10 papers
Mechanist: AI as a Scientific Instrument for Discovering the Mechanisms of Intelligence
Mengru Wang, Junfeng Fang, Shuofei Qiao +17
AI models are increasingly used in scientific discovery and human decision-making. Yet how AI models work and what risks they pose remain poorly understood. As AI development becom…
MAE I Trust Myself? Self-Evaluating VLA Action Generation with Markov Attention Entropy
Aniri, Chen Yilin, Jinhe Bi +10
Vision-Language-Action models (VLAs) integrate visual perception, language instruction, and action generation into end-to-end policies across heterogeneous architectures. However,…
OPD-V: Visual On-Policy Self-Distillation with Modality Balance
Aniri, Jinhe Bi, Peng Liao +5
On-Policy Self-Distillation (OPSD) has become a standard post-training approach for improving visual reasoning in multimodal large language models (MLLMs). Existing methods draw pr…
ReflectRL: Learning from Golden Negative Trajectories via Reflective-to-Direct Reasoning
Jinhe Bi, Chennan Zhou, Zengjie Jin +10
On-policy training has emerged as a powerful post-training paradigm for improving the reasoning capabilities of large language models, and is often enhanced by golden trajectories…
TRACE: Trajectory Risk-Aware Compression for Long-Horizon Agent Safety
Zhepei Hong, Lin Wang, Liting Li +5
Long-horizon LLM agents produce safety evidence across long trajectories, where sparse, delayed, and compositional risk signals often escape local moderation. Existing turn-level o…
DRAFT: Task Decoupled Latent Reasoning for Agent Safety
Lin Wang, Junfeng Fang, Dan Zhang +3
The advent of tool-using LLM agents shifts safety monitoring from output moderation to auditing long, noisy interaction trajectories, where risk-critical evidence is sparse-making…
CoC-VLA: Delving into Adversarial Domain Transfer for Explainable Autonomous Driving via Chain-of-Causality Visual-Language-Action Model
Dapeng Zhang, Fei Shen, Rui Zhao +5
Autonomous driving represents a prominent application of artificial intelligence. Recent approaches have shifted from focusing solely on common scenarios to addressing complex, lon…
Reasoning-VLA: A Fast and General Vision-Language-Action Reasoning Model for Autonomous Driving
Dapeng Zhang, Zhenlong Yuan, Zhangquan Chen +5
Vision-Language-Action (VLA) models have recently shown strong decision-making capabilities in autonomous driving. However, existing VLAs often struggle with achieving efficient in…
ETTRL: Balancing Exploration and Exploitation in LLM Test-Time Reinforcement Learning Via Entropy Mechanism
Jia Liu, ChangYi He, YingQiao Lin +3
Recent advancements in Large Language Models have yielded significant improvements in complex reasoning tasks such as mathematics and programming. However, these models remain heav…
Closing the Gap between TD Learning and Supervised Learning with -Conditioned Maximization
Xing Lei, Zifeng Zhuang, Shentao Yang +6
Recently, supervised learning (SL) methodology has emerged as an effective approach for offline reinforcement learning (RL) due to their simplicity, stability, and efficiency. Howe…