CARD is an RL-based framework that transforms solver trajectories into teaching trajectories aligned with the student's cognition that outperforms distillation from raw teacher trajectories in in-domain settings while achieving substantial gains in out-of-distribution performance.
Ya-Shuo Luo, Qian-Ren Mao, Zi-Qi Qin et al.· 0 citations
STI-OPD, a stochastic teacher intervention framework for multi-turn agentic OPD, and an Importance-Weighted Reverse KL objective that corrects the token sampling mismatch between teacher-generated responses and the student policy to preserve the original OPD objective are introduced.
Jun-Nan Liu, Lin-Hao Luo, Zhijun Chen et al.· 0 citations
Autonomous driving has made significant progress in both academia and industry, including performance improvements in perception tasks and the development of end-to-end autonomous driving systems. However, the safety and robustness assessment of autonomous driving has not received sufficient attention. Current evaluati...
Jingzheng Li, Xiang-Long Liu, Shikui Wei et al.· IEEE Transactions on Image P...· 3 citations
The results suggest that wide TopK SAEs should be evaluated not only by reconstruction, sparsity, and feature count, but also by feature reliability under semantic variation and boundary geometry for stable interpretability.
Zhen-Ting Huang, Bo-Han Jiang, J. Liu et al.· 0 citations
Proof-R1 is proposed, an RL framework from formal verification that trains LLMs to construct verifiable proofs for natural-language logical reasoning and improves answer accuracy across three logical reasoning benchmarks and four backbone models and outperforms training-free agents and training-based methods in terms o...
Qi-Li Zhang, Qian-Ren Mao, Han-Ze Cai et al.· 0 citations
Conditioned on front-view visual observations, E2E-CDiff jointly denoises future motion states and executable low-level controls for route-interacting background vehicles, and mitigates the planning-control mismatch in conventional two-stage trajectory-then-controller pipelines.
Results suggest that different edits are sparsely encoded within dominant singular components and can be separable when the number of edits is moderate, making selective spectral reversal a promising direction for locating edit-specific components and repairing edited language models.
Wei-Feng Jiang, Rui-Rui Chen, Qian-Ren Mao et al.· 0 citations
We propose LLM-PeerReview, an unsupervised LLM Ensemble method that selects the most ideal response from multiple LLM-generated candidates for each query, harnessing the collective wisdom of multiple models with diverse strengths. LLM-PeerReview is built on a novel, peer-review-inspired framework that offers a transpar...
Zhijun Chen, Zeyu Ji, Qianren Mao et al.· arXiv.org· 5 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.