2024.09.04 [24’ ECCV] FlexAttention for Efficient High-Resolution Vision-Language Models Multimodal Attention Efficiency
2024.09.04 [24’ ACL] Spectral Filters, Dark Signals, and Attention Sinks Language Attention Interpretability
2024.09.03 [24’ ECCV] FastV: An Image is Worth 1/2 Tokens After Layer 2 Multimodal Attention Efficiency
2024.08.29 [24’ ICLR] StreamingLLM: Efficient Streaming Language Models with Attention Sinks Language Attention Efficiency
2024.08.29 [24’ ICLR] PASTA: Tell Your Model Where to Attend: Post-hoc Attention Steering for LLMs Language Attention