会员服务
From Trace to Fix: Residual Task State in Long-Horizon Agents
Arxiv
0+阅读 · 10月19日
DTDD: Divergence-Triggered Dynamic Distillation for Reliable On-Policy Supervision
Arxiv
0+阅读 · 10月13日
Evaluating Large Language Models for Multilingual Abstractive Summarization: A Comprehensive Study of English and Bengali
Arxiv
0+阅读 · 10月13日
Visual Evidence Under Cross-Examination: Evaluating and Controlling Decision-Level Evidence Use in Vision-Language Models
Arxiv
0+阅读 · 10月7日
From Open Standards to Openly Governed: Standards-Setting Organizations as Stewards of Openness amid Platformization and Digital Sovereignty
Arxiv
0+阅读 · 9月1日
Runtime Safety Filtering for Learned Small UAS Separation Policies under GNSS Degradation
Arxiv
0+阅读 · 8月29日
Nudging Sustainable Choices through LLM-Generated Recommendation Explanations
Arxiv
0+阅读 · 7月28日
Nudging Sustainable Choices through LLM-Generated Recommendation Explanations
Arxiv
0+阅读 · 7月30日
When Readability and Source Retention Diverge: An Evaluability Gap in AI Translation
Arxiv
0+阅读 · 8月19日
ScratchLens: Lens-Parametric Behavioral Equivalence for Scratch Programs
Arxiv
0+阅读 · 6月16日
Contemporary AI lacks the imagination to diverge or negate in science
Arxiv
0+阅读 · 6月9日
Dynamic Multi-Pair Trading Strategy in Cryptocurrency Markets with Deep Reinforcement Learning
Arxiv
0+阅读 · 6月3日
Detecting Hallucinations in Large Language Models via Internal Attention Divergence Signals
Arxiv
0+阅读 · 5月6日
Learn Where Outcomes Diverge: Efficient VLA RL via Probabilistic Chunk Masking
Arxiv
0+阅读 · 5月15日
Instruction Data Selection via Answer Divergence
Arxiv
0+阅读 · 4月19日
参考链接
微信扫码咨询专知VIP会员
Top