Manan Shah

cs-mshah's activity

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

authored a paper about 3 hours ago

MirrorVerse: Pushing Diffusion Models to Realistically Reflect the World

Paper • 2504.15397 • Published Apr 21, 2025

authored a paper about 4 hours ago

Lift4D: Harmonizing Single-View 3D Estimation for 4D Reconstruction In-the-Wild

Paper • 2606.23688 • Published 4 days ago • 4

upvoted a paper about 18 hours ago

Lift4D: Harmonizing Single-View 3D Estimation for 4D Reconstruction In-the-Wild

Paper • 2606.23688 • Published 4 days ago • 4

liked a model 4 days ago

Lightricks/LTX-2.3-22b-IC-LoRA-Ingredients

Video-to-Video • Updated 8 days ago • 78

liked a dataset 8 days ago

FudanCVL/EffectErase

Viewer • Updated Mar 26 • 781k • 784 • 18

liked a model 19 days ago

Lightricks/LTX-2.3-22b-IC-LoRA-Union-Control

Any-to-Any • Updated Apr 13 • 86

upvoted a paper 21 days ago

Crafter: A Multi-Agent Harness for Editable Scientific Figure Generation from Diverse Inputs

Paper • 2605.30611 • Published 29 days ago • 247

liked a dataset 22 days ago

htdong/Wan-Alpha-dataset

Viewer • Updated Mar 10 • 445 • 73 • 1

liked a model 24 days ago

nvidia/LocateAnything-3B

Image-Text-to-Text • 4B • Updated 13 days ago • 408k • 2.35k

upvoted 2 papers about 2 months ago

Leveraging Verifier-Based Reinforcement Learning in Image Editing

Paper • 2604.27505 • Published Apr 30 • 58

Representation Fréchet Loss for Visual Generation

Paper • 2604.28190 • Published Apr 30 • 32

liked a Space about 2 months ago

Running

230

FineVision: Open Data is All You Need

📝

230

A new open-source dataset for training VLMs

liked a dataset 2 months ago

apple/DFNDR-12M-bf16

Viewer • Updated May 22 • 12.8M • 127 • 3

liked 2 models 2 months ago

Qwen/Qwen3.6-27B

Image-Text-to-Text • 28B • Updated Apr 24 • 5.69M • • 1.8k

Qwen/Qwen3.6-27B-FP8

Image-Text-to-Text • 28B • Updated Apr 24 • 5.22M • 286

upvoted a paper 2 months ago

Extending One-Step Image Generation from Class Labels to Text via Discriminative Text Representation

Paper • 2604.18168 • Published Apr 20 • 96

liked a Space 2 months ago

Running

Featured

88

Distilling 100B+ Models 40x Faster with TRL

📝

88

TRL distillation for 100B+ teachers, 40x faster

upvoted 2 articles 3 months ago

view article

Article

2. Attention Optimizations: From Standard Attention to FlashAttention

• 

atharv6f

•

Feb 9

• 2

view article

Article

Keep the Tokens Flowing: Lessons from 16 Open-Source RL Libraries

• 
• 
• +7

aminediroHF, qgallouedec, kashif, lewtun, edbeeching, albertvillanova, nouamanetazi, lvwerra, sergiopaniego

•

Mar 10

• 164

liked a dataset 3 months ago

allenai/MolmoWeb-SyntheticTrajs

Viewer • Updated Apr 10 • 108k • 1.09k • 11