Tianyi Zhou

zhoutianyi's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

authored 4 papers 1 day ago

Don't Think Longer, Think Wisely: Optimizing Thinking Dynamics for Large Reasoning Models

Paper • 2505.21765 • Published May 27

Pisces: An Auto-regressive Foundation Model for Image Understanding and Generation

Paper • 2506.10395 • Published 17 days ago

Where to find Grokking in LLM Pretraining? Monitor Memorization-to-Generalization without Test

Paper • 2506.21551 • Published 2 days ago • 25

FaSTA$^*$: Fast-Slow Toolpath Agent with Subroutine Mining for Efficient Multi-turn Image Editing

Paper • 2506.20911 • Published 3 days ago • 37

authored 2 papers 11 days ago

Optimizing Length Compression in Large Reasoning Models

Paper • 2506.14755 • Published 11 days ago • 10

Wait, We Don't Need to "Wait"! Removing Thinking Tokens Improves Reasoning Efficiency

Paper • 2506.08343 • Published 19 days ago • 46

authored a paper 18 days ago

What makes Reasoning Models Different? Follow the Reasoning Leader for Efficient Decoding

Paper • 2506.06998 • Published 21 days ago

authored 3 papers about 1 month ago

Skill Discovery for Software Scripting Automation via Offline Simulations with LLMs

Paper • 2504.20406 • Published Apr 29 • 7

VideoHallu: Evaluating and Mitigating Multi-modal Hallucinations for Synthetic Videos

Paper • 2505.01481 • Published May 2 • 3

BLIP3-o: A Family of Fully Open Unified Multimodal Models-Architecture, Training and Dataset

Paper • 2505.09568 • Published May 14 • 94

authored 8 papers 2 months ago

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

Paper • 2504.15785 • Published Apr 22 • 19

GraphicBench: A Planning Benchmark for Graphic Design with Language Agents

Paper • 2504.11571 • Published Apr 15 • 1

Exploring Expert Failures Improves LLM Agent Tuning

Paper • 2504.13145 • Published Apr 17 • 12

On the Trustworthiness of Generative Foundation Models: Guideline, Assessment, and Perspective

Paper • 2502.14296 • Published Feb 20 • 46

AutoBench-V: Can Large Vision-Language Models Benchmark Themselves?

Paper • 2410.21259 • Published Oct 28, 2024 • 1

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

Paper • 2504.10514 • Published Apr 10 • 47

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 Apr 14 • 40

authored 2 papers 3 months ago

Towards Visual Text Grounding of Multimodal Large Language Model

Paper • 2504.04974 • Published Apr 7 • 16

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

Paper • 2504.07964 • Published Apr 10 • 61