10 papers
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,…
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…
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…
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…
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…
Critique to Verify: Accurate and Honest Test-Time Scaling with RL-Trained Verifiers
Zhicheng Yang, Zhijiang Guo, Yinya Huang +4
Test-time scaling via solution sampling and aggregation has become a key paradigm for improving the reasoning performance of Large Language Models (LLMs). While reward model select…
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…
PhyBlock: A Progressive Benchmark for Physical Understanding and Planning via 3D Block Assembly
Liang Ma, Jiajun Wen, Min Lin +12
While vision-language models (VLMs) have demonstrated promising capabilities in reasoning and planning for embodied agents, their ability to comprehend physical phenomena, particul…
EACO: Enhancing Alignment in Multimodal LLMs via Critical Observation
Yongxin Wang, Meng Cao, Haokun Lin +5
Multimodal large language models (MLLMs) have achieved remarkable progress on various visual question answering and reasoning tasks leveraging instruction fine-tuning specific data…
Web2Code: A Large-scale Webpage-to-Code Dataset and Evaluation Framework for Multimodal LLMs
Sukmin Yun, Haokun Lin, Rusiru Thushara +14
Multimodal large language models (MLLMs) have shown impressive success across modalities such as image, video, and audio in a variety of understanding and generation tasks. However…