5 papers
Reinforcement Learning with Robust Rubric Rewards
Ya-Qi Yu, Hao Wang, Fangyu Hong +15
While Reinforcement Learning with Verifiable Rewards (RLVR) is effective for deterministically checkable tasks, many vision-language tasks are partially verifiable, demanding multi…
What if Agents Could Imagine? Reinforcing Open-Vocabulary HOI Comprehension through Generation
Zhenlong Yuan, Yue Wang, Dapeng Zhang +9
Multimodal Large Language Models have shown promising capabilities in bridging visual and textual reasoning, yet their reasoning capabilities in Open-Vocabulary Human-Object Intera…
Video-STAR: Reinforcing Open-Vocabulary Action Recognition with Tools
Zhenlong Yuan, Xiangyan Qu, Chengxuan Qian +8
Multimodal large language models (MLLMs) have demonstrated remarkable potential in bridging visual and textual reasoning, yet their reliance on text-centric priors often limits the…
Visual Preference Optimization with Rubric Rewards
Ya-Qi Yu, Fangyu Hong, Xiangyang Qu +15
The effectiveness of Direct Preference Optimization (DPO) depends on preference data that reflect the quality differences that matter in multimodal tasks. Existing pipelines often…
From Scale to Speed: Adaptive Test-Time Scaling for Image Editing
Xiangyan Qu, Zhenlong Yuan, Jing Tang +9
Image Chain-of-Thought (Image-CoT) is a test-time scaling paradigm that improves image generation by extending inference time. Most Image-CoT methods focus on text-to-image (T2I) g…