Yang You

41

Papers

208

Total Citations

Papers (41)

Real-Time Video Generation with Pyramid Attention Broadcast

Asynchronous Parallel Greedy Coordinate Descent

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

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

Can a Large Language Model be a Gaslighter?

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

PACE: Pose Annotations in Cluttered Environments

Info-Coevolution: An Efficient Framework for Data Model Coevolution

Canonical Voting: Towards Robust Oriented Bounding Box Detection in 3D Scenes

Modeling Motion With Multi-Modal Features for Text-Based Video Segmentation

CAFE: Learning To Condense Dataset by Aligning Features

CPPF: Towards Robust Category-Level 9D Pose Estimation in the Wild

Crafting Better Contrastive Views for Siamese Representation Learning

UKPGAN: A General Self-Supervised Keypoint Detector

An Efficient Training Approach for Very Large Scale Face Recognition

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

MSINet: Twins Contrastive Search of Multi-Scale Interaction for Object ReID

Preventing Zero-Shot Transfer Degradation in Continual Learning of Vision-Language Models

Dataset Quantization

DREAM: Efficient Dataset Distillation by Representative Matching

Human Correspondence Consensus for 3D Object Semantic Understanding

BiCro: Noisy Correspondence Rectification for Multi-Modality Data via Bi-Directional Cross-Modal Similarity Consistency

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

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

KeypointNet: A Large-Scale 3D Keypoint Dataset Aggregated From Numerous Human Annotations

Skeleton Merger: An Unsupervised Aligned Keypoint Detector

Towards Efficient and Scalable Sharpness-Aware Minimization

Random Sharpness-Aware Minimization

Does Graph Distillation See Like Vision Dataset Counterpart?

To Repeat or Not To Repeat: Insights from Scaling LLM under Token-Crisis

Response Length Perception and Sequence Scheduling: An LLM-Empowered LLM Inference Pipeline