Multi-turn visual search agents answer questions about high-resolution images by iteratively deciding where to look. Reinforcement learning for these agents rewards only the final answer, leaving the search process unsupervised. Consequently, faulty routes in which the reasoning process is erroneous yet the final resul...
Zhangquan Chen, Yao-Xin Niu, Xiang An et al.· 0 citations
Spatial-OPSD, a label-free self-improvement framework that instead exploits spatial structure naturally available from perception and reconstruction tools, is introduced, achieving the highest average among the open models and the best results on three of five spatial reasoning benchmarks.
Zhen-Yu Liu, Zhangquan Chen, Ke-Yi Chen et al.· 0 citations
EviViT, a lightweight attachment that learns where a pretrained vision transformer should acquire detail, is introduced, a lightweight attachment that learns where a pretrained vision transformer should acquire detail without refitting.
Yao-Xin Niu, Zhangquan Chen, Yang Zhang et al.· 0 citations
This work proposes Counterfactual Evidence Disentanglement (CED), a training-time evidence audit for VLM grounding, which outperforms prior RL-based post-training methods, with targeted analyses verifying its object-centric signal.
Haojie Huang, Xin-Lei Yu, Cheng-Ming Xu et al.· 3 citations
This work identifies an implicit advantage symmetry inherent in Group Relative Advantage Estimation (GRAE) as a structural property that provides a new perspective for understanding bottlenecks in reinforcement learning, and proposes Asymmetric GRAE (A-GRAE), which dynamically modulates exploration incentives and sampl...
Zhiqiu Yu, Zhangquan Chen, Meng-Ting Liu et al.· arXiv.org· 6 citations
This work presents Hybrid Stratified Replay (HSR), a novel mechanism that restructures batches by stratifying rollouts based on Path Entropy, a rollout-level confidence proxy, and outcome reward, offering a principled solution for stable and efficient RL fine-tuning.
Yi-Meng Ye, Shuang Chen, Wen-Xuan Huang et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
