collaborators

13 papers

cs.MM2026

Balancing Efficiency and Efficacy: Training-Free Attention-Guided Switching Between Explicit and Latent Thoughts for MLLMs

Haoqian Kang, Liupeng Li, Kuofeng Gao +5

Reasoning in Multimodal Large Language Models (MLLMs) requires both fine-grained visual perception and rigorous logical deduction. Explicit text-based Chain-of-Thought (CoT) is com…

cs.CL2026

AgentSpec: Understanding Embodied Agent Scaffolds Through Controlled Composition

Jixuan Chen, Jianzhi Shen, Haoqiang Kang +10

LLM agents are increasingly built not as single model calls, but as scaffolded systems that combine reasoning, memory, reflection, action execution, and learning. While such scaffo…

cs.CL2026

Latent Reasoning with Normalizing Flows

Guancheng Tu, Xiangjun Fu, Suhao Yu +5

Large language models often improve reasoning by generating explicit chain-of-thought (CoT), demonstrating the importance of intermediate computation. However, textual CoT forces t…

cs.CV2026

CVSearch: Empowering Multimodal LLMs with Cognitive Visual Search for High-Resolution Image Perception

Liupeng Li, Haoqian Kang, Zhenyu Lu +4

High-resolution (HR) image perception presents a key bottleneck for multimodal large language models (MLLMs). While visual search offers a promising solution, existing methods stru…

cs.CV2026

SegCompass: Exploring Interpretable Alignment with Sparse Autoencoders for Enhanced Reasoning Segmentation

Zhenyu Lu, Liupeng Li, Jinpeng Wang +4

While large language models provide strong compositional reasoning, existing reasoning segmentation pipelines fail to transparently connect this reasoning to visual perception. Cur…

cs.LG2026

LaDi-RL: Latent Diffusion Reasoning Prevents Entropy Collapse in Reinforcement Learning

Haoqiang Kang, Yizhe Zhang, Nikki Lijing Kuang +2

Reinforcement learning has become a central paradigm for improving LLM reasoning, but most existing methods optimize policies over discrete token sequences. This creates a mismatch…