yangsui's picture

1 8

yangsui

yangsui

·

AI & ML interests

None yet

Recent Activity

upvoted a paper 26 days ago

When Tokens Talk Too Much: A Survey of Multimodal Long-Context Token Compression across Images, Videos, and Audios

upvoted a paper about 1 month ago

4KAgent: Agentic Any Image to 4K Super-Resolution

upvoted a paper 2 months ago

Give Me FP32 or Give Me Death? Challenges and Solutions for Reproducible Reasoning

View all activity

Organizations

None yet

authored a paper 3 months ago

HoliTom: Holistic Token Merging for Fast Video Large Language Models

Paper • 2505.21334 • Published May 27 • 20

authored 2 papers 4 months ago

Plug-and-Play 1.x-Bit KV Cache Quantization for Video Large Language Models

Paper • 2503.16257 • Published Mar 20 • 25

70% Size, 100% Accuracy: Lossless LLM Compression for Efficient GPU Inference via Dynamic-Length Float

Paper • 2504.11651 • Published Apr 15 • 30

authored 3 papers 5 months ago

DyCoke: Dynamic Compression of Tokens for Fast Video Large Language Models

Paper • 2411.15024 • Published Nov 22, 2024 • 1

SnapGen-V: Generating a Five-Second Video within Five Seconds on a Mobile Device

Paper • 2412.10494 • Published Dec 13, 2024 • 2

Stop Overthinking: A Survey on Efficient Reasoning for Large Language Models

Paper • 2503.16419 • Published Mar 20 • 76

authored 2 papers about 1 year ago

In-Sensor Radio Frequency Computing for Energy-Efficient Intelligent Radar

Paper • 2312.10343 • Published Dec 16, 2023 • 1

BitsFusion: 1.99 bits Weight Quantization of Diffusion Model

Paper • 2406.04333 • Published Jun 6, 2024 • 39