Soroush Mehraban

SoroushMehraban's activity

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

upvoted a paper 24 days ago

Puppeteer: Object-Grounded Posture-Aware Co-Speech Gesture Generation

Paper • 2609.00369 • Published Aug 31 • 22

upvoted a paper 25 days ago

SynthGait-19K: A Physically Grounded Synthetic Video Dataset for Gait Parameter Estimation

Paper • 2609.08108 • Published 26 days ago • 18

upvoted a paper 2 months ago

ATSplat: Compact Feed-forward 3D Gaussian Splatting with Adaptive Token Expansion

Paper • 2607.20417 • Published Jul 22 • 10

upvoted 2 papers 3 months ago

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

Paper • 2607.01642 • Published Jul 2 • 38

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

Paper • 2606.30968 • Published Jun 29 • 26

upvoted a paper 4 months ago

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

Paper • 2605.22668 • Published May 21 • 43

upvoted 3 papers 6 months ago

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

Paper • 2604.14268 • Published Apr 15 • 128

Woosh: A Sound Effects Foundation Model

Paper • 2604.01929 • Published Apr 2 • 10

Steerable Visual Representations

Paper • 2604.02327 • Published Apr 2 • 56

upvoted 5 papers 7 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 • 176

MIBURI: Towards Expressive Interactive Gesture Synthesis

Paper • 2603.03282 • Published Mar 3 • 5

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 8 months ago

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

Paper • 2602.11451 • Published Feb 11 • 18

upvoted a paper 9 months ago

LTX-2: Efficient Joint Audio-Visual Foundation Model

Paper • 2601.03233 • Published Jan 6 • 197

upvoted 4 papers 10 months ago

Animate Any Character in Any World

Paper • 2512.17796 • Published Dec 18, 2025 • 12

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

CRISP: Contact-Guided Real2Sim from Monocular Video with Planar Scene Primitives

Paper • 2512.14696 • Published Dec 16, 2025 • 8