collaborators

10 papers

cs.LG2026

Context Distillation as Latent Memory Management

Ziyang Zheng, Zeju Li, Xiangyu Wen +5

Context distillation compresses contextual information into model parameters, yet existing methods often ignore how multiple distilled latent memories should be stored, retrieved,…

cs.CL2026

HyLaT: Efficient Multi-Agent Communication via Hybrid Latent-Text Protocol

Xinyi Mou, Siyuan Wang, Zejun Li +2

Communication protocol design is a central challenge in large language model-based multi-agent systems. Existing single-channel approaches face an inherent communication trilemma:…

cs.AI2026

Mixture-of-Visual-Thoughts: Exploring Context-Adaptive Reasoning Mode Selection for General Visual Reasoning

Zejun Li, Yingxiu Zhao, Jiwen Zhang +6

Current visual reasoning methods mainly focus on exploring specific reasoning modes. Although improvements can be achieved in particular domains, they struggle to develop general r…

cs.CV2026

SpatialNav: Leveraging Spatial Scene Graphs for Zero-Shot Vision-and-Language Navigation

Jiwen Zhang, Zejun Li, Siyuan Wang +3

Although learning-based vision-and-language navigation (VLN) agents can learn spatial knowledge implicitly from large-scale training data, zero-shot VLN agents lack this process, r…

cs.CV2026

MoIIE: Mixture of Intra- and Inter-Modality Experts for Large Vision Language Models

Dianyi Wang, Siyuan Wang, Zejun Li +6

Large Vision-Language Models (LVLMs) have demonstrated remarkable performance across multi-modal tasks by scaling model size and training data. However, these dense LVLMs incur sig…

cs.CV2025

OViP: Online Vision-Language Preference Learning for VLM Hallucination

Shujun Liu, Siyuan Wang, Zejun Li +3

Large vision-language models (LVLMs) remain vulnerable to hallucination, often generating content misaligned with visual inputs. Although recent training-based approaches aim to mi…