collaborators

7 papers

cs.CV2026

Advantage-Guided Gate: Reshaping Open-Ended Reasoning for Vision-Based Spatial Intelligence

Ling Lin, Yang Bai, Congcong Zhu +6

Multimodal large language models (MLLMs) have demonstrated significant potential in complex spatial scene understanding and reasoning tasks. However, their open-ended reasoning pro…

cs.CV2026

See Only When Needed: Context-Aware Attention Intervention for Mitigating Hallucinations in LVLMs

Yuqing Lei, Wenbo Lyu, Yingjun Du +3

Large Vision-Language Models (LVLMs) excel at multimodal tasks but remain prone to object hallucinations. Prior training-free remedies often uniformly strengthen visual signals, wh…

cs.CV2026

Task-Aware Structured Memory for Dynamic Multi-modal In-Context Learning

Zhirui Chen, Ziwei Chen, Ling Shao

Multi-modal large language models (MLLMs) depend on in-context learning (ICL) for rapid task adaptation, but their scalability is severely limited by finite context windows and the…

cs.CL2026

StructKV: Preserving the Structural Skeleton for Scalable Long-Context Inference

Zhirui Chen, Peiyang Liu, Ling Shao

As Large Language Models (LLMs) scale to support context windows exceeding one million tokens, the linear growth of Key-Value (KV) cache imposes severe memory capacity and bandwidt…

cs.LG2026

Self-Consolidation for Self-Evolving Agents

Hongzhuo Yu, Fei Zhu, Guo-Sen Xie +1

While large language model (LLM) agents have demonstrated impressive problem-solving capabilities, they typically operate as static systems, lacking the ability to evolve through l…

cs.CV2025

MetaTPT: Meta Test-time Prompt Tuning for Vision-Language Models

Yuqing Lei, Yingjun Du, Yawen Huang +2

Vision-language models (VLMs) such as CLIP exhibit strong zero-shot generalization but remain sensitive to domain shifts at test time. Test-time prompt tuning (TPT) mitigates this…