activity
20232026
most citedAdvancing Vision Transformers with Group-Mix Attention

12 citations · 12 across the 6 of their papers we have counts for

collaborators
Showing cs.CVShow all

10 papers · 1 filter

cs.CV2026

Relax Within, Balance Across: Geometry-Guided Load Balancing for Vision-Language Mixture-of-Experts

Ziang Wu, Peng Jin, Qishen Yin +4

Vision-language MoE batches contain different numbers of image and text tokens. Image resolution, image count, tiling, and prompt length all change this token mix. We call the stan…

cs.CV2026

V-Zero: Answer-Label-Free On-Policy Distillation with Contrastive Evidence Gating for Fine-Grained Visual Reasoning

Haoxiang Sun, Zhihang Yi, Langxuan Deng +6

Fine-grained visual reasoning requires multimodal large language models (MLLMs) to identify task-relevant visual evidence and ground their reasoning in local image regions. Existin…

cs.CV2026

Benchmarking PhD-Level Coding in 3D Geometric Computer Vision

Wenyi Li, Renkai Luo, Yue Yu +5

AI-assisted coding has rapidly reshaped software practice and research workflows, yet today's models still struggle to produce correct code for complex 3D geometric vision. If mode…

cs.CV2026

Dr. Seg: Revisiting GRPO Training for Visual Large Language Models through Perception-Oriented Design

Haoxiang Sun, Tao Wang, Chenwei Tang +2

Following the success of Group Relative Policy Optimization (GRPO) in foundation LLMs, an increasing number of works have sought to adapt GRPO to Visual Large Language Models (VLLM…

cs.CV2025

CoT-lized Diffusion: Let's Reinforce T2I Generation Step-by-step

Zheyuan Liu, Munan Ning, Qihui Zhang +8

Current text-to-image (T2I) generation models struggle to align spatial composition with the input text, especially in complex scenes. Even layout-based approaches yield suboptimal…

cs.CV2025

Look-Back: Implicit Visual Re-focusing in MLLM Reasoning

Shuo Yang, Yuwei Niu, Yuyang Liu +3

Multimodal Large Language Models (MLLMs) have achieved remarkable progress in multimodal reasoning. However, they often excessively rely on textual information during the later sta…