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 3 days ago

Multi-Agent LLMs Fail to Explore Each Other

yingfanbot authored a paper 11 days ago

Bridging the Gap Between Latent and Explicit Reasoning with Looped Transformers

changdae authored a paper 18 days ago

Hide-and-Seek in Trajectories: Discovering Failure Signals for VLA Runtime Monitoring

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

uw-madison 's papers 15

Submitted by

Hyeong Kyu (Froilan) Choi

Multi-Agent LLMs Fail to Explore Each Other

uw-madison

University of Wisconsin - Madison

Submitted by

Changdae Oh

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

uw-madison

University of Wisconsin - Madison

Submitted by

Zhuoming Liu

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

uw-madison

University of Wisconsin - Madison

Submitted by

Anirudh Sundara Rajan

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

uw-madison

University of Wisconsin - Madison

Submitted by

Jaden Park

Exploration and Exploitation Errors Are Measurable for Language Model Agents

uw-madison

University of Wisconsin - Madison

Submitted by

Gabe Orlanski

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

uw-madison

University of Wisconsin - Madison

Submitted by

Tengyang Xie

Understanding Behavior Cloning with Action Quantization

uw-madison

University of Wisconsin - Madison

2

Submitted by

Tengyang Xie

Breaking the Capability Ceiling of LLM Post-Training by Reintroducing Markov States

uw-madison

University of Wisconsin - Madison

2

Submitted by

Jiayu (Mila) Wang

SkillOrchestra: Learning to Route Agents via Skill Transfer

uw-madison

University of Wisconsin - Madison

Submitted by

Jongwon Jeong

TAPE: Tool-Guided Adaptive Planning and Constrained Execution in Language Model Agents

uw-madison

University of Wisconsin - Madison

Submitted by

Changdae Oh

Thinking Makes LLM Agents Introverted: How Mandatory Thinking Can Backfire in User-Engaged Agents

uw-madison

University of Wisconsin - Madison

2

Submitted by

Changdae Oh

Towards Reducible Uncertainty Modeling for Reliable Large Language Model Agents

uw-madison

University of Wisconsin - Madison

3

Submitted by

Mu Cai

Contamination Detection for VLMs using Multi-Modal Semantic Perturbation

uw-madison

University of Wisconsin - Madison

UniTalk: Towards Universal Active Speaker Detection in Real World Scenarios

uw-madison

University of Wisconsin - Madison

VersaPRM: Multi-Domain Process Reward Model via Synthetic Reasoning Data

uw-madison

University of Wisconsin - Madison