LinkedIn

company

Verified

https://www.linkedin.com

AI & ML interests

None defined yet.

Recent Activity

pb09204048 authored a paper 6 days ago

TRIAGE: Role-Typed Credit Assignment for Agentic Reinforcement Learning

pb09204048 submitted a paper 10 days ago

TRIAGE: Role-Typed Credit Assignment for Agentic Reinforcement Learning

pb09204048 authored a paper 3 months ago

TIP: Token Importance in On-Policy Distillation

View all activity

Papers

TRIAGE: Role-Typed Credit Assignment for Agentic Reinforcement Learning

Support Tokens, Stability Margins, and a New Foundation for Robust LLMs

View all Papers

Articles

Unlocking Agentic RL Training for GPT-OSS: A Practical Retrospective

authored a paper 6 days ago

TRIAGE: Role-Typed Credit Assignment for Agentic Reinforcement Learning

Paper • 2606.32017 • Published 12 days ago • 12

submitted a paper to Daily Papers 10 days ago

TRIAGE: Role-Typed Credit Assignment for Agentic Reinforcement Learning

Paper • 2606.32017 • Published 12 days ago • 12

authored a paper 3 months ago

TIP: Token Importance in On-Policy Distillation

Paper • 2604.14084 • Published Apr 15 • 15

submitted a paper to Daily Papers 4 months ago

On-Policy Self-Distillation for Reasoning Compression

Paper • 2603.05433 • Published Mar 5 • 9

authored a paper 4 months ago

Overconfident Errors Need Stronger Correction: Asymmetric Confidence Penalties for Reinforcement Learning

Paper • 2602.21420 • Published Feb 24 • 6

submitted a paper to Daily Papers 4 months ago

Overconfident Errors Need Stronger Correction: Asymmetric Confidence Penalties for Reinforcement Learning

Paper • 2602.21420 • Published Feb 24 • 6

published an article 6 months ago

Article

Unlocking Agentic RL Training for GPT-OSS: A Practical Retrospective

LinkedIn

•

Jan 27

• 80

authored a paper 6 months ago

Debunk the Myth of SFT Generalization

Paper • 2510.00237 • Published Sep 30, 2025 • 2

authored a paper 9 months ago

Planner-R1: Reward Shaping Enables Efficient Agentic RL with Smaller LLMs

Paper • 2509.25779 • Published Sep 30, 2025 • 19

authored a paper over 2 years ago

Birbal: An efficient 7B instruct-model fine-tuned with curated datasets

Paper • 2403.02247 • Published Mar 4, 2024 • 1

authored a paper over 2 years ago

QuantEase: Optimization-based Quantization for Language Models

Paper • 2309.01885 • Published Sep 5, 2023 • 4