University of Wisconsin - Madison

university

Activity Feed Request to join this org

AI & ML interests

None defined yet.

Recent Activity

changdae authored a paper 6 days ago

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

changdae submitted a paper 6 days ago

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

changdae authored a paper 10 days ago

Towards Reducible Uncertainty Modeling for Reliable Large Language Model Agents

View all activity

Papers

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

What Limits Agentic Systems Efficiency?

View all Papers

changdae

authored a paper 6 days ago

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

Paper • 2602.07796 • Published 8 days ago • 7

changdae

submitted a paper to Daily Papers 6 days ago

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

Paper • 2602.07796 • Published 8 days ago • 7

changdae

authored a paper 10 days ago

Towards Reducible Uncertainty Modeling for Reliable Large Language Model Agents

Paper • 2602.05073 • Published 12 days ago • 11

changdae

submitted a paper to Daily Papers 10 days ago

Towards Reducible Uncertainty Modeling for Reliable Large Language Model Agents

Paper • 2602.05073 • Published 12 days ago • 11

plnguyen2908

submitted a paper to Daily Papers 2 months ago

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

Paper • 2512.02231 • Published Dec 1, 2025 • 9

jiakaiW

authored a paper 2 months ago

ViDiC: Video Difference Captioning

Paper • 2512.03405 • Published Dec 3, 2025 • 28

changdae

authored a paper 5 months ago

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

Paper • 2509.23050 • Published Sep 27, 2025 • 15

changdae

authored 5 papers 9 months 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

changdae

authored 2 papers 11 months ago

BlackVIP: Black-Box Visual Prompting for Robust Transfer Learning

Paper • 2303.14773 • Published Mar 26, 2023

Geodesic Multi-Modal Mixup for Robust Fine-Tuning

Paper • 2203.03897 • Published Mar 8, 2022 • 1

BochengZou

authored 2 papers over 1 year ago

TemporalBench: Benchmarking Fine-grained Temporal Understanding for Multimodal Video Models

Paper • 2410.10818 • Published Oct 14, 2024 • 16

VGBench: Evaluating Large Language Models on Vector Graphics Understanding and Generation

Paper • 2407.10972 • Published Jul 15, 2024 • 1

BochengZou

authored 2 papers almost 2 years ago

LLM as Dataset Analyst: Subpopulation Structure Discovery with Large Language Model

Paper • 2405.02363 • Published May 3, 2024

Draw-and-Understand: Leveraging Visual Prompts to Enable MLLMs to Comprehend What You Want

Paper • 2403.20271 • Published Mar 29, 2024 • 3

BochengZou

authored a paper about 2 years ago

Split & Merge: Unlocking the Potential of Visual Adapters via Sparse Training

Paper • 2312.02923 • Published Dec 5, 2023 • 1