University of Wisconsin - Madison

university

Activity Feed Request to join this org

AI & ML interests

None defined yet.

Recent Activity

changdae authored a paper 8 days ago

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

changdae authored a paper 8 days ago

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

changdae submitted a paper 10 days ago

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

View all activity

Papers

When Does Trajectory-Level Supervision Permit Efficient Offline Reinforcement Learning?

Expert-Choice Routing Enables Adaptive Computation in Diffusion Language Models

View all Papers

authored 2 papers 8 days ago

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

Paper • 2605.30834 • Published May 29 • 10

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

Paper • 2606.26080 • Published 13 days ago • 10

submitted a paper to Daily Papers 10 days ago

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

Paper • 2606.26080 • Published 13 days ago • 10

submitted a paper to Daily Papers 18 days ago

When Does Trajectory-Level Supervision Permit Efficient Offline Reinforcement Learning?

Paper • 2606.18531 • Published 21 days ago • 4

authored a paper about 1 month ago

Agent Skills Should Go Beyond Text: The Case for Visual Skills

Paper • 2606.01414 • Published May 31 • 10

authored a paper about 2 months ago

MementoGUI: Learning Agentic Multimodal Memory Control for Long-Horizon GUI Agents

Paper • 2605.18652 • Published May 18 • 8

submitted a paper to Daily Papers 3 months ago

Expert-Choice Routing Enables Adaptive Computation in Diffusion Language Models

Paper • 2604.01622 • Published Apr 2 • 7

authored a paper 3 months ago

MuRF: Unlocking the Multi-Scale Potential of Vision Foundation Models

Paper • 2603.25744 • Published Mar 26 • 13

submitted a paper to Daily Papers 3 months ago

MuRF: Unlocking the Multi-Scale Potential of Vision Foundation Models

Paper • 2603.25744 • Published Mar 26 • 13

authored a paper 5 months ago

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

Paper • 2602.07796 • Published Feb 8 • 7

submitted a paper to Daily Papers 5 months ago

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

Paper • 2602.07796 • Published Feb 8 • 7

authored a paper 5 months ago

Towards Reducible Uncertainty Modeling for Reliable Large Language Model Agents

Paper • 2602.05073 • Published Feb 4 • 11

submitted a paper to Daily Papers 5 months ago

Towards Reducible Uncertainty Modeling for Reliable Large Language Model Agents

Paper • 2602.05073 • Published Feb 4 • 11

submitted a paper to Daily Papers 7 months ago

See, Hear, and Understand: Benchmarking Audiovisual Human Speech Understanding in Multimodal Large Language Models

Paper • 2512.02231 • Published Dec 1, 2025 • 9

authored a paper 9 months ago

Understanding Language Prior of LVLMs by Contrasting Chain-of-Embedding

Paper • 2509.23050 • Published Sep 27, 2025 • 15

authored 5 papers about 1 year ago

DaWin: Training-free Dynamic Weight Interpolation for Robust Adaptation

Paper • 2410.03782 • Published Oct 3, 2024 • 1

Towards Calibrated Robust Fine-Tuning of Vision-Language Models

Paper • 2311.01723 • Published Nov 3, 2023

Learning Fair Representation via Distributional Contrastive Disentanglement

Paper • 2206.08743 • Published Jun 17, 2022

Visual Instruction Bottleneck Tuning

Paper • 2505.13946 • Published May 20, 2025 • 10

Understanding Multimodal LLMs Under Distribution Shifts: An Information-Theoretic Approach

Paper • 2502.00577 • Published Feb 1, 2025