1 citations · 1 across the 6 of their papers we have counts for
7 papers · 1 filter
Beyond Saying Less: Fine-Grained Alignment for Informative and Faithful Vision-Language Models
Xingming Long, Jie Zhang, Yuecong Min +2
Object hallucination remains a major challenge for large vision-language models. While off-policy preference optimization proves to be an effective solution, on-policy reinforcemen…
V-Gym: Enhancing Agentic Visual Reasoning via Skill-Data Co-Evolution
Bei Yan, Yuecong Min, Jie Zhang +3
Advances in multimodal understanding, reasoning, and tool use enable agents to tackle increasingly complex visual reasoning tasks. By distilling past execution experience into reus…
ACT Now: Preempting LVLM Hallucinations via Adaptive Context Integration
Bei Yan, Yuecong Min, Jie Zhang +2
Large Vision-Language Models (LVLMs) frequently suffer from severe hallucination issues. Existing mitigation strategies predominantly rely on isolated, single-step states to enhanc…
INFACT: A Diagnostic Benchmark for Induced Faithfulness and Factuality Hallucinations in Video-LLMs
Junqi Yang, Yuecong Min, Jie Zhang +2
Despite rapid progress, Video Large Language Models (Video-LLMs) remain unreliable due to hallucinations, which are outputs that contradict either video evidence (faithfulness) or…
T2VAttack: Adversarial Attack on Text-to-Video Diffusion Models
Changzhen Li, Yuecong Min, Jie Zhang +3
The rapid evolution of Text-to-Video (T2V) diffusion models has driven remarkable advancements in generating high-quality, temporally coherent videos from natural language descript…
SHALE: A Scalable Benchmark for Fine-grained Hallucination Evaluation in LVLMs
Bei Yan, Zhiyuan Chen, Yuecong Min +4
Despite rapid advances, Large Vision-Language Models (LVLMs) still suffer from hallucinations, i.e., generating content inconsistent with input or established world knowledge, whic…
A Survey of Multimodal Hallucination Evaluation and Detection
Zhiyuan Chen, Yuecong Min, Jie Zhang +4
Multi-modal Large Language Models (MLLMs) have emerged as a powerful paradigm for integrating visual and textual information, supporting a wide range of multi-modal tasks. However,…