3 papers
cs.CV2025
Distilling Cross-Modal Knowledge via Feature Disentanglement
Junhong Liu, Yuan Zhang, Tao Huang +2
Knowledge distillation (KD) has proven highly effective for compressing large models and enhancing the performance of smaller ones. However, its effectiveness diminishes in cross-m…
cs.CV2025
ChainV: Atomic Visual Hints Make Multimodal Reasoning Shorter and Better
Yuan Zhang, Ming Lu, Junwen Pan +4
Recent advances in multimodal reasoning models have demonstrated impressive capabilities across text and vision. However, even leading models exhibit redundant self-reflection when…
cs.CV2025
ActVAR: Activating Mixtures of Weights and Tokens for Efficient Visual Autoregressive Generation
Kaixin Zhang, Ruiqing Yang, Yuan Zhang +2
Visual Autoregressive (VAR) models enable efficient image generation via next-scale prediction but face escalating computational costs as sequence length grows. Existing static pru…