EAPO: Entropy-Driven Adaptive Positive-Negative Sample Weighting for Policy Optimization …
Explorar
Noticias de IA
27413 elementos — filtrados, clasificados y sin duplicados
DenoiseRL: Bootstrapping Reasoning Models to Recover from Noisy Prefixes
SafeMed-R1: Clinician-Audited Safety and Ethics Alignment for Medical Large Language Mode…
Where Rollouts Begin: Low-Load, High-Leverage First-Token Diversification for RLVR
DynaSchedBench: Calibrated Dynamic Scheduling Benchmarks and Observability Paradox in LLM…
Global Policy-Space Response Oracles for Two-Player Zero-Sum Games
Personalized Observation Normalization for Federated Reinforcement Learning in Simulation…
AI, Take the Wheel: What Drives Delegation and Trust in Human-Computer Cooperative Questi…
DeepSciVerify: Verifying Scientific Claim--Citation Alignment via LLM-Driven Evidence Esc…
Agentic Active Omni-Modal Perception for Multi-Hop Audio-Visual Reasoning
Deconstructing Spatial Complexity: Hierarchical Decomposition for LLM Spatial Reasoning
Verifiable Benchmarking of Long-Horizon Spatial Biology
MTAVG-Bench 2.0: Diagnosing Failure Modes of Cinematic Expressiveness in Multi-Talker Aud…
MIRA: A Bilingual Benchmark for Medical Information Response Audit
Learning after COVID-19 and the ICT career aspirations: Are students entering the AI era …
Human-AI Collaboration for Estimating Scientific Replicability
Mathematical Modelling of Ethical AI Use in Higher Education: A Coordination Game Framewo…
From Talking to Singing: A New Challenge for Audio-Visual Deepfake Detection
Ligand-Conditioned Discrete Diffusion for Protein Sequence-Structure Co-Design
REC-CBM: Rubric-Aware Error-Correction Concept Bottleneck Models for Trustworthy Open-End…
CubePart: An Open-Vocabulary Part-Controllable 3D Generator
C-MIG: Multi-view Information Gain-based Retrieval-Augmented Generation for Clinical Diag…
LLM-assisted sentiment analysis for integrated computational and qualitative mixed method…
GraD-IBD: Graph Representation Learning from Diagnosis Trajectories for Early Detection o…
SkillGrad: Optimizing Agent Skills Like Gradient Descent
Hierarchical Prompt-Domain Control and Learning for Resource-Constrained Agentic Language…
You Are in Control of Your State: Why Human Outcomes Are Controllable Through Causal Stat…
Detecting and Mitigating the Correct-Answer Extinction Window in Test-Time Reinforcement …
STARS: Spike Tail-Aware Relational Synthesis for ANN-to-SNN Data-Free Knowledge Distillat…
CiteCheck: Retrieval-Grounded Detection of LLM Citation Hallucinations in Scientific Text