6 papers
Efficient Long-context Language Model Training by Core Attention Disaggregation
Yonghao Zhuang, Junda Chen, Bo Pang +6
We present core attention disaggregation (CAD), a technique that improves long-context large language model training by decoupling the core attention computation, softmax(QK^T)V, f…
lmgame-Bench: How Good are LLMs at Playing Games?
Lanxiang Hu, Mingjia Huo, Yuxuan Zhang +6
Playing video games requires perception, memory, and planning, exactly the faculties modern large language model (LLM) agents are expected to master. We study the major challenges…
VSA: Faster Video Diffusion with Trainable Sparse Attention
Peiyuan Zhang, Yongqi Chen, Haofeng Huang +5
Scaling video diffusion transformers (DiTs) is limited by their quadratic 3D attention, even though most of the attention mass concentrates on a small subset of positions. We turn…
Efficient-vDiT: Efficient Video Diffusion Transformers With Attention Tile
Hangliang Ding, Dacheng Li, Runlong Su +4
Despite the promise of synthesizing high-fidelity videos, Diffusion Transformers (DiTs) with 3D full attention suffer from expensive inference due to the complexity of attention co…
Fast Video Generation with Sliding Tile Attention
Peiyuan Zhang, Yongqi Chen, Runlong Su +4
Diffusion Transformers (DiTs) with 3D full attention power state-of-the-art video generation, but suffer from prohibitive compute cost -- when generating just a 5-second 720P video…
Efficiently Scaling LLM Reasoning with Certaindex
Yichao Fu, Junda Chen, Siqi Zhu +8
Test-time reasoning algorithms such as chain-of-thought, self-consistency, and MCTS enhance LLM problem-solving but can wastefully generate many tokens without improving accuracy.…