activity
20242026
collaborators

9 papers

cs.AI2026

When Prompts Become Pixels: Prompt-Region Grounding for Multimodal Reasoning

Yongxin Wang, Ruizhe Zhou, Yueling Tang +4

Multimodal large language models increasingly reason over screenshots and documents where the task itself may be written in pixels. Yet benchmarks usually place questions in text,…

cs.CV2026

Latent Visual States for Efficient Multimodal Reasoning

Xiuwei Chen, Wentao Hu, Yongxin Wang +8

The integration of visual evidence has significantly enhanced the capabilities of large multimodal models. However, this integration predominantly relies on generating discrete out…

cs.LG2026

Prune-OPD: Efficient and Reliable On-Policy Distillation for Long-Horizon Reasoning

Zhicheng Yang, Zhijiang Guo, Yifan Song +5

On-policy distillation (OPD) leverages dense teacher rewards to enhance reasoning models. However, scaling OPD to long-horizon tasks exposes a critical flaw: as the student's gener…

cs.LG2026

Depth-Breadth Synergy in RLVR: Unlocking LLM Reasoning Gains with Adaptive Exploration

Zhicheng Yang, Zhijiang Guo, Yinya Huang +6

Reinforcement Learning with Verifiable Reward (RLVR) is a powerful method for enhancing the reasoning abilities of Large Language Models, but its full potential is limited by a lac…

cs.AI2026

Accordion-Thinking: Self-Regulated Step Summaries for Efficient and Readable LLM Reasoning

Zhicheng Yang, Zhijiang Guo, Yinya Huang +5

Scaling test-time compute via long Chain-of-Thought unlocks remarkable gains in reasoning capabilities, yet it faces practical limits due to the linear growth of KV cache and quadr…

cs.LG2026

CARE What Fails: Contrastive Anchored-REflection for Verifiable Multimodal Reasoning

Yongxin Wang, Zhicheng Yang, Meng Cao +5

Group-relative reinforcement learning with verifiable rewards (RLVR) often wastes the most informative data it already has the failures. When all rollouts are wrong, gradients stal…