Tianyi Lab @ UMD

university

https://tianyizhou.github.io/

zhoutianyi

tianyi-lab

Activity Feed Request to join this org

AI & ML interests

Machine Learning, Natural Language Processing, Optimization, Multi-Modality, Artificial Intelligence

Recent Activity

advaitgupta new activity 2 days ago

umd-zhou-lab/CoSTAR:Add paper link and improve description

zhoutianyi authored a paper 3 days ago

CoSTA$\ast$: Cost-Sensitive Toolpath Agent for Multi-turn Image Editing

advaitgupta authored a paper 3 days ago

CoSTA$\ast$: Cost-Sensitive Toolpath Agent for Multi-turn Image Editing

View all activity

umd-zhou-lab's activity

advaitgupta

in umd-zhou-lab/CoSTAR 2 days ago

Add paper link and improve description

#2 opened 2 days ago by

nielsr

zhoutianyi

authored a paper 3 days ago

CoSTA$\ast$: Cost-Sensitive Toolpath Agent for Multi-turn Image Editing

Paper • 2503.10613 • Published 3 days ago • 64

advaitgupta

authored a paper 3 days ago

CoSTA$\ast$: Cost-Sensitive Toolpath Agent for Multi-turn Image Editing

Paper • 2503.10613 • Published 3 days ago • 64

zhoutianyi

authored a paper 7 days ago

R1-Zero's "Aha Moment" in Visual Reasoning on a 2B Non-SFT Model

Paper • 2503.05132 • Published 10 days ago • 49

advaitgupta

updated a dataset 10 days ago

umd-zhou-lab/CoSTAR

Viewer • Updated 2 days ago • 121 • 89 • 2

zhoutianyi

authored a paper 12 days ago

ATLaS: Agent Tuning via Learning Critical Steps

Paper • 2503.02197 • Published 13 days ago • 7

Lichang-Chen

authored a paper 17 days ago

Self-rewarding correction for mathematical reasoning

Paper • 2502.19613 • Published 18 days ago • 77

zhoutianyi

authored a paper 17 days ago

R2-T2: Re-Routing in Test-Time for Multimodal Mixture-of-Experts

Paper • 2502.20395 • Published 17 days ago • 44

mgor

authored a paper 18 days ago

Is your benchmark truly adversarial? AdvScore: Evaluating Human-Grounded Adversarialness

Paper • 2406.16342 • Published Jun 24, 2024

jwkirchenbauer

authored a paper about 1 month ago

Scaling up Test-Time Compute with Latent Reasoning: A Recurrent Depth Approach

Paper • 2502.05171 • Published Feb 7 • 124

Lichang-Chen

authored a paper about 2 months ago

OmnixR: Evaluating Omni-modality Language Models on Reasoning across Modalities

Paper • 2410.12219 • Published Oct 16, 2024 • 1

zhoutianyi

authored 2 papers 3 months ago

GUI Agents: A Survey

Paper • 2412.13501 • Published Dec 18, 2024 • 25

Florence-VL: Enhancing Vision-Language Models with Generative Vision Encoder and Depth-Breadth Fusion

Paper • 2412.04424 • Published Dec 5, 2024 • 61

zhoutianyi

authored a paper 4 months ago

DynaSaur: Large Language Agents Beyond Predefined Actions

Paper • 2411.01747 • Published Nov 4, 2024 • 31

dangmn

authored a paper 4 months ago

DynaSaur: Large Language Agents Beyond Predefined Actions

Paper • 2411.01747 • Published Nov 4, 2024 • 31

zhoutianyi

authored 2 papers 4 months ago

Easy2Hard-Bench: Standardized Difficulty Labels for Profiling LLM Performance and Generalization

Paper • 2409.18433 • Published Sep 27, 2024

What Happened in LLMs Layers when Trained for Fast vs. Slow Thinking: A Gradient Perspective

Paper • 2410.23743 • Published Oct 31, 2024 • 62

zhoutianyi

authored a paper 5 months ago

MuLan: Multimodal-LLM Agent for Progressive and Interactive Multi-Object Diffusion

Paper • 2402.12741 • Published Feb 20, 2024

joliang17

authored 2 papers 5 months ago

CFMatch: Aligning Automated Answer Equivalence Evaluation with Expert Judgments For Open-Domain Question Answering

Paper • 2401.13170 • Published Jan 24, 2024 • 4

PANDA (Pedantic ANswer-correctness Determination and Adjudication):Improving Automatic Evaluation for Question Answering and Text Generation

Paper • 2402.11161 • Published Feb 17, 2024 • 1

AI & ML interests

Recent Activity

Team members 13

umd-zhou-lab's activity

Add paper link and improve description