18 31 2

Tianyi Zhou

zhoutianyi

https://tianyizhou.github.io/

AI & ML interests

ML, NLP, RL, Multi-modality

Recent Activity

upvoted a paper 6 days ago

Exploring Expert Failures Improves LLM Agent Tuning

upvoted a paper 11 days ago

GraphicBench: A Planning Benchmark for Graphic Design with Language Agents

authored a paper 19 days ago

WALL-E 2.0: World Alignment by NeuroSymbolic Learning improves World Model-based LLM Agents

View all activity

Organizations

zhoutianyi's activity

upvoted a paper 6 days ago

Exploring Expert Failures Improves LLM Agent Tuning

Paper • 2504.13145 • Published 24 days ago • 12

upvoted a paper 11 days ago

GraphicBench: A Planning Benchmark for Graphic Design with Language Agents

Paper • 2504.11571 • Published 26 days ago • 1

upvoted a paper 19 days ago

WALL-E 2.0: World Alignment by NeuroSymbolic Learning improves World Model-based LLM Agents

Paper • 2504.15785 • Published 20 days ago • 19

upvoted a paper 25 days ago

ColorBench: Can VLMs See and Understand the Colorful World? A Comprehensive Benchmark for Color Perception, Reasoning, and Robustness

Paper • 2504.10514 • Published Apr 10 • 45

upvoted 2 papers 26 days ago

Efficient Reinforcement Finetuning via Adaptive Curriculum Learning

Paper • 2504.05520 • Published Apr 7 • 10

How Instruction and Reasoning Data shape Post-Training: Data Quality through the Lens of Layer-wise Gradients

Paper • 2504.10766 • Published 27 days ago • 40

upvoted a paper 29 days ago

Towards Visual Text Grounding of Multimodal Large Language Model

Paper • 2504.04974 • Published Apr 7 • 16

upvoted 2 papers about 1 month ago

C3PO: Critical-Layer, Core-Expert, Collaborative Pathway Optimization for Test-Time Expert Re-Mixing

Paper • 2504.07964 • Published Apr 10 • 61

Missing Premise exacerbates Overthinking: Are Reasoning Models losing Critical Thinking Skill?

Paper • 2504.06514 • Published Apr 9 • 39

upvoted a paper about 2 months ago

CoSTAast: Cost-Sensitive Toolpath Agent for Multi-turn Image Editing

Paper • 2503.10613 • Published Mar 13 • 79

upvoted 3 papers 2 months ago

upvoted 2 papers 5 months ago

GUI Agents: A Survey

Paper • 2412.13501 • Published Dec 18, 2024 • 29

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

Paper • 2412.04424 • Published Dec 5, 2024 • 63

upvoted 2 papers 6 months ago

DynaSaur: Large Language Agents Beyond Predefined Actions

Paper • 2411.01747 • Published Nov 4, 2024 • 34

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

Paper • 2410.23743 • Published Oct 31, 2024 • 64

upvoted 3 papers 7 months ago

Diffusion Curriculum: Synthetic-to-Real Generative Curriculum Learning via Image-Guided Diffusion

Paper • 2410.13674 • Published Oct 17, 2024 • 17

BenTo: Benchmark Task Reduction with In-Context Transferability

Paper • 2410.13804 • Published Oct 17, 2024 • 20

Your Mixture-of-Experts LLM Is Secretly an Embedding Model For Free

Paper • 2410.10814 • Published Oct 14, 2024 • 52