9 papers
Through the PRISM: Preference Representation in Intermediate States of Video Diffusion Models
Haoxuan Wu, Lai Man Po, Mengyang Liu +3
Evaluating video generation with clean, pixel-based reward models disconnects evaluation from the noisy diffusion process and incurs massive VAE decoding costs. In this paper, we c…
SpecPL: Disentangling Spectral Granularity for Prompt Learning
Jingtao Zhou, Xirui Kang, Feiyang Huang +1
Existing prompt learning for VLMs exhibits a modality asymmetry, predominantly optimizing text tokens while still relying on frozen visual encoder as holistic extractor and neglect…
From Exploration to Exploitation: A Two-Stage Entropy RLVR Approach for Noise-Tolerant MLLM Training
Donglai Xu, Hongzheng Yang, Yuzhi Zhao +10
Reinforcement Learning with Verifiable Rewards (RLVR) for Multimodal Large Language Models (MLLMs) is highly dependent on high-quality labeled data, which is often scarce and prone…
Omni-C: Compressing Heterogeneous Modalities into a Single Dense Encoder
Kin Wai Lau, Yasar Abbas Ur Rehman, Lai-Man Po +1
Recent multimodal systems often rely on separate expert modality encoders which cause linearly scaling complexity and computational overhead with added modalities. While unified Om…
AesBiasBench: Evaluating Bias and Alignment in Multimodal Language Models for Personalized Image Aesthetic Assessment
Kun Li, Lai-Man Po, Hongzheng Yang +3
Multimodal Large Language Models (MLLMs) are increasingly applied in Personalized Image Aesthetic Assessment (PIAA) as a scalable alternative to expert evaluations. However, their…
Motion Transfer-Driven intra-class data augmentation for Finger Vein Recognition
Xiu-Feng Huang, Lai-Man Po, Wei-Feng Ou
Finger vein recognition (FVR) has emerged as a secure biometric technique because of the confidentiality of vascular bio-information. Recently, deep learning-based FVR has gained i…