Haocheng Xi

xihc-ucb's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

upvoted a paper 2 days ago

Scaling RL to Long Videos

Paper • 2507.07966 • Published 2 days ago • 109

upvoted a collection 5 days ago

LPD

Collection

Locality-aware Parallel Decoding for Efficient Autoregressive Image Generation • 6 items • Updated 10 days ago • 1

upvoted a paper 9 days ago

Locality-aware Parallel Decoding for Efficient Autoregressive Image Generation

Paper • 2507.01957 • Published 10 days ago • 18

authored a paper 10 days ago

Radial Attention: $O(n\log n)$ Sparse Attention with Energy Decay for Long Video Generation

Paper • 2506.19852 • Published 18 days ago • 38

upvoted a paper 10 days ago

Radial Attention: O(nlog n) Sparse Attention with Energy Decay for Long Video Generation

Paper • 2506.19852 • Published 18 days ago • 38

upvoted a paper about 1 month ago

Fast-dLLM: Training-free Acceleration of Diffusion LLM by Enabling KV Cache and Parallel Decoding

Paper • 2505.22618 • Published May 28 • 42

commented a paper about 2 months ago

Sparse VideoGen2: Accelerate Video Generation with Sparse Attention via Semantic-Aware Permutation

Paper • 2505.18875 • Published May 24 • 41 •

2

authored 7 papers about 2 months ago

Jetfire: Efficient and Accurate Transformer Pretraining with INT8 Data Flow and Per-Block Quantization

Paper • 2403.12422 • Published Mar 19, 2024 • 1

COAT: Compressing Optimizer states and Activation for Memory-Efficient FP8 Training

Paper • 2410.19313 • Published Oct 25, 2024 • 19

T-Rex: Text-assisted Retrosynthesis Prediction

Paper • 2401.14637 • Published Jan 26, 2024

NVILA: Efficient Frontier Visual Language Models

Paper • 2412.04468 • Published Dec 5, 2024 • 60

Sparse VideoGen: Accelerating Video Diffusion Transformers with Spatial-Temporal Sparsity

Paper • 2502.01776 • Published Feb 3 • 2

QuantSpec: Self-Speculative Decoding with Hierarchical Quantized KV Cache

Paper • 2502.10424 • Published Feb 5 • 1

Sparse VideoGen2: Accelerate Video Generation with Sparse Attention via Semantic-Aware Permutation

Paper • 2505.18875 • Published May 24 • 41

upvoted 3 papers about 2 months ago

SageAttention3: Microscaling FP4 Attention for Inference and An Exploration of 8-Bit Training

Paper • 2505.11594 • Published May 16 • 73

Sparse VideoGen2: Accelerate Video Generation with Sparse Attention via Semantic-Aware Permutation

Paper • 2505.18875 • Published May 24 • 41

Sparse VideoGen: Accelerating Video Diffusion Transformers with Spatial-Temporal Sparsity

Paper • 2502.01776 • Published Feb 3 • 2