activity
20242026
collaborators
Showing cs.CVShow all

7 papers · 1 filter

cs.CV2026

MT-Web2Code: Benchmarking Coding Agents on Multi-Turn Regional Reconstruction and Localized Modification

Qiming Li, Shujie Hu, Haohan Liu +3

Recent advances in Large Vision-Language Models (LVLMs) have demonstrated impressive capabilities in web UI generation. However, existing benchmarks predominantly focus on single-t…

cs.CV2026

Unlocking Multilingual Reasoning Capability of LLMs and LVLMs through Representation Engineering

Qiming Li, Xiaocheng Feng, Yixuan Ma +4

Large Language Models (LLMs) and Large Vision-Language Models (LVLMs) demonstrate strong reasoning capabilities, yet their performance in English significantly outperforms that in…

cs.CV2026

PRPO: Perception-Reinforced Policy Optimization via Token-Level Dynamic Advantage Reshaping

Qiming Li, Tianlun Li, Xiaolong Cheng +5

Reinforcement Learning with Verifiable Rewards (RLVR) has become an effective paradigm for improving the reasoning capability of Large Vision-Language Models (LVLMs). However, exis…

cs.CV2026

CAST: Mitigating Object Hallucination in Large Vision-Language Models via Caption-Guided Visual Attention Steering

Qiming Li, Zekai Ye, Xiaocheng Feng +9

Although Large Vision-Language Models (LVLMs) have demonstrated remarkable performance on downstream tasks, they frequently produce contents that deviate from visual information, l…

cs.CV2025

Causal Tracing of Object Representations in Large Vision Language Models: Mechanistic Interpretability and Hallucination Mitigation

Qiming Li, Zekai Ye, Xiaocheng Feng +3

Despite the remarkable advancements of Large Vision-Language Models (LVLMs), the mechanistic interpretability remains underexplored. Existing analyses are insufficiently comprehens…

cs.CV2025

CAI: Caption-Sensitive Attention Intervention for Mitigating Object Hallucination in Large Vision-Language Models

Qiming Li, Zekai Ye, Xiaocheng Feng +8

Although Large Vision-Language Models (LVLMs) have demonstrated powerful capabilities in interpreting visual information, they frequently produce content that deviates from visual…