Song Han
15 papers · 0 citations
Most-cited papers
- Efficient Streaming Language Models With Attention Sinks2023 · 1654 citations
- VILA: On Pre-training For Visual Language Models2023 · 803 citations
- Longlora: Efficient Fine-tuning Of Long-context Large Language Models2023 · 253 citations
- Duoattention: Efficient Long-context LLM Inference With Retrieval And Streaming Heads2024 · 211 citations
- Scaling Vision Pre-training To 4K Resolution2025 · 3 citations
- Streamingvlm: Real-time Understanding For Infinite Video Streams2025
- DC-AE 1.5: Accelerating Diffusion Model Convergence With Structured Latent Space2025
- Dc-gen: Post-training Diffusion Acceleration With Deeply Compressed Latent Space2025
- Sana-video: Efficient Video Generation With Block Linear Diffusion Transformer2025
- Nemotron 3 Nano Omni: Efficient And Open Multimodal Intelligence2026
- Sparse Videogen2: Accelerate Video Generation With Sparse Attention Via Semantic-aware Permutation2026
- Sparse Videogen2: Accelerate Video Generation With Sparse Attention Via Semantic-aware Permutation2026
- EGM: Efficient Visual Grounding Language Models2026
Topics