detecting and Repairing Hallucinations in Retrieval-Augmented Generation
PyKEEN-NSX: A Modular Framework for Static, Dynamic and Schema-Aware Negative Sampling in…
Evaluating LLM-based AI agents integrated with materials synthesis tools: the case of ato…
GarmentWeaver: Schema-Aware Structured Synthesis for Multimodal Sewing Patterns
Safe to Resume? Breaking Execution Continuity of Agent Execution via Rollback
TPvG: A Moral Decision Framework for Large Language Models from One-Shot to Sequential Fe…
Game-Agnostic Value Functions through Automatic JSON Feature Extraction
RAGDiffusion++: From Macro-Retrieval to Micro-Fidelity Alignment for Garment Generation
LaMoC: Loss-Aware Modular Compression for LLMs
Rethinking the Test-Time Prompt Tuning Objective from the Perspective of Calibration
Spec2Twin-Chain: Orchestrating Bi-Level Optimization with LLMs for Blockchain Digital Twi…
Dense Clinical Contrasts Enhance Medical Knowledge Updating in Large Language Models
Disentangling Representation using Attributes-based Gaussian Estimation for Medical Sound…
Spatial Matryoshka Training for Multi-Granularity Visual Document Retrieval
Balance of Benchmarks: Semantic Density Reweighting for Benchmark Multiplicity and Task-C…