Good Papers

Showing papers from Microsoft Research Show all papers

45%Niche pick
?Niche pickVote to see the score
NeurIPS 2026MicrosoftMicrosoft ResearchResearch, MicrosoftMicrosoft Research, Redmond, WAMeta, transfer & few-shot learning

Test-Time Learning with an Evolving Library

Weijia Xu, Alessandro Sordoni, Chandan Singh, Zelalem Gero and 3 more

Sydney Poster Session 3, Wed, Dec 9, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet
0/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 0 of 20 reviewers recommend it
lenient 0/5
medium 0/10
strict 0/5
45%Niche pick
?Niche pickVote to see the score
NeurIPS 2026CornellU CambridgeHarvardMicrosoft ResearchLLM pretraining & scaling laws

Express Language Modeling

Albert Gong, Annabelle M Carrell, Raaz Dwivedi, Lester Mackey

Atlanta Poster Session 1, Wed, Dec 9, 10:00 AM–1:00 PM, Hall C1 · Published 2026

– ReadersNo votes yet
0/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 0 of 20 reviewers recommend it
lenient 0/5
medium 0/10
strict 0/5
57%Worth a look
?Worth a lookVote to see the score
NeurIPS 2026TongjiMicrosoft ResearchMultimodal reasoning

CMI-Trans: Cross Modal Inconsistency-aware Transport for HSI-LiDAR Classification

Yanli Li, Xuan Tan, Ding Qi, XINYANG JIANG

Sydney Poster Session 5, Thu, Dec 10, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet
1/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 1 of 20 reviewers recommend it
lenient 1/5
medium 0/10
strict 0/5
57%Worth a look
?Worth a lookVote to see the score
NeurIPS 2026UC BerkeleyMicrosoft ResearchU California, BerkeleyOpenAIEECS, UC BerkeleyEfficient inference & serving

SPECS: Faster Test-Time Scaling through Speculative Drafts and Dynamic Switching

Mert Cemri, Nived Rajaraman, Rishabh Tiwari, Xiaoxuan Liu and 5 more

Sydney Poster Session 1, Tue, Dec 8, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet
1/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 1 of 20 reviewers recommend it
lenient 1/5
medium 0/10
strict 0/5
67%Highly rated
?Highly ratedVote to see the score
NeurIPS 2026MicrosoftU WashingtonStanfordResearch, MicrosoftPUC-RIORL for LLMs

Multi-Turn RL Makes Small Language Model Competitive for Optimization Modeling

Xinzhi Zhang, Zeyi Chen, Humishka Zope, Hugo Barbalho and 5 more

Atlanta Poster Session 2, Wed, Dec 9, 4:30 PM–7:30 PM, Hall C1 · Published 2026

– ReadersNo votes yet
2/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 2 of 20 reviewers recommend it
lenient 2/5
medium 0/10
strict 0/5
45%Niche pick
?Niche pickVote to see the score
NeurIPS 2026OralNanyang TechnologicalU Science and Technology of ChinUSTCMicrosoft ResearchNTUMultimodal reasoning

Thinking with Images as Continuous Policy: Numerical Visual Chain-of-Thought

Kesen Zhao, Beier Zhu, Junbao Zhou, Xingyu Zhu and 2 more

Sydney Poster Session 1, Tue, Dec 8, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet
0/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 0 of 20 reviewers recommend it
lenient 0/5
medium 0/10
strict 0/5
57%Worth a look
?Worth a lookVote to see the score
NeurIPS 2026The Chinese University of Hong KNanyang TechnologicalSaarland Informatics Campus, MaxThe Chinese University of Hong KMicrosoft ResearchVideo generation

GeoMemory: Geometry-Indexed Memory for Long-Horizon Interactive Video Generation

Junchao Huang, Xinting Hu, Boyao Han, Shaoshuai Shi and 3 more

Sydney Poster Session 5, Thu, Dec 10, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet
1/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 1 of 20 reviewers recommend it
lenient 1/5
medium 0/10
strict 0/5
45%Niche pick
?Niche pickVote to see the score
NeurIPS 2026U Technology SydneyTsinghuaMicrosoft ResearchMicrosoftTsinghua University, TsinghuaVision-language-action models

Unified Noise Steering for Efficient Human-Guided VLA Adaptation

Junjie Lu, Xinyao Qin, Yuhua Jiang, Kaixin Wang and 5 more

Sydney Poster Session 6, Thu, Dec 10, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet
0/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 0 of 20 reviewers recommend it
lenient 0/5
medium 0/10
strict 0/5
45%Niche pick
?Niche pickVote to see the score
NeurIPS 2026Indian Institute of Technology, MicrosoftAalto University / IIT BombayIIT BombayMicrosoft Research Lab IndiaGraphs & LLMs

Active Corpus Selection for Training Subgraph Retrievers Using OOD Queries

Pritish Chakraborty, Aditya Singh, Indradyumna Roy, Lokesh N and 7 more

Sydney Poster Session 1, Tue, Dec 8, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet
0/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 0 of 20 reviewers recommend it
lenient 0/5
medium 0/10
strict 0/5
57%Worth a look
?Worth a lookVote to see the score
NeurIPS 2026Tohoku University, Institute of RIKEN AIPMicrosoft ResearchRIKEN/University of TokyoRIKENFairness & bias

Practical Estimation of the Bayes Optimal Fairness-Accuracy Tradeoff with Soft Labels

mohit sharma, Okan Koc, Amit Jayant Deshpande, Takashi Ishida and 3 more

Sydney Poster Session 3, Wed, Dec 9, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet
1/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 1 of 20 reviewers recommend it
lenient 1/5
medium 0/10
strict 0/5
57%Worth a look
?Worth a lookVote to see the score
NeurIPS 2026Washington University in St. LouMicrosoft ResearchImitation learning

Skill-Level Effects in Behavioral Cloning: When Low-Skill Data Improves Performance

Saumik Narayanan, Kassa Korley, Siddhartha Sen, Chien-Ju Ho

Sydney Poster Session 5, Thu, Dec 10, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet
1/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 1 of 20 reviewers recommend it
lenient 0/5
medium 0/10
strict 1/5
45%Niche pick
?Niche pickVote to see the score
NeurIPS 2026ETH AI Center, ZurichU California BerkeleyUIUCEPFLU California, BerkeleyImitation learning

When Does Interaction Help? Representational Tradeoffs in Value-Based Imitation Learning

Luca Viano, Antoine Moulin, Audrey Huang, Volkan Cevher and 2 more

Sydney Poster Session 2, Tue, Dec 8, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet
0/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 0 of 20 reviewers recommend it
lenient 0/5
medium 0/10
strict 0/5
57%Worth a look
?Worth a lookVote to see the score
NeurIPS 2026U CambridgeMicrosoft ResearchAlibaba GroupRL for LLMs

Reward Budgeting Reduces Premature Convergence in Reinforcement Learning for LLM Reasoning

Mengni Jia, Mengyu Zhou, xiaoxi jiang, Guanjun Jiang

Sydney Poster Session 5, Thu, Dec 10, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet
1/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 1 of 20 reviewers recommend it
lenient 1/5
medium 0/10
strict 0/5
57%Worth a look
?Worth a lookVote to see the score
NeurIPS 2026ProximalMicrosoft ResearchMicrosoftLLM evaluation & benchmarks

fxBench: Evaluating and Understanding Formula Suggestions in Spreadsheets

Sanket Mhatre, Sumit Gulwani, Vu Le, Yasharth Bajpai and 1 more

Sydney Poster Session 2, Tue, Dec 8, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet
1/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 1 of 20 reviewers recommend it
lenient 1/5
medium 0/10
strict 0/5
57%Worth a look
?Worth a lookVote to see the score
NeurIPS 2026U Illinois at Urbana-ChampaignMicrosoft AIMicrosoftMicrosoft ResearchUIUCSparse autoencoders

Cascaded Sparse Autoencoders LearnMulti-Level Visual Concepts in Multimodal LLMs

Yusong Zhao, Hengyi Wang, Tanuja Ganu, Akshay Nambi and 1 more

Sydney Poster Session 4, Wed, Dec 9, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet
1/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 1 of 20 reviewers recommend it
lenient 1/5
medium 0/10
strict 0/5
70%Highly rated
?Highly ratedVote to see the score
NeurIPS 2026UC BerkeleyMicrosoftMicrosoft ResearchProteins

Bigger Isn’t Better: Why the Indiscriminate Scaling of Foundation Models Can’t Solve Biology

Kathryne Metcalf, Lorin Crawford, Mary L Gray, Kevin K Yang and 1 more

Sydney Poster Session 2, Tue, Dec 8, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet
4/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 4 of 20 reviewers recommend it
lenient 2/5
medium 1/10
strict 1/5
57%Worth a look
?Worth a lookVote to see the score
NeurIPS 2026MicrosoftMicrosoft ResearchGoogle DeepmindMicrosoft Research AsiaMulti-agent LLM systems

The Era of Agentic Organization: Learning to Organize with Language Models

Zewen Chi, Li Dong, Qingxiu Dong, Yaru Hao and 3 more

Sydney Poster Session 6, Thu, Dec 10, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet
1/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 1 of 20 reviewers recommend it
lenient 1/5
medium 0/10
strict 0/5
45%Niche pick
?Niche pickVote to see the score
NeurIPS 2026Microsoft ResearchMicrosoftIndian Institute of Technology, IIT BombayOptimization

A Cross-Interaction Neural Architecture for Submodular Functions

SOUTRIK SARANGI, Aditya Singh, Vansh Maheshwari, Abir De

Sydney Poster Session 3, Wed, Dec 9, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet
0/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 0 of 20 reviewers recommend it
lenient 0/5
medium 0/10
strict 0/5
57%Worth a look
?Worth a lookVote to see the score
NeurIPS 2026NortheasternCarnegie MellonMicrosoft ResearchNortheastern University, ChinaFudanRL for LLMs

What are Key Factors for Updates in RL for LLM Reasoning?

Peidong Wang, Demi Wang, Xufang Luo, Jiahang Xu and 4 more

Paris Poster Session 6, Fri, Dec 11, 2:30 PM–4:30 PM, Paris Poster Hall · Published 2026

– ReadersNo votes yet
1/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 1 of 20 reviewers recommend it
lenient 1/5
medium 0/10
strict 0/5
76%Highly rated
?Highly ratedVote to see the score
NeurIPS 2026ColumbiaThe Chinese University of Hong KDartmouth CollegeMicrosoftMicrosoft ResearchLLM agents & planning

Reinforcement World Model Learning for LLM-based Agents

RWML learns action-conditioned world models for LLM agents via self-supervised sim-to-real alignment, outperforming direct task-success RL by up to 6.9 points without expert data.

Xiao Yu, Baolin Peng, Ruize Xu, yelong shen and 5 more

Sydney Poster Session 1, Tue, Dec 8, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026 · ▲ 28 on Hugging Face

– ReadersNo votes yet
10/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 10 of 20 reviewers recommend it
lenient 4/5
medium 6/10
strict 0/5
Show 20 more papers