Tianyi Zhou

Visiting Assistant Professor@Mohamed bin Zayed University of Artificial Intelligence·阿联酋·OpenReview

研究方向

LLMs · multi-modal agent · personalization and controllability of generative AI · multi-modality models · vision-language models · multi-objective optimization · continual learning · interpretable AI · self-supervised learning · reinforcement learning · federated learning · meta-learning · curriculum learning · mixture-of-experts · NLP · attention mechanism · submodular optimization · combinatorial optimization · spectral method · dimension reduction · matrix factorization · sparse learning · compressed sensing · multi-label learning · multi-task learning

Tianyi Zhou

Vision-Zero: Scalable VLM Self-Evolution via Multi-Agent Self-Play

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

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

CoSTA*: Cost-Sensitive Toolpath Agent for Multi-turn Image Editing

ECA: Efficient Continual Alignment for Open-Ended Image-to-Text Generation

TrustGen: A Platform of Dynamic Benchmarking on the Trustworthiness of Generative Foundation Models

Mutual Information Dynamics Learning: A New Paradigm for Unsupervised Reinforcement Learning

Routing Manifold Alignment Improves Generalization of Mixture-of-Experts LLMs

Exploring Expert Failures Improves LLM Agent Tuning

VisR-Bench: An Empirical Study on Visual Retrieval-Augmented Generation for Multilingual Long Document Understanding

Beyond Parameters: Exploring Virtual Logic Depth for Scaling Laws

Towards Visual Text Grounding of Multimodal Large Language Model

TS-Reasoner: Aligning Time Series Foundation Models with LLM Reasoning

Efficient Reinforcement Finetuning via Adaptive Curriculum Learning

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

AutoDavis: Automatic and Dynamic Evaluation Protocol of Large Vision-Language Models on Visual Question-Answering

CaughtCheating: Is Your MLLM a Good Cheating Detective? Exploring the Boundary of Visual Perception and Reasoning

VisualThinker: First ever R1-Zero's Aha Moment on just a 2B non-SFT Model

PolySona: Parameter-Efficient and Modular Latent Behavior Modeling for Traffic Simulation

Where do Reasoning Models Make a Difference? Follow the Reasoning Leader for Efficient Decoding

Modality-Balancing Preference Optimization of Large Multimodal Models by Adversarial Negative Mining

ChartAlignBench: A Benchmark for Chart Grounding & Dense Alignment

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

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

VideoHallu: Evaluating and Mitigating Multi-modal Hallucinations on Synthetic Video Understanding

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

DynaSaur: Large Language Agents Beyond Predefined Actions

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