Showing cs.CVShow all
2 papers · 1 filter
cs.CV2026
Fewer Tokens, More Self-Teaching: On-Policy Self-Distillation for Extreme Visual Token Reduction
Junxian Li, Ruixuan Yang, Tianao Zhang +3
Visual token reduction is an effective way to accelerate multimodal large language models (MLLMs), but performance deteriorates rapidly under extremely low token budgets. Existing…
cs.CV2026
VecAttention: Vector-wise Sparse Attention for Accelerating Long Context Inference
Anmin Liu, Ruixuan Yang, Huiqiang Jiang +5
Long-context video understanding and generation pose a significant computational challenge for Transformer-based video models due to the quadratic complexity of self-attention. Whi…