Microsoft Research

company

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

Activity Feed

AI & ML interests

None defined yet.

Recent Activity

ParadiseYu submitted a paper about 5 hours ago

Weak-to-Strong On-Policy Distillation

akshaynambi submitted a paper 4 days ago

Echoverse: Deep, Evolving Environments for Training Computer-Use Agents at Scale

baohao submitted a paper 11 days ago

Multi-Turn On-Policy Distillation with Prefix Replay

View all activity

Papers

Echoverse: Deep, Evolving Environments for Training Computer-Use Agents at Scale

Weak-to-Strong On-Policy Distillation

View all Papers

ParadiseYu

submitted a paper to Daily Papers about 5 hours ago

Weak-to-Strong On-Policy Distillation

Paper • 2607.26246 • Published 7 days ago • 46

akshaynambi

submitted a paper to Daily Papers 4 days ago

Echoverse: Deep, Evolving Environments for Training Computer-Use Agents at Scale

Paper • 2607.28074 • Published 5 days ago • 10

baohao

submitted a paper to Daily Papers 11 days ago

Multi-Turn On-Policy Distillation with Prefix Replay

Paper • 2607.04763 • Published 19 days ago • 12

ytz20

submitted a paper to Daily Papers 14 days ago

LLM-as-a-Coach: Experiential Learning for Non-Verifiable Tasks

Paper • 2607.18110 • Published 15 days ago • 14

kinam0252

submitted a paper to Daily Papers about 1 month ago

Object-Centric Residual RL for Zero-Shot Sim-to-Real VLA Enhancement

Paper • 2606.18953 • Published Jun 17 • 7

AmirhosseinAbaskohi

submitted a paper to Daily Papers about 2 months ago

ReVision: Scaling Computer-Use Agents via Temporal Visual Redundancy Reduction

Paper • 2605.11212 • Published Jun 5 • 5

lhmd

submitted a paper to Daily Papers about 2 months ago

Latent Spatial Memory for Video World Models

Paper • 2606.09828 • Published Jun 8 • 71

vshrivas

submitted a paper to Daily Papers 2 months ago

ECHO: Terminal Agents Learn World Models for Free

Paper • 2605.24517 • Published May 23 • 8

qianhuiwu

submitted a paper to Daily Papers 3 months ago

Orchard: An Open-Source Agentic Modeling Framework

Paper • 2605.15040 • Published May 14 • 21

beanie00

submitted a paper to Daily Papers 3 months ago

Rebellious Student: Reversing Teacher Signals for Reasoning Exploration with Self-Distilled RLVR

Paper • 2605.10781 • Published May 11 • 17

lhmd

submitted a paper to Daily Papers 3 months ago

World-R1: Reinforcing 3D Constraints for Text-to-Video Generation

Paper • 2604.24764 • Published Apr 27 • 119

adi8196

submitted a paper to Daily Papers 3 months ago

Mind's Eye: A Benchmark of Visual Abstraction, Transformation and Composition for Multimodal LLMs

Paper • 2604.16054 • Published Apr 17 • 1

unilm

submitted a paper to Daily Papers 4 months ago

Universal YOCO for Efficient Depth Scaling

Paper • 2604.01220 • Published Apr 1 • 19

Yif29

submitted a paper to Daily Papers 4 months ago

BizGenEval: A Systematic Benchmark for Commercial Visual Content Generation

Paper • 2603.25732 • Published Mar 26 • 11

beanie00

submitted a paper to Daily Papers 4 months ago

Why Does Self-Distillation (Sometimes) Degrade the Reasoning Capability of LLMs?

Paper • 2603.24472 • Published Mar 25 • 57

unilm

submitted a paper to Daily Papers 5 months ago

Online Experiential Learning for Language Models

Paper • 2603.16856 • Published Mar 17 • 60

beanie00

submitted a paper to Daily Papers 5 months ago

Understanding Reasoning in LLMs through Strategic Information Allocation under Uncertainty

Paper • 2603.15500 • Published Mar 16 • 12

ZongqianLi

submitted 2 papers to Daily Papers 5 months ago

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

Paper • 2603.07779 • Published Mar 8 • 5

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

Paper • 2603.07777 • Published Mar 8 • 5

ACID23333

submitted a paper to Daily Papers 5 months ago

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

Paper • 2603.05168 • Published Mar 5 • 6

AI & ML interests

Recent Activity

Papers

Team members 1

MicrosoftResearch's activity