arXiv
Efficient Test-Time Adaptation through Human-AI Interaction
AI agents are trained on population-scale data to encode broad capabilities spanning those of many practitioners. Yet...
🤖 AI 前沿资讯
每天自动聚合 AI 领域最新动态
arXiv
A Low-Cost, Open Platform for End-to-End Autonomous Driving on a Miniature Ackermann Vehicle
This paper presents a low-cost, open experimental platform for research in end-to-end autonomous driving with miniatu...
arXiv
Terminal-Universe: Turning Agent Trajectories into Scalable Terminal Environments
As terminal-based code agents become prevalent, agent trajectories have accumulated at scale, while realistic, execut...
arXiv
SENTINEL-RL: Offloading Topological Reasoning from LLM Agents in the Security Operations Center
Large language model (LLM) agents are increasingly proposed as autonomous SOC analysts, but two limitations make them...
arXiv
From Deceptive Outputs to Deceptive Mechanisms: A Causal Framework for Language-Model Deception Research
Research and news coverage of language-model deception increasingly attributes human-like mental-state concepts to la...
arXiv
SWE-Gate: Passing Functional Tests Is Not Enough for Software Engineering Agents
Repository-level software engineering benchmarks have significantly advanced the evaluation of coding agents, but exi...
arXiv
A Case Study on Emergent Cheating and Whistleblowing in Autonomous Research Swarms
Multi-agent AI science ecosystems rely on agents possessing tools that allow them to communicate, coordinate, and bui...
arXiv
Rethinking On-Policy Distillation of Large Language Models II: One Training Example
On-policy distillation (OPD) combines student-generated rollouts with dense token-level supervision from a teacher. E...
arXiv
A Computationally Feasible Framework for Causal Probabilistic Explanation
Explaining why a specific outcome occurred, and which inputs deserve the blame or credit, is central to philosophical...
arXiv
Knowledge Acquisition During Pre-training? Large Language Models Learn Better With Auxiliary Views
Gaps remain in our understanding of how large language models (LLMs) acquire knowledge during pre-training. We posit ...
arXiv
Seeing Before Synthesizing: VLM-Guided Transition Event Discovery for Weakly-Supervised Dense Video Captioning
Weakly-Supervised Dense Video Captioning aims to localize and describe multiple events in untrimmed videos given only...
arXiv
One Editor, Many Edits: A Unified Training-Free Framework for Diverse Video Editing
Video editing spans diverse editing paradigms, yet achieving high-quality instruction-guided and subject-guided editi...