Zhen Dong

zhendongucb's activity

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

authored 4 papers about 2 months ago

R-KV: Redundancy-aware KV Cache Compression for Reasoning Models

Paper • 2505.24133 • Published May 30 • 1

Efficient Deweather Mixture-of-Experts with Uncertainty-aware Feature-wise Linear Modulation

Paper • 2312.16610 • Published Dec 27, 2023

CVPR 2023 Text Guided Video Editing Competition

Paper • 2310.16003 • Published Oct 24, 2023

DrafterBench: Benchmarking Large Language Models for Tasks Automation in Civil Engineering

Paper • 2507.11527 • Published Jul 15 • 31

authored a paper 8 months ago

Diffusion as Shader: 3D-aware Video Diffusion for Versatile Video Generation Control

Paper • 2501.03847 • Published Jan 7 • 23

authored 4 papers 11 months ago

Meissonic: Revitalizing Masked Generative Transformers for Efficient High-Resolution Text-to-Image Synthesis

Paper • 2410.08261 • Published Oct 10, 2024 • 53

An Item is Worth a Prompt: Versatile Image Editing with Disentangled Control

Paper • 2403.04880 • Published Mar 7, 2024 • 6

Interpolating Video-LLMs: Toward Longer-sequence LMMs in a Training-free Manner

Paper • 2409.12963 • Published Sep 19, 2024

K-Sort Arena: Efficient and Reliable Benchmarking for Generative Models via K-wise Human Preferences

Paper • 2408.14468 • Published Aug 26, 2024 • 38

authored 5 papers about 1 year ago

PB-LLM: Partially Binarized Large Language Models

Paper • 2310.00034 • Published Sep 29, 2023 • 2

QFT: Quantized Full-parameter Tuning of LLMs with Affordable Resources

Paper • 2310.07147 • Published Oct 11, 2023 • 1

LLM Inference Unveiled: Survey and Roofline Model Insights

Paper • 2402.16363 • Published Feb 26, 2024 • 2

Integrating View Conditions for Image Synthesis

Paper • 2310.16002 • Published Oct 24, 2023 • 3

MAgIC: Investigation of Large Language Model Powered Multi-Agent in Cognition, Adaptability, Rationality and Collaboration

Paper • 2311.08562 • Published Nov 14, 2023

authored a paper over 1 year ago

Magic-Me: Identity-Specific Video Customized Diffusion

Paper • 2402.09368 • Published Feb 14, 2024 • 31

authored 5 papers about 2 years ago

Q-Diffusion: Quantizing Diffusion Models

Paper • 2302.04304 • Published Feb 8, 2023 • 4

NoisyQuant: Noisy Bias-Enhanced Post-Training Activation Quantization for Vision Transformers

Paper • 2211.16056 • Published Nov 29, 2022 • 4

CSQ: Growing Mixed-Precision Quantization Scheme with Bi-level Continuous Sparsification

Paper • 2212.02770 • Published Dec 6, 2022

UnrealNAS: Can We Search Neural Architectures with Unreal Data?

Paper • 2205.02162 • Published May 4, 2022

Applications and Techniques for Fast Machine Learning in Science

Paper • 2110.13041 • Published Oct 25, 2021