Yang You

20

Papers

190

Total Citations

Papers (20)

Real-Time Video Generation with Pyramid Attention Broadcast

A Closer Look at Time Steps is Worthy of Triple Speed-Up for Diffusion Model Training

A Stitch in Time Saves Nine: Small VLM is a Precise Guidance for Accelerating Large VLMs

Summarizing Stream Data for Memory-Constrained Online Continual Learning

AllTracker: Efficient Dense Point Tracking at High Resolution

DSP: Dynamic Sequence Parallelism for Multi-Dimensional Transformers

REPA Works Until It Doesn’t: Early-Stopped, Holistic Alignment Supercharges Diffusion Training

Drag-and-Drop LLMs: Zero-Shot Prompt-to-Weights

StarTrail: Concentric Ring Sequence Parallelism for Efficient Near-Infinite-Context Transformer Model Training

NeurIPS 2025arXiv

Can a Large Language Model be a Gaslighter?

Info-Coevolution: An Efficient Framework for Data Model Coevolution

PACE: Pose Annotations in Cluttered Environments

OpenMoE: An Early Effort on Open Mixture-of-Experts Language Models

Emphasizing Discriminative Features for Dataset Distillation in Complex Scenarios

Primitive-Based 3D Human-Object Interaction Modelling and Programming

Efficient Dataset Distillation via Minimax Diffusion

Unsupervised Learning for Class Distribution Mismatch

Navigating Complexity: Toward Lossless Graph Condensation via Expanding Window Matching

DiffAug: Enhance Unsupervised Contrastive Learning with Domain-Knowledge-Free Diffusion-based Data Augmentation

GliDe with a CaPE: A Low-Hassle Method to Accelerate Speculative Decoding