Massachusetts Institute of Technology

university

Verified

https://www.mit.edu/

AI & ML interests

None defined yet.

Recent Activity

sebasmos submitted a paper about 2 hours ago

Loud or Silent? A Reusable Framework for Per-Modality Failure Analysis in Multimodal Clinical AI

ShadenA submitted a paper 21 days ago

A Theory of Contrastive Learning with Natural Images

mjbuehler submitted a paper about 1 month ago

Graph-Native Reinforcement Learning Enables Traceable Scientific Hypothesis Generation through Conceptual Recombination

View all activity

Papers

Loud or Silent? A Reusable Framework for Per-Modality Failure Analysis in Multimodal Clinical AI

A Theory of Contrastive Learning with Natural Images

View all Papers

submitted a paper to Daily Papers about 2 hours ago

Loud or Silent? A Reusable Framework for Per-Modality Failure Analysis in Multimodal Clinical AI

Paper • 2608.01462 • Published 3 days ago • 1

submitted a paper to Daily Papers 21 days ago

A Theory of Contrastive Learning with Natural Images

Paper • 2607.07470 • Published 28 days ago • 16

submitted a paper to Daily Papers about 1 month ago

Graph-Native Reinforcement Learning Enables Traceable Scientific Hypothesis Generation through Conceptual Recombination

Paper • 2607.00924 • Published Jul 1 • 11

submitted a paper to Daily Papers about 2 months ago

Learning User Simulators with Turing Rewards

Paper • 2606.19336 • Published Jun 17 • 3

submitted a paper to Daily Papers about 2 months ago

EvoArena: Tracking Memory Evolution for Robust LLM Agents in Dynamic Environments

Paper • 2606.13681 • Published Jun 11 • 143

submitted a paper to Daily Papers 3 months ago

SENSE: Satellite-based ENergy Synthesis for Sustainable Environment

Paper • 2605.18101 • Published May 18 • 13

submitted a paper to Daily Papers 3 months ago

PEEK: Context Map as an Orientation Cache for Long-Context LLM Agents

Paper • 2605.19932 • Published May 19 • 7

submitted a paper to Daily Papers 3 months ago

RigidFormer: Learning Rigid Dynamics using Transformers

Paper • 2605.09196 • Published May 9 • 14

submitted a paper to Daily Papers 4 months ago

EquiformerV3: Scaling Efficient, Expressive, and General SE(3)-Equivariant Graph Attention Transformers

Paper • 2604.09130 • Published Apr 10 • 4

submitted a paper to Daily Papers 4 months ago

Reaching Beyond the Mode: RL for Distributional Reasoning in Language Models

Paper • 2603.24844 • Published Mar 25 • 10

submitted a paper to Daily Papers 5 months ago

Neural Thickets: Diverse Task Experts Are Dense Around Pretrained Weights

Paper • 2603.12228 • Published Mar 12 • 12

authored a paper 5 months ago

Training Language Models via Neural Cellular Automata

Paper • 2603.10055 • Published Mar 9 • 8

submitted a paper to Daily Papers 5 months ago

AI Gamestore: Scalable, Open-Ended Evaluation of Machine General Intelligence with Human Games

Paper • 2602.17594 • Published Feb 19 • 9

submitted a paper to Daily Papers 6 months ago

How Much Reasoning Do Retrieval-Augmented Models Add beyond LLMs? A Benchmarking Framework for Multi-Hop Inference over Hybrid Knowledge

Paper • 2602.10210 • Published Feb 10 • 1

submitted a paper to Daily Papers 6 months ago

Stemphonic: All-at-once Flexible Multi-stem Music Generation

Paper • 2602.09891 • Published Feb 10 • 2

improbableaimit

submitted a paper to Daily Papers 6 months ago

Self-Distillation Enables Continual Learning

Paper • 2601.19897 • Published Jan 27 • 41

submitted 2 papers to Daily Papers 7 months ago

Collaborative Multi-Agent Test-Time Reinforcement Learning for Reasoning

Paper • 2601.09667 • Published Jan 14 • 92

Rewarding the Rare: Uniqueness-Aware RL for Creative Problem Solving in LLMs

Paper • 2601.08763 • Published Jan 13 • 151

submitted a paper to Daily Papers 8 months ago

FoundationMotion: Auto-Labeling and Reasoning about Spatial Movement in Videos

Paper • 2512.10927 • Published Dec 11, 2025 • 6

authored a paper 9 months ago

Optimize Any Topology: A Foundation Model for Shape- and Resolution-Free Structural Topology Optimization

Paper • 2510.23667 • Published Oct 26, 2025 • 3