7 papers
Hi-Light: A Path to high-fidelity, high-resolution video relighting with a Novel Evaluation Paradigm
Xiangrui Liu, Haoxiang Li, Yezhou Yang
Video relighting offers immense creative potential and commercial value but is hindered by challenges, including the absence of an adequate evaluation metric, severe light flickeri…
VOCAL: Visual Odometry via ContrAstive Learning
Chi-Yao Huang, Zeel Bhatt, Yezhou Yang
Breakthroughs in visual odometry (VO) have fundamentally reshaped the landscape of robotics, enabling ultra-precise camera state estimation that is crucial for modern autonomous sy…
CounterVid: Counterfactual Video Generation for Mitigating Action and Temporal Hallucinations in Video-Language Models
Tobia Poppi, Burak Uzkent, Amanmeet Garg +7
Video-language models (VLMs) achieve strong multimodal understanding but remain prone to hallucinations, especially when reasoning about actions and temporal order. Existing mitiga…
Foundation Model in Biomedicine
Xiangrui Liu, Yuanyuan Zhang, Qianyu Shang +14
Foundation models, first introduced in 2021, refer to large-scale pretrained models (e.g., large language models (LLMs) and vision-language models (VLMs)) that learn from extensive…
Chimera: Compositional Image Generation using Part-based Concepting
Shivam Singh, Yiming Chen, Agneet Chatterjee +4
Personalized image generative models are highly proficient at synthesizing images from text or a single image, yet they lack explicit control for composing objects from specific pa…
Investigating VLM Hallucination from a Cognitive Psychology Perspective: A First Step Toward Interpretation with Intriguing Observations
Xiangrui Liu, Man Luo, Agneet Chatterjee +3
Hallucination is a long-standing problem that has been actively investigated in Vision-Language Models (VLMs). Existing research commonly attributes hallucinations to technical lim…