collaborators

6 papers

cs.CV2026

Thinking with Geometry: Active Geometry Integration for Spatial Reasoning

Haoyuan Li, Qihang Cao, Tao Tang +6

Recent progress in spatial reasoning with Multimodal Large Language Models (MLLMs) increasingly leverages geometric priors from 3D encoders. However, most existing integration stra…

cs.CV2026

MagicSeg: Open-World Segmentation Pretraining via Counterfactural Diffusion-Based Auto-Generation

Kaixin Cai, Pengzhen Ren, Jianhua Han +4

Open-world semantic segmentation presently relies significantly on extensive image-text pair datasets, which often suffer from a lack of fine-grained pixel annotations on sufficien…

cs.CV2026

HiRes-LLaVA: Restoring Fragmentation Input in High-Resolution Large Vision-Language Models

Runhui Huang, Xinpeng Ding, Chunwei Wang +7

High-resolution inputs enable Large Vision-Language Models (LVLMs) to discern finer visual details, enhancing their comprehension capabilities. To reduce the training and computati…

cs.CV2026

AtomThink: Multimodal Slow Thinking with Atomic Step Reasoning

Kun Xiang, Zhili Liu, Terry Jingchen Zhang +12

In this paper, we address the challenging task of multimodal reasoning by incorporating the notion of ``slow thinking'' into multimodal large language models (MLLMs). Our core idea…

cs.CV2025

TransMamba: Fast Universal Architecture Adaption from Transformers to Mamba

Xiuwei Chen, Wentao Hu, Xiao Dong +7

Transformer-based architectures have become the backbone of both uni-modal and multi-modal foundation models, largely due to their scalability via attention mechanisms, resulting i…

cs.CV2025

Getting More Juice Out of Your Data: Hard Pair Refinement Enhances Visual-Language Models Without Extra Data

Haonan Wang, Minbin Huang, Runhui Huang +7

Contrastive Language-Image Pre-training (CLIP) has become the standard for cross-modal image-text representation learning. Improving CLIP typically requires additional data and ret…