7 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…
Thinking as Compression: Your Reasoning Model is Secretly a Context Compressor
Guoxin Ma, Yibing Liu, Chengzhengxu Li +7
Context compression aims to shorten long context inputs with minimal information loss for LLM inference acceleration. While existing methods have shown promise, they typically rely…
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…
CASL: Curvature-Augmented Self-supervised Learning for 3D Anomaly Detection
Yaohua Zha, Xue Yuerong, Chunlin Fan +4
Deep learning-based 3D anomaly detection methods have demonstrated significant potential in industrial manufacturing. However, many approaches are specifically designed for anomaly…
Point Cloud Mixture-of-Domain-Experts Model for 3D Self-supervised Learning
Yaohua Zha, Tao Dai, Hang Guo +4
Point clouds, as a primary representation of 3D data, can be categorized into scene domain point clouds and object domain point clouds. Point cloud self-supervised learning (SSL) h…