Abstract
Education
Experiences (Selected)
Outreach
- [Work] I am open to industrial opportunities (Corporate Research Team, VC, Startups) focus on building and commericializing next generation AIGC technologies. If you are in VC/Startup business or leading a corporate research team, I'd be delighted to have a chat with you.
- [TurningPoint AI Hiring]: TPAI is a long-term multi-lab research collaboration dedicated to exploring key technologies in building reliable multimodal foundational agents. We are a compact and hardcore team comprised of 4 senior advisors and multiple project leads. Checkout our website for research, team construction and hiring!
Publications and Manuscripts
MOSSBench: Is Your Multimodal Language Model Oversensitive to Safe Queries?
Arxiv, 2024
TurningPoint AI
Large Language Models are Interpretable Learners
Arxiv, 2024
Google
The Crystal Ball Hypothesis in diffusion models: Anticipating object positions from initial noise
Arxiv, 2024
TurningPoint AI
Solving for X and Beyond: Can Large Language Models Solve Complex Math Problems with More-Than-Two Unknowns?
EMNLP, 2024
Understanding the Impact of Negative Prompts: When and How Do They Take Effect?
ECCV, 2024
TurningPoint AI
MuLan: Multimodal-LLM Agent for Progressive Multi-Object Diffusion
Arxiv, 2024
TurningPoint AI
DrAttack: Prompt Decomposition and Reconstruction Makes Powerful LLM Jailbreakers
EMNLP, 2024
TurningPoint AI
One Prompt is not Enough: Automated Construction of a Mixture-of-Expert Prompts
ICML, 2024
TurningPoint AI
On Discrete Prompt Optimization for Diffusion Models
ICML, 2024
Google
Ameliorate Spurious Correlations in Dataset Condensation
ICML, 2024
Scaling Up Dataset Distillation to ImageNet-1K with Constant Memory
ICML, 2023
FedDM: Iterative Distribution Matching for Communication-Efficient Federated Learning
CVPR, 2023
DC-BENCH: Dataset Condensation Benchmark
NeurIPS, 2022
Efficient Non-Parametric Optimizer Search for Diverse Tasks
NeurIPS, 2022
Generalizing Few-Shot NAS with Gradient Matching
ICLR, 2022
Learning to Schedule Learning Rate with Graph Neural Networks
ICLR, 2022
RANK-NOSH: Efficient Predictor-Based NAS via Non-Uniform Successive Halving
ICCV, 2021
Rethinking Architecture Selection in Differentiable NAS
ICLR, 2021
Outstanding Paper Award (1/8)
DrNAS: Dirichlet Neural Architecture Search
ICLR, 2021
Awards (Selected)
Teaching
Top