6 days 57:44 De novo Generation for Molecular Structure Elucidation from Mass Spectrometry
Recent advances in generative AI are enabling new approaches to scientific discovery in chemistry and biology.
220
6 days 47:42 Constrained Generative AI for Materials Inverse Design
Materials inverse design aims to discover new compounds with targeted structural and functional properties, but the search space is vast and strongly constrained by chemistry and physics.
473
7.5
6 days 1:01:50 Emerging Hardware Acceleration for Fully Homomorphic Encryption
Host: Patrick Longa, Microsoft Research Redmond Speaker: Minxuan Zhou, Illinois Institute of Technology Fully homomorphic encryption (FHE) is crucial for post-quantum privacy-preserving computing.
254
15 days 1:12:40 A non-Markovian approach to diffusion-based sampling
Recently, measure transport via stochastic processes - where samples from a simple prior are evolved toward a target measure specified only by an unnormalized density - has gained significant
334
8.9
15 days 40:07 Where the Score Lives: What Wavelets Reveal About Diffusion Models
Diffusion models have had remarkable success in generating a diverse set of visually plausible images.
146
15 days 52:55 Wavefunction Flows: Efficient Quantum Simulation of Continuous Flow Models
Continuous flow models transform Gaussian noise into samples from a learned distribution that closely approximates a complex data distribution.
211
15 days 58:30 Q-learning with Flow-Matching Policies
Expressive policies such as diffusion and flow-matching policies have recently driven progress in robotic manipulation because they can model complex action distributions and generalize from just a
204
15 days 1:08:08 Extending measure dynamics beyond generative modeling
Transport-based generative models, such as score-based diffusion and flow-matching, are a leading paradigm for learning complex data distributions.
141
15 days 1:20:43 Physics and information theory of generative diffusion
Diffusion models generate structure by progressively transforming noise into data, yet the mechanisms underlying this transition remain poorly understood.
167
15 days 1:11:49 Designing Dynamic Measure Transport for Sampling
Sampling from a target probability distribution is fundamental to modern computational science and machine learning.
112
15 days 44:50 Matching features, not tokens: Energy-based fine-tuning of language models
Cross-entropy (CE) training provides dense and scalable supervision for language models, but it optimizes next-token prediction under teacher forcing rather than sequence-level behavior under model
57
15 days 59:04 Meta Flow Maps
Controlling generative models—whether via inference-time steering or fine-tuning—is expensive. Control relies on estimating the value function—typically necessitating costly trajectory simulations.
202
15 days 1:06:47 Generative Models for Molecular Dynamics Across Timescales
The primary computational bottleneck in molecular dynamics is the timescale gap between the microscopic timesteps required for numerical integration and the macroscopic timescales of biological
232
15 days 50:42 Generative AI for High-Stakes Decision-Making with Applications in One Health
With rapid advances in machine learning, data-driven methods have become a powerful tool for decision making.
119
15 days 43:40 Data-Driven Discovery and Verification of Singularities in Nonlinear Partial Differential Equations
Motivated by the Clay Prize problem on the blowup of Navier-Stokes equations (NSE), I present numerical approaches that facilitate deeper insights into singularity formation, demonstrating that
106
15 days 55:26 Tractable Mapping Entropy and Generative Backmapping via Split-Flows
The transition between fine-grained and coarse-grained representations in molecular dynamics is a fundamental problem for multiscale modeling.
182
15 days 56:15 A Unified Approach to Analysis and Design of Denoising Markov Models
Diffusion and flow-based generative models can be viewed through the lens of measure transport via Markovian stochastic dynamics, where the choice of dynamics critically shapes both theory and
68
15 days 51:59 Blind denoising diffusion models and the blessings of dimensionality
We analyze, theoretically and empirically, the performance of generative diffusion models based on blind denoisers, in which the denoiser is not given the noise amplitude in either the training or
95
18 days 1:05 Test-time verification for AI agents: New from Microsoft Research #ai #agenticai #verification
Register to know when there are new releases out of MSR: microsoft.com/en-us/research/event/microsoft-research-forum/?OCID=MSR_Researchforum_YT
751
31
19 days 0:40 AI that runs your repo in GitHub : New from Microsoft Research #ai #agenticai #github #workflow
Register to know when there are new releases out of MSR: microsoft.com/en-us/research/event/microsoft-research-forum/?OCID=MSR_Researchforum_YT
1 001
41.3
20 days 0:39 AI that runs your repo in GitHub : New from Microsoft Research #ai #agenticai #github #workflow
Register to know when there are new releases out of MSR: microsoft.com/en-us/research/event/microsoft-research-forum/?OCID=MSR_Researchforum_YT
920
23.3
21 day 0:58 Test-time verification for AI agents: New from Microsoft Research #ai #agenticai #verification
Register to know when there are new releases out of MSR: microsoft.com/en-us/research/event/microsoft-research-forum/?OCID=MSR_Researchforum_YT
826
91.4
22 days 2:18 New tools, models, repos, and papers out of Microsoft Research are here. #ai #llm #github #agenticai
Register to know when there are new releases out of MSR: microsoft.com/en-us/research/event/microsoft-research-forum/?OCID=MSR_Researchforum_YT
2 294
54.2
22 days 0:31 New tools, models, repos, and papers out of Microsoft Research are here.
Register to know when there are new releases out of MSR: microsoft.com/en-us/research/event/microsoft-research-forum/?OCID=MSR_Researchforum_YT Microsoft Research Forum is a virtual
2 207 595
38729
22 days 0:36 New tools, models, repos, and papers out of Microsoft Research are here.
Register to know when there are new releases out of MSR: microsoft.com/en-us/research/event/microsoft-research-forum/?OCID=MSR_Researchforum_YT
272
27 days 9:05 Guiding the AI disruption to the Good Place
The true impact of AI does not lie in how well it takes tests or surfs the web, but in how effectively it teaches, coordinates, and operates in a web built for agents rather than humans.
260
27 days 7:40 New fine-tuning of language models: Match meaning, not tokens
Language models are usually trained to predict the next word, but that does not always lead to the best overall answers.
304
27 days 6:29 Introducing Interwhen: Steering reasoning agents with real-time verification
What if AI agents could check their work as they go? This verification method extracts verifiable properties from natural language and evaluates them using symbolic or model-based verifiers.
169
27 days 4:43 Introducing GitHub Agentic Workflows: AI that runs your repo
What if your repo could run itself? GitHub Agentic Workflows bring AI agents directly into repository automation, enabling tasks to run end-to-end inside GitHub Actions.
638
26.3
27 days 13:34 MagenticLite: A full-stack agentic experience powered by Small Models
What if you could run a capable AI agent without leaning on frontier-scale models?
611
13.2