Soroush Mehraban

SoroushMehraban's activity

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

upvoted 4 papers 6 days ago

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

Paper • 2602.23165 • Published 15 days ago • 2

Helios: Real Real-Time Long Video Generation Model

Paper • 2603.04379 • Published 9 days ago • 161

MIBURI: Towards Expressive Interactive Gesture Synthesis

Paper • 2603.03282 • Published 10 days ago • 4

OmniLottie: Generating Vector Animations via Parameterized Lottie Tokens

Paper • 2603.02138 • Published 11 days ago • 138

upvoted a paper 10 days ago

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

Paper • 2603.01301 • Published 12 days ago • 8

upvoted a paper 28 days ago

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

Paper • 2602.11451 • Published 30 days ago • 15

upvoted a paper 2 months ago

LTX-2: Efficient Joint Audio-Visual Foundation Model

Paper • 2601.03233 • Published Jan 6 • 166

upvoted 4 papers 3 months ago

Animate Any Character in Any World

Paper • 2512.17796 • Published Dec 18, 2025 • 11

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

Paper • 2512.16920 • Published Dec 18, 2025 • 18

Puzzle Curriculum GRPO for Vision-Centric Reasoning

Paper • 2512.14944 • Published Dec 16, 2025 • 36

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

Paper • 2512.14696 • Published Dec 16, 2025 • 8

upvoted 2 papers 5 months ago

FastHMR: Accelerating Human Mesh Recovery via Token and Layer Merging with Diffusion Decoding

Paper • 2510.10868 • Published Oct 13, 2025 • 12

PickStyle: Video-to-Video Style Transfer with Context-Style Adapters

Paper • 2510.07546 • Published Oct 8, 2025 • 22

upvoted a paper 9 months ago

Token Perturbation Guidance for Diffusion Models

Paper • 2506.10036 • Published Jun 10, 2025 • 5