UC Berkeley

Berkeley's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts

jacklishufan 

authored a paper 10 days ago

OmniFlow: Any-to-Any Generation with Multi-Modal Rectified Flows

Paper • 2412.01169 • Published 24 days ago • 11

jacklishufan 

authored 7 papers 22 days ago

InstructAny2Pix: Flexible Visual Editing via Multimodal Instruction Following

Paper • 2312.06738 • Published Dec 11, 2023

Hierarchical Open-vocabulary Universal Image Segmentation

Paper • 2307.00764 • Published Jul 3, 2023

Mamba-ND: Selective State Space Modeling for Multi-Dimensional Data

Paper • 2402.05892 • Published Feb 8

xT: Nested Tokenization for Larger Context in Large Images

Paper • 2403.01915 • Published Mar 4

Aligning Diffusion Models by Optimizing Human Utility

Paper • 2404.04465 • Published Apr 6 • 13

Scale-MAE: A Scale-Aware Masked Autoencoder for Multiscale Geospatial Representation Learning

Paper • 2212.14532 • Published Dec 30, 2022 • 1

SegLLM: Multi-round Reasoning Segmentation

Paper • 2410.18923 • Published Oct 24

brjathu 

authored a paper about 1 month ago

Scaling Properties of Diffusion Models for Perceptual Tasks

Paper • 2411.08034 • Published Nov 12 • 13

zeeshanp 

authored a paper about 1 month ago

Scaling Properties of Diffusion Models for Perceptual Tasks

Paper • 2411.08034 • Published Nov 12 • 13

g-luo 

authored 3 papers about 2 months ago

Diffusion Hyperfeatures: Searching Through Time and Space for Semantic Correspondence

Paper • 2305.14334 • Published May 23, 2023 • 1

Readout Guidance: Learning Control from Diffusion Features

Paper • 2312.02150 • Published Dec 4, 2023 • 3

Task Vectors are Cross-Modal

Paper • 2410.22330 • Published Oct 29 • 11

zhendongucb 

authored a paper 2 months ago

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

Paper • 2410.08261 • Published Oct 10 • 49

zhendongucb 

authored 3 papers 3 months ago

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

Paper • 2403.04880 • Published Mar 7 • 7

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

Paper • 2409.12963 • Published Sep 19

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

Paper • 2408.14468 • Published Aug 26 • 35

peterwg 

authored 2 papers 3 months ago

Deep Multimodal Fusion for Surgical Feedback Classification

Paper • 2312.03231 • Published Dec 6, 2023

Pose-Aware Self-Supervised Learning with Viewpoint Trajectory Regularization

Paper • 2403.14973 • Published Mar 22

zhendongucb 

authored a paper 5 months ago

PB-LLM: Partially Binarized Large Language Models

Paper • 2310.00034 • Published Sep 29, 2023 • 1