Microsoft Research

company

https://www.microsoft.com/en-us/research/

AI & ML interests

None defined yet.

Recent Activity

ZongqianLi submitted a paper about 7 hours ago

Scaling Data Difficulty: Improving Coding Models via Reinforcement Learning on Fresh and Challenging Problems

ZongqianLi submitted a paper about 7 hours ago

Breaking Training Bottlenecks: Effective and Stable Reinforcement Learning for Coding Models

ACID23333 submitted a paper about 11 hours ago

Sparse-BitNet: 1.58-bit LLMs are Naturally Friendly to Semi-Structured Sparsity

View all activity

Papers

Scaling Data Difficulty: Improving Coding Models via Reinforcement Learning on Fresh and Challenging Problems

Breaking Training Bottlenecks: Effective and Stable Reinforcement Learning for Coding Models

View all Papers

submitted 2 papers to Daily Papers about 7 hours ago

Scaling Data Difficulty: Improving Coding Models via Reinforcement Learning on Fresh and Challenging Problems

Paper • 2603.07779 • Published 2 days ago • 2

Breaking Training Bottlenecks: Effective and Stable Reinforcement Learning for Coding Models

Paper • 2603.07777 • Published 2 days ago • 2

submitted a paper to Daily Papers about 11 hours ago

Sparse-BitNet: 1.58-bit LLMs are Naturally Friendly to Semi-Structured Sparsity

Paper • 2603.05168 • Published 5 days ago • 2

submitted a paper to Daily Papers about 18 hours ago

Scaling Agentic Capabilities, Not Context: Efficient Reinforcement Finetuning for Large Toolspaces

Paper • 2603.06713 • Published 5 days ago • 12

submitted a paper to Daily Papers 7 days ago

Learning When to Act or Refuse: Guarding Agentic Reasoning Models for Safe Multi-Step Tool Use

Paper • 2603.03205 • Published 7 days ago • 11

submitted a paper to Daily Papers about 1 month ago

Reinforcement World Model Learning for LLM-based Agents

Paper • 2602.05842 • Published Feb 5 • 27

submitted a paper to Daily Papers about 1 month ago

Efficient Autoregressive Video Diffusion with Dummy Head

Paper • 2601.20499 • Published Jan 28 • 8

submitted a paper to Daily Papers about 1 month ago

Self-Hinting Language Models Enhance Reinforcement Learning

Paper • 2602.03143 • Published Feb 3 • 30

submitted a paper to Daily Papers about 1 month ago

LIVE: Long-horizon Interactive Video World Modeling

Paper • 2602.03747 • Published Feb 3 • 12

submitted a paper to Daily Papers about 1 month ago

Training LLMs for Divide-and-Conquer Reasoning Elevates Test-Time Scalability

Paper • 2602.02477 • Published Feb 2 • 10

unilm

submitted a paper to Daily Papers about 2 months ago

Multiplex Thinking: Reasoning via Token-wise Branch-and-Merge

Paper • 2601.08808 • Published Jan 13 • 39