← authors · overview

• BitDelta: Your Fine-Tune May Only Be Worth One Bit
  2024 · 1 citations
• TriAttention: Efficient Long Reasoning with Trigonometric KV Compression
  2026
• Lightning OPD: Efficient Post-Training for Large Reasoning Models with Offline On-Policy Distillation
  2026
• SparDA: Sparse Decoupled Attention for Efficient Long-Context LLM Inference
  2026
• Fast-dLLM v2: Efficient Block-Diffusion LLM
  2025
• Token-Efficient Long Video Understanding for Multimodal LLMs
  2025
• Scaling Vision Pre-Training to 4K Resolution
  2025
• Fast-dLLM: Training-free Acceleration of Diffusion LLM by Enabling KV Cache and Parallel Decoding
  2025
• SparseLoRA: Accelerating LLM Fine-Tuning with Contextual Sparsity
  2025
• QeRL: Beyond Efficiency -- Quantization-enhanced Reinforcement Learning for LLMs
  2025
• OmniVinci: Enhancing Architecture and Data for Omni-Modal Understanding LLM
  2025
• Efficient-DLM: From Autoregressive to Diffusion Language Models, and Beyond in Speed
  2025
• PockEngine: Sparse and Efficient Fine-tuning in a Pocket
  2023
• VILA: On Pre-training for Visual Language Models
  2023
• VILA^2: VILA Augmented VILA
  2024