Manan Shah

cs-mshah's activity

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

upvoted an article about 18 hours ago

view article

Article

Custom Kernels for All from Codex and Claude

• 
• 
• +2

12 days ago

•

60

liked a model about 19 hours ago

nvidia/Qwen3.5-397B-A17B-NVFP4

Text Generation • Updated 6 days ago • 49.7k • 35

liked 2 datasets 4 days ago

tencent/HY3D-Bench

Updated 3 days ago • 62.4k • 82

cindyxl/ObjaversePlusPlus

Viewer • Updated Dec 4, 2025 • 789k • 481 • 15

upvoted a paper 9 days ago

GigaBrain-0.5M*: a VLA That Learns From World Model-Based Reinforcement Learning

Paper • 2602.12099 • Published 12 days ago • 56

updated a Space 17 days ago

Sleeping

Mesh Visualizer

🎬

Explore and view interactive data visualizations

published a Space 17 days ago

Sleeping

Mesh Visualizer

🎬

Explore and view interactive data visualizations

upvoted an article 25 days ago

view article

Article

We Got Claude to Build CUDA Kernels and teach open models!

• 
• 
• +2

28 days ago

•

139

upvoted a paper 29 days ago

SALAD: Achieve High-Sparsity Attention via Efficient Linear Attention Tuning for Video Diffusion Transformer

Paper • 2601.16515 • Published Jan 23 • 15

upvoted a paper about 1 month ago

Your Group-Relative Advantage Is Biased

Paper • 2601.08521 • Published Jan 13 • 154

liked a Space about 1 month ago

Running

52

Ai Paper Finder

👀

52

Find academic papers using keywords

liked a model about 1 month ago

nvidia/personaplex-7b-v1

Audio-to-Audio • Updated 9 days ago • 539k • 2.18k

upvoted a paper about 1 month ago

PhysRVG: Physics-Aware Unified Reinforcement Learning for Video Generative Models

Paper • 2601.11087 • Published Jan 16 • 11

liked a model about 1 month ago

rednote-hilab/dots.ocr

Image-Text-to-Text • Updated Oct 31, 2025 • 256k • 1.25k

liked a Space about 1 month ago

Running on CPU Upgrade

Featured

3.01k

The Smol Training Playbook

📚

3.01k

The secrets to building world-class LLMs

upvoted a paper about 1 month ago

STEP3-VL-10B Technical Report

Paper • 2601.09668 • Published Jan 14 • 193

liked a dataset about 1 month ago

facebook/action100m-preview

Viewer • Updated 26 days ago • 120k • 3.45k • 137

upvoted 2 papers about 1 month ago

VideoAuto-R1: Video Auto Reasoning via Thinking Once, Answering Twice

Paper • 2601.05175 • Published Jan 8 • 36

Watching, Reasoning, and Searching: A Video Deep Research Benchmark on Open Web for Agentic Video Reasoning

Paper • 2601.06943 • Published Jan 11 • 212

upvoted a paper about 2 months ago

Choreographing a World of Dynamic Objects

Paper • 2601.04194 • Published Jan 7 • 13