Carnegie Mellon University School of Computer Science

university

Activity Feed Request to join this org

AI & ML interests

None defined yet.

Recent Activity

sungj1026 submitted a paper 15 days ago

πR^2: Reactive Real-time Flow Policies

haizhongzheng submitted a paper 3 months ago

AstraFlow: Dataflow-Oriented Reinforcement Learning for Agentic LLMs

ethanning authored a paper 3 months ago

Auto Research with Specialist Agents Develops Effective and Non-Trivial Training Recipes

View all activity

Papers

$π\mathbf{R}^2$: Reactive Real-time Flow Policies

Modeling Distinct Human Interaction in Web Agents

View all Papers

authored a paper 6 days ago

PithTrain: A Compact and Agent-Native MoE Training System

Paper • 2605.31463 • Published May 29 • 1

submitted a paper to Daily Papers 15 days ago

πR^2: Reactive Real-time Flow Policies

Paper • 2607.26055 • Published 18 days ago • 5

authored 2 papers 16 days ago

DemoDiffusion: One-Shot Human Imitation using pre-trained Diffusion Policy

Paper • 2506.20668 • Published Jun 25, 2025 • 1

DROID: A Large-Scale In-The-Wild Robot Manipulation Dataset

Paper • 2403.12945 • Published Mar 19, 2024 • 1

authored a paper 3 months ago

Efficient Agentic Reasoning Through Self-Regulated Simulative Planning

Paper • 2605.22138 • Published May 21 • 11

submitted a paper to Daily Papers 3 months ago

AstraFlow: Dataflow-Oriented Reinforcement Learning for Agentic LLMs

Paper • 2605.15565 • Published May 15 • 17

authored a paper 3 months ago

Auto Research with Specialist Agents Develops Effective and Non-Trivial Training Recipes

Paper • 2605.05724 • Published May 7 • 16

submitted a paper to Daily Papers 3 months ago

Auto Research with Specialist Agents Develops Effective and Non-Trivial Training Recipes

Paper • 2605.05724 • Published May 7 • 16

authored a paper 3 months ago

DR Tulu: Reinforcement Learning with Evolving Rubrics for Deep Research

Paper • 2511.19399 • Published Nov 24, 2025 • 64

authored 2 papers 4 months ago

SkillLearnBench: Benchmarking Continual Learning Methods for Agent Skill Generation on Real-World Tasks

Paper • 2604.20087 • Published Apr 22 • 15

Revision or Re-Solving? Decomposing Second-Pass Gains in Multi-LLM Pipelines

Paper • 2604.01029 • Published Apr 1 • 8

submitted a paper to Daily Papers 5 months ago

Revision or Re-Solving? Decomposing Second-Pass Gains in Multi-LLM Pipelines

Paper • 2604.01029 • Published Apr 1 • 8

submitted a paper to Daily Papers 5 months ago

SurvHTE-Bench: A Benchmark for Heterogeneous Treatment Effect Estimation in Survival Analysis

Paper • 2603.05483 • Published Mar 5 • 2

authored 5 papers 5 months ago

Forecasting Clinical Risk from Textual Time Series: Structuring Narratives for Temporal AI in Healthcare

Paper • 2504.10340 • Published Apr 14, 2025

The Impact of Medication Non-adherence on Adverse Outcomes: Evidence from Schizophrenia Patients via Survival Analysis

Paper • 2506.18187 • Published Jun 22, 2025

Temporal Supervised Contrastive Learning for Modeling Patient Risk Progression

Paper • 2312.05933 • Published Dec 10, 2023

SurvHTE-Bench: A Benchmark for Heterogeneous Treatment Effect Estimation in Survival Analysis

Paper • 2603.05483 • Published Mar 5 • 2

Deep sequence models tend to memorize geometrically; it is unclear why

Paper • 2510.26745 • Published Oct 30, 2025

submitted a paper to Daily Papers 6 months ago

Modeling Distinct Human Interaction in Web Agents

Paper • 2602.17588 • Published Feb 19 • 4

authored a paper 7 months ago

Agentic Search in the Wild: Intents and Trajectory Dynamics from 14M+ Real Search Requests

Paper • 2601.17617 • Published Jan 24 • 4