University of Wisconsin - Madison

university

Verified

https://www.wisc.edu

Activity Feed Request to join this org

AI & ML interests

None defined yet.

Recent Activity

imhgchoi submitted a paper about 1 month ago

Multi-Agent LLMs Fail to Explore Each Other

changdae submitted a paper about 2 months ago

Neglected Free Lunch from Post-training: Progress Advantage for LLM Agents

zhuomingliu submitted a paper 2 months ago

DRIFT: A Residual Flow Adapter for Decoding Continuous Outputs in Vision-Language Models

View all activity

Papers

Multi-Agent LLMs Fail to Explore Each Other

Neglected Free Lunch from Post-training: Progress Advantage for LLM Agents

View all Papers

submitted a paper to Daily Papers about 1 month ago

Multi-Agent LLMs Fail to Explore Each Other

Paper • 2607.11250 • Published Jul 13 • 18

submitted a paper to Daily Papers about 2 months ago

Neglected Free Lunch from Post-training: Progress Advantage for LLM Agents

Paper • 2606.26080 • Published Jun 24 • 12

submitted a paper to Daily Papers 2 months ago

DRIFT: A Residual Flow Adapter for Decoding Continuous Outputs in Vision-Language Models

Paper • 2606.05758 • Published Jun 4 • 5

authored a paper 3 months ago

When Does Multi-Agent RL Improve LLM Workflows? Workflow, Scale, and Policy-Sharing Tradeoffs

Paper • 2605.24202 • Published May 22 • 18

submitted 2 papers to Daily Papers 3 months ago

Capturing LLM Capabilities via Evidence-Calibrated Query Clustering

Paper • 2605.17110 • Published May 16 • 2

DynMuon: A Dynamic Spectral Shaping View of Muon

Paper • 2605.17109 • Published May 16 • 3

authored a paper 3 months ago

Capturing LLM Capabilities via Evidence-Calibrated Query Clustering

Paper • 2605.17110 • Published May 16 • 2

authored a paper 3 months ago

MetaAgent-X : Breaking the Ceiling of Automatic Multi-Agent Systems via End-to-End Reinforcement Learning

Paper • 2605.14212 • Published May 14 • 19

submitted a paper to Daily Papers 3 months ago

MetaAgent-X : Breaking the Ceiling of Automatic Multi-Agent Systems via End-to-End Reinforcement Learning

Paper • 2605.14212 • Published May 14 • 19

authored a paper 3 months ago

EVOCHAMBER: Test-Time Co-evolution of Multi-Agent System at Individual, Team, and Population Scales

Paper • 2605.11136 • Published May 11 • 11

submitted a paper to Daily Papers 3 months ago

From Plans to Pixels: Learning to Plan and Orchestrate for Open-Ended Image Editing

Paper • 2605.15181 • Published May 14 • 12

authored a paper 3 months ago

EVOCHAMBER: Test-Time Co-evolution of Multi-Agent System at Individual, Team, and Population Scales

Paper • 2605.11136 • Published May 11 • 11

submitted a paper to Daily Papers 3 months ago

EVOCHAMBER: Test-Time Co-evolution of Multi-Agent System at Individual, Team, and Population Scales

Paper • 2605.11136 • Published May 11 • 11

submitted a paper to Daily Papers 4 months ago

Exploration and Exploitation Errors Are Measurable for Language Model Agents

Paper • 2604.13151 • Published Apr 14 • 25

submitted a paper to Daily Papers 5 months ago

SlopCodeBench: Benchmarking How Coding Agents Degrade Over Long-Horizon Iterative Tasks

Paper • 2603.24755 • Published Mar 25 • 30

authored 2 papers 5 months ago

Live-Evo: Online Evolution of Agentic Memory from Continuous Feedback

Paper • 2602.02369 • Published Feb 2 • 1

EVA: Efficient Reinforcement Learning for End-to-End Video Agent

Paper • 2603.22918 • Published Mar 24 • 44

submitted a paper to Daily Papers 5 months ago

EVA: Efficient Reinforcement Learning for End-to-End Video Agent

Paper • 2603.22918 • Published Mar 24 • 44

updated a model 5 months ago

uw-madison/mnemodyn

Updated Mar 24 • 2

submitted a paper to Daily Papers 5 months ago

Understanding Behavior Cloning with Action Quantization

Paper • 2603.20538 • Published Mar 20 • 2