Yushi Huang

Harahan's activity

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

authored 4 papers about 7 hours ago

Light Forcing: Accelerating Autoregressive Video Diffusion via Sparse Attention

Paper • 2602.04789 • Published 2 days ago • 2

LLMC: Benchmarking Large Language Model Quantization with a Versatile Compression Toolkit

Paper • 2405.06001 • Published May 9, 2024

Focus-dLLM: Accelerating Long-Context Diffusion LLM Inference via Confidence-Guided Context Focusing

Paper • 2602.02159 • Published 4 days ago

MoDES: Accelerating Mixture-of-Experts Multimodal Large Language Models via Dynamic Expert Skipping

Paper • 2511.15690 • Published Nov 19, 2025

submitted a paper to Daily Papers about 14 hours ago

Focus-dLLM: Accelerating Long-Context Diffusion LLM Inference via Confidence-Guided Context Focusing

Paper • 2602.02159 • Published 4 days ago

upvoted a paper about 18 hours ago

Light Forcing: Accelerating Autoregressive Video Diffusion via Sparse Attention

Paper • 2602.04789 • Published 2 days ago • 2

submitted a paper to Daily Papers about 18 hours ago

Light Forcing: Accelerating Autoregressive Video Diffusion via Sparse Attention

Paper • 2602.04789 • Published 2 days ago • 2

liked 2 models 4 days ago

Harahan/QVGen-CogVideoX-2B-W4A4

Text-to-Video • Updated 5 days ago • 22 • 1

Harahan/QVGen-Wan-1_3B-W4A4

Text-to-Video • Updated 5 days ago • 30 • 2

authored a paper 4 days ago

Temporal Feature Matters: A Framework for Diffusion Model Quantization

Paper • 2407.19547 • Published Jul 28, 2024

updated 2 models 5 days ago

Harahan/QVGen-CogVideoX-2B-W4A4

Text-to-Video • Updated 5 days ago • 22 • 1

Harahan/QVGen-Wan-1_3B-W4A4

Text-to-Video • Updated 5 days ago • 30 • 2

updated a collection 5 days ago

QVGen

Collection

This is the official checkpoint collection of paper: https://arxiv.org/pdf/2505.11497 • 3 items • Updated 5 days ago

updated a collection 7 days ago

QVGen

Collection

This is the official checkpoint collection of paper: https://arxiv.org/pdf/2505.11497 • 3 items • Updated 5 days ago

published 2 models 7 days ago

Harahan/QVGen-CogVideoX-2B-W4A4

Text-to-Video • Updated 5 days ago • 22 • 1

Harahan/QVGen-Wan-1_3B-W4A4

Text-to-Video • Updated 5 days ago • 30 • 2

authored 2 papers about 1 month ago

SlimInfer: Accelerating Long-Context LLM Inference via Dynamic Token Pruning

Paper • 2508.06447 • Published Aug 8, 2025

LinVideo: A Post-Training Framework towards O(n) Attention in Efficient Video Generation

Paper • 2510.08318 • Published Oct 9, 2025

upvoted a paper 5 months ago

WebWeaver: Structuring Web-Scale Evidence with Dynamic Outlines for Open-Ended Deep Research

Paper • 2509.13312 • Published Sep 16, 2025 • 105