7 papers
d3LLM: Ultra-Fast Diffusion LLM using Pseudo-Trajectory Distillation
Yu-Yang Qian, Junda Su, Lanxiang Hu +4
Diffusion large language models (dLLMs) offer capabilities beyond those of autoregressive (AR) LLMs, such as parallel decoding and random-order generation. However, realizing these…
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…
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…
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…
Criteria and Bias of Parameterized Linear Regression under Edge of Stability Regime
Peiyuan Zhang, Amin Karbasi
Classical optimization theory requires a small step-size for gradient-based methods to converge. Nevertheless, recent findings challenge the traditional idea by empirically demonst…
Temporal Reasoning Transfer from Text to Video
Lei Li, Yuanxin Liu, Linli Yao +6
Video Large Language Models (Video LLMs) have shown promising capabilities in video comprehension, yet they struggle with tracking temporal changes and reasoning about temporal rel…