5 papers
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…
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…
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…
CoPRS: Learning Positional Prior from Chain-of-Thought for Reasoning Segmentation
Zhenyu Lu, Liupeng Li, Jinpeng Wang +4
Existing works on reasoning segmentation either connect hidden features from a language model directly to a mask decoder or represent positions in text, which limits interpretabili…
In-Context Learning Distillation for Efficient Few-Shot Fine-Tuning
Yifei Duan, Liu Li, Zirui Zhai +1
We applied few-shot in-context learning on the OPT-1.3B model for the natural language inference task and employed knowledge distillation to internalize the context information, re…