activity
20212026
most citedPanGu-: Large-scale Autoregressive Pretrained Chinese Language Models with Auto-parallel Computation

94 citations · 94 across the 2 of their papers we have counts for

collaborators

9 papers

cs.CV2026

Unsafe by Reciprocity: How Generation-Understanding Coupling Undermines Safety in Unified Multimodal Models

Kaishen Wang, Heng Huang

Recent advances in Large Language Models (LLMs) and Text-to-Image (T2I) models have led to the emergence of Unified Multimodal Models (UMMs), where multimodal understanding and ima…

cs.CL2026

Parallel-Probe: Towards Efficient Parallel Thinking via 2D Probing

Tong Zheng, Chengsong Huang, Runpeng Dai +9

Parallel thinking has emerged as a promising paradigm for reasoning, yet it imposes significant computational burdens. Existing efficiency methods primarily rely on local, per-traj…

cs.CV2025

Multi-Crit: Benchmarking Multimodal Judges on Pluralistic Criteria-Following

Tianyi Xiong, Yi Ge, Ming Li +13

Large multimodal models (LMMs) are increasingly adopted as judges in multimodal evaluation systems due to their strong instruction following and consistency with human preferences.…

cs.CV2025

ImAgent: A Unified Multimodal Agent Framework for Test-Time Scalable Image Generation

Kaishen Wang, Ruibo Chen, Tong Zheng +1

Recent text-to-image (T2I) models have made remarkable progress in generating visually realistic and semantically coherent images. However, they still suffer from randomness and in…

cs.CV2025

Enhancing Feature Fusion of U-like Networks with Dynamic Skip Connections

Yue Cao, Quansong He, Kaishen Wang +3

U-like networks have become fundamental frameworks in medical image segmentation through skip connections that bridge high-level semantics and low-level spatial details. Despite th…

cs.CV2025

HalluRNN: Mitigating Hallucinations via Recurrent Cross-Layer Reasoning in Large Vision-Language Models

Le Yu, Kaishen Wang, Jianlong Xiong +3

Though Large Vision-Language Models (LVLMs) have achieved remarkable performance across various tasks, they are still prone to hallucinations-generating outputs that are textually…