Somshubra Majumdar

smajumdar94's activity

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

upvoted a paper 4 days ago

Weak-to-Strong Generalization via Direct On-Policy Distillation

Paper • 2607.05394 • Published Jul 8 • 147

upvoted a paper 6 days ago

SWE-Bench ProMax: Benchmarking Agents on Large-Scale Multilingual Code Refactoring

Paper • 2608.09802 • Published 8 days ago • 128

upvoted a paper about 1 month ago

LongStraw: Long-Context RL Beyond 2M Tokens under a Fixed GPU Budget

Paper • 2607.14952 • Published Jul 16 • 212

upvoted 2 papers 3 months ago

Rubric-based On-policy Distillation

Paper • 2605.07396 • Published May 8 • 41

Unmasking On-Policy Distillation: Where It Helps, Where It Hurts, and Why

Paper • 2605.10889 • Published May 11 • 6

upvoted 2 papers 5 months ago

SKILL0: In-Context Agentic Reinforcement Learning for Skill Internalization

Paper • 2604.02268 • Published Apr 2 • 103

daVinci-Env: Open SWE Environment Synthesis at Scale

Paper • 2603.13023 • Published Mar 13 • 30

upvoted a collection 5 months ago

Nemotron-Post-Training-v3

Collection

Collection of datasets used in the post-training phase of Nemotron Nano, Super, and Ultra v3. • 50 items • Updated 6 days ago • 195

upvoted a paper 6 months ago

BeyondSWE: Can Current Code Agent Survive Beyond Single-Repo Bug Fixing?

Paper • 2603.03194 • Published Mar 3 • 57

upvoted 2 articles 6 months ago

view article

Article

Custom Kernels for All from Codex and Claude

• 
• 
• +2

burtenshaw, sayakpaul, ariG23498, evalstate

•

Feb 13

• 81

view article

Article

Forge: Scalable Agent RL Framework and Algorithm

• 

MiniMax-AI

•

Feb 13

• 157

upvoted an article 7 months ago

view article

Article

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

• 
• 
• +2

burtenshaw, evalstate, merve, pcuenq

•

Jan 28

• 159

upvoted a collection 8 months ago

Openhands Trajectories

Collection

Dataset of 67,074 OpenHands trajectories collected with Qwen3-Coder-480B-A35B-Instruct and two RFT checkpoints trained on the data • 3 items • Updated Dec 23, 2025 • 9

upvoted a paper 9 months ago

From Code Foundation Models to Agents and Applications: A Practical Guide to Code Intelligence

Paper • 2511.18538 • Published Nov 23, 2025 • 306

upvoted 3 papers 11 months ago

DeepSearch: Overcome the Bottleneck of Reinforcement Learning with Verifiable Rewards via Monte Carlo Tree Search

Paper • 2509.25454 • Published Sep 29, 2025 • 147

On the Generalization of SFT: A Reinforcement Learning Perspective with Reward Rectification

Paper • 2508.05629 • Published Aug 7, 2025 • 191

Parallel-R1: Towards Parallel Thinking via Reinforcement Learning

Paper • 2509.07980 • Published Sep 9, 2025 • 106

upvoted 2 papers 12 months ago

Towards a Unified View of Large Language Model Post-Training

Paper • 2509.04419 • Published Sep 4, 2025 • 77

Understanding Tool-Integrated Reasoning

Paper • 2508.19201 • Published Aug 26, 2025 • 32

upvoted an article 12 months ago

view article

Article

Supercharge Edge AI With High‑Accuracy Reasoning Using NVIDIA Nemotron Nano 2 9B

• 

nvidia

•

Aug 18, 2025

• 32