会员服务
Failure Modes of Deep Multi-Agent RL in Asynchronous Pricing: Reproducible Triggers, Trace Diagnostics, and a Partial Fix
Arxiv
0+阅读 · 6月3日
Stress-Testing Neural Network Verifiers with Provably Robust Instances
Arxiv
0+阅读 · 5月16日
Samudra 2: Scaling Ocean Emulators across Resolutions
Arxiv
0+阅读 · 5月24日
VoLo: A Physical Orchestrator for Open-Vocabulary Long-Horizon Manipulation
Arxiv
0+阅读 · 6月5日
Cascading Hallucination in Agentic RAG: The CHARM Framework for Detection and Mitigation
Arxiv
0+阅读 · 6月3日
Direct Preference Optimization for English-Mandarin Code-Switching Speech Recognition in Audio LLMs
Arxiv
0+阅读 · 5月13日
LegalCiteBench: Evaluating Citation Reliability in Legal Language Models
Arxiv
0+阅读 · 5月11日
Exact Bayesian Planning for Simple Step-Stress Accelerated Life Testing with Competing Risks
Arxiv
0+阅读 · 4月10日
Reward Models Can Improve Themselves: Reward-Guided Adversarial Failure Mode Discovery for Robust Reward Modeling
Arxiv
0+阅读 · 4月8日
Revisiting On-Policy Distillation: Empirical Failure Modes and Simple Fixes
Arxiv
0+阅读 · 3月26日
Mechanisms of Prompt-Induced Hallucination in Vision-Language Models
Arxiv
0+阅读 · 4月17日
Safer by Diffusion, Broken by Context: Diffusion LLM's Safety Blessing and Its Failure Mode
Arxiv
0+阅读 · 4月2日
Pause or Fabricate? Training Language Models for Grounded Reasoning
Arxiv
0+阅读 · 4月21日
What People See (and Miss) About Generative AI Risks: Perceptions of Failures, Risks, and Who Should Address Them
Arxiv
0+阅读 · 4月24日
Negation is Not Semantic: Diagnosing Dense Retrieval Failure Modes for Trade-offs in Contradiction-Aware Biomedical QA
Arxiv
0+阅读 · 3月18日
参考链接
微信扫码咨询专知VIP会员
Top