Soroush Mehraban

SoroushMehraban's activity

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

upvoted a paper 2 days ago

Multi-Resolution Flow Matching: Training-Free Diffusion Acceleration via Staged Sampling

Paper • 2607.01642 • Published 4 days ago • 28

upvoted a paper 4 days ago

PhotoQuilt: Training-Free Arbitrary-Resolution Photomosaics via Bootstrapped Tiled Denoising

Paper • 2606.30968 • Published 7 days ago • 24

upvoted a paper about 1 month ago

SEGA: Spectral-Energy Guided Attention for Resolution Extrapolation in Diffusion Transformers

Paper • 2605.22668 • Published May 21 • 41

upvoted 3 papers 3 months ago

HY-World 2.0: A Multi-Modal World Model for Reconstructing, Generating, and Simulating 3D Worlds

Paper • 2604.14268 • Published Apr 15 • 127

Woosh: A Sound Effects Foundation Model

Paper • 2604.01929 • Published Apr 2 • 12

Steerable Visual Representations

Paper • 2604.02327 • Published Apr 2 • 56

upvoted 5 papers 4 months ago

DyaDiT: A Multi-Modal Diffusion Transformer for Socially Favorable Dyadic Gesture Generation

Paper • 2602.23165 • Published Feb 26 • 3

Helios: Real Real-Time Long Video Generation Model

Paper • 2603.04379 • Published Mar 4 • 190

MIBURI: Towards Expressive Interactive Gesture Synthesis

Paper • 2603.03282 • Published Mar 3 • 4

OmniLottie: Generating Vector Animations via Parameterized Lottie Tokens

Paper • 2603.02138 • Published Mar 2 • 151

When Does RL Help Medical VLMs? Disentangling Vision, SFT, and RL Gains

Paper • 2603.01301 • Published Mar 1 • 8

upvoted a paper 5 months ago

LoopFormer: Elastic-Depth Looped Transformers for Latent Reasoning via Shortcut Modulation

Paper • 2602.11451 • Published Feb 11 • 17

updated a dataset 5 months ago

Pickford/PickStyle-Dataset

Viewer • Updated Jan 21 • 801 • 1.97k • 1

upvoted a paper 6 months ago

LTX-2: Efficient Joint Audio-Visual Foundation Model

Paper • 2601.03233 • Published Jan 6 • 183

updated a model 6 months ago

Pickford/PickStyle

Updated Dec 31, 2025

published a model 6 months ago

Pickford/PickStyle

Updated Dec 31, 2025

published a dataset 6 months ago

Pickford/PickStyle-Dataset

Viewer • Updated Jan 21 • 801 • 1.97k • 1

upvoted a paper 6 months ago

Animate Any Character in Any World

Paper • 2512.17796 • Published Dec 18, 2025 • 12

upvoted 2 papers 7 months ago

EasyV2V: A High-quality Instruction-based Video Editing Framework

Paper • 2512.16920 • Published Dec 18, 2025 • 18

PuzzleCraft: Exploration-Aware Curriculum Learning for Puzzle-Based RLVR in VLMs

Paper • 2512.14944 • Published Mar 13 • 36