Biography

My research interests are in machine learning, natural language processing, optimization, and multimodal agentic AI. I earned my Ph.D. (thesis) from Computer Science of University of Washington. We built Program-of-Layers, ThinkARM, HallusionBench, WALL-E, MoE-Embedding, Blip3-o, SuperFiltering, InstructZero, FedProto, Robust Curriculum, Curriculum HER, DiSAN, Divide-and-Conquer Anchoring, GoDec, etc. Our works have been published in ML (NeurIPS, ICML, ICLR), NLP (ACL, EMNLP, NAACL, COLM), CV (CVPR, ICCV, ECCV), DM (KDD, ICDM), AI (AAAI, IJCAI) conferences, and journals as Machine Learning (Springer), IEEE TPAMI/TIP/TNNLS/TKDE, etc. Our recent works mainly focus on:

• Human-AI-World Alignment: Cognitive/Epistemic Alignment, Human Modeling, Human-AI Teaming, Multi-Objective Alignment; Neuro-Symbolic and Physics/Geometry-Grounded World Models, Interactive Agents;
• Self-evolving AI and Sustainable Learning: Data/Task/Env Selection, Synthesis, and Curriculum; Continual Learning; Auto-benchmarking; Auditing; Self-Reward/Labeling;
• Generalist AI built by Experts: Dynamic Models, Mixture-of-Experts, Federated/Collaborative Learning, Multi-Agent Orchestration;
• Interpretability of ML: Memorization, Generalization, Grokking, Collapse, Representation, Hallucination, Steering;

Our studies are built upon recent LLMs, unified multi-modal models, RL, agentic systems, to address practical challenges in education, science, design, visualization, embodied intelligence, etc. Our goal is to develop efficient, versatile, trustworthy, and environmentally-friendly hybrid-intelligence based on coevolution between humans and machines. Our code/data/models can be found at Tianyi Lab’s GitHub and HF.

News

• 2026/07: 4 papers have been accepted by COLM.
• 2026/07: Schoenfeld’s Anatomy of Mathematical Reasoning by Language Models has been selected as “SAC Highlight” on ACL 2026.
• 2026/06: Item Difficulty Modeling Using Fine-tuned Small and Large Language Models won 2026 Best Research Award from the International EAssessment Association (eAA).
• 2026/05: 6 ICML (1 Oral + 1 Spotlight) + 5 ACL (1 Oral) + 5 ICLR + 1 ACM CAIS + 1 EACL + 1 AAAI have been accepted in 2026.
• 2026/03: I will serve as the Area Chair for NeurIPS 2026 and most ARR circles (ACL, EMNLP, etc.).
• 2026/01: I am visiting MBZUAI, UAE as a Visiting Assistant Professor for one year and has experienced the 2026 Middle East Conflict.
• 2026/01: Congratulations to Ming Li on being awarded 2026 Apple Scholar in AI/ML!
• 2025/11: I am going to serve as an Area Chair of ICML 2026.
• 2025/09: 4 works (ColorBench: VLMs struggle on colors, WALL-E: neurosymbolic world model, VideoHallu: VLMs hallucinate on synthetic videos, DTO: dynamic thinking pattern optimization) have been accepted by NeurIPS 2025.
• 2025/09: Congratulations to Dongping Chen on being awarded UMD Flagship Fellowship (the only CS recipient this year)!
• 2025/08: 3 works (Demos’ Position in Prompt bias, Schoenfeld’s Episode Theory for LLM reasoning, NoWait reasoning on LLMs/VLMs) have been accepted by EMNLP 2025.
• 2025/08: I am going to serve as an Area Chair of ICLR 2026 and AAAI 2026.
• 2025/07: 3 works (C3PO, MiP-Overthinking, DynaSaur) have been accepted by COLM 2025.
• 2025/05: We release BLIP3-o, a fully-open sourced framework to unify image reasoning + generation in one model. It aligns the two foundamental tasks via CLIP-level features. You can find report and demo.
• 2025/05: 6 works (3 main with 2 Oral + 3 findings) have been accepted by ACL 2025.
• 2025/05: 3 works have been accepted by ICML: R2-T2 (Test-Time Multimodal MoE), Preference Controllable Multi-Objective RL, and Tilted Sharpness-Aware Minimization.
• 2025/04: We release WALL-E 2.0 (code) to improve the world model for LLM-based embodied agents. TL;DR: WALL-E 2.0 = Neuro-Symbolic World Model + MPC-based LLM Agent, where Neuro-Symbolic World Model = LLM + Complementary Symbolic knowledge (action rules, scene graph, knowledge graph) extracted from LLM errors in experiences.
• 2025/04: We release ColorBench, the first comprehensive benchmark exposing the weaknesses of existing VLMs on color perception, reasoning, and robustness, across >5,800 images from 11 tasks based on real applications including shopping, medical test-kit reading, map-reading, agriculture, art, wildlife research, etc.
• 2025/04: We release C3PO and R2-T2, which develop a novel class of test-time optimization approaches that can significantly boost the performance of existing MoE VLMs and MoE LLMs by 7-15% on challenging tasks.
• 2025/04: We release two works investigating how traning data for LLMs (slow vs. fast thinking, instruction vs. reasoning) lead to different layer-wise gradient patterns and training dynamics, from which we unified vairous existing data quality metrics into one: small but diverse gradient directions indicate better data.
• 2025/04: We release ATLaS and EEF that study better usage of expert trajectories in supervised/reinforcement finetuning of LLM agents. ATLaS selects only 30% critical steps from expert trajectories to achieve better generalization across tasks/envs, while EEF show that expert failed trajectories can considerably improve the agent exploration in RL.
• 2025/04: I am going to serve as an Area Chair of NeurIPS 2025.
• 2025/03: Florence-VL (3B/8B pretrained/SFT VLMs) trained with depth-breadth fusion has been accepted by CVPR 2025 and the complete training recipe has been open-sourced.
• 2025/02: Check the very first “Aha moment” of multimodal reasoning by RL acheived by VisualThinker-R1-Zero from our TurningPoint-AI team!
• 2025/01: 7 ICLR + 3 NAACL accepted, featuring our latest works on synthetic data for post-training, MoE (ICLR Oral), many-objective optimization, in-context transferality, multi-modality imbalance & alignment, oversensitiveness & controllability of GenAI.

Research Topics

• Machine Learning (2008-present)
  1. Learning over time: Curriculum Learning, Continual Learning (DisCL, DIH, DoCL, MECE, Time-Consistency, RAR, FPF, CoTASP)
  2. Learning via interactions: Reinforcement Learning, Online Learning (CHER, Unsupervised RL, CO-PILOT, P3)
  3. Learning across tasks/domains: Multi-task Learning, Meta-Learning, Domain Adaptation/Generalization (GPN, PPN, MTC)
  4. Learning multiple models: Mixture-of-Experts (MoE), Collaborative/Cooperative Learning, Federated/Decentralized Learning (MoEE, DivE2, L2C, SCooL, DivFL, FedProto, FedRAP, CAM, MosT)
  5. Learning under noises: Noisy-Label Learning, Adversarial Learning (RoCL, CD-VAE)
  6. Learning representations: Self-Supervised Learning, Dimension Reduction (MEN, LPA3, IDAA)
  7. Sparse Learning: Compressed Sensing, Matrix Factorization, Spectral Method (GoDec, DCA, k-bit HCS)
  8. Optimization: Continuous, Combinatorial, Multi-Objective, Zeroth-order (MosT, Minimax CL, Submodular Partition, TSAM)
• Natural Language Processing (2016-present)
  1. Attention mechanisms: DiSAN, BiBloSA
  2. Data Engineering (selection, exploration, synthesis) for Large language models (LLMs) training: Reflection-Tuning, SuperFiltering, Alpagasus, Cherry LLM, Mosaic-IT, RuleR
  3. LLM Agents, NeuroSymbolic World Models: WALL-E, DynaSaur, ATLaS, EEF
  4. Personalization and Human-AI Alignment: DEBATunE, MCTune, CAIMIRA
  5. Prompting: InstructZero, MoP
  6. In-Context Learning: BenTo, Div-S3
  7. Test-Time Optimization: C3PO, R2-T2
  8. Embedding: MoEE, MetaEOL
  9. Efficient Inference: SpecHub, BumbleBee
  10. Adversarial attack and defense（Jailbreak, Unlearning, etc.): DrAttack
  11. Reasoning: MiP-Overthinking, AdaRFT
• Multi-modal Models (2021-present)
  1. Unified Multi-modal Models with Dense Alignment: Florence-VL, BLIP3-o
  2. Reasoning Multi-modal Models: VisualThinker-R1-Zero
  3. Multi-modal Embodied Agent and RL: EMMA, CoTASP
  4. Multi-modal Generative Agents: MuLan, CoSTA*, FaSTA*
  5. Benchmarks: HallusionBench, AutoHallusion, MOSSBench, ColorBench