Wei Huang

Consistency Is Not Always Correct: Towards Understanding the Role of Exploration in Post-Training Reasoning

Mamba Can Learn Low-Dimensional Targets In-Context via Test-Time Feature Learning

SELF-HARMONY: LEARNING TO HARMONIZE SELF-SUPERVISION AND SELF-PLAY IN TEST-TIME REINFORCEMENT LEARNING

Accelerating Discrete Diffusion Models with Parallel Sampling

Multimodal Information is All You Need for Adversarial Purification via Diffusion Models

Node-wise Filtering in Graph Neural Networks: A Mixture of Experts Approach

Provable Benefit of Curriculum in Transformer Tree-Reasoning Post-Training

On the Optimization and Generalization of Two-layer Transformers with Sign Gradient Descent

Trained Mamba Emulates Online Gradient Descent in In-Context Linear Regression

Generalization Bound of Gradient Flow through Training Trajectory and Data-dependent Kernel

Scaling Diffusion Transformers Efficiently via $\mu$P

How Does Label Noise Gradient Descent Improve Generalization in the Low SNR Regime?

Test-Time Graph Neural Dataset Search With Generative Projection

Can Diffusion Models Learn Hidden Inter-Feature Rules Behind Images?

Understanding the Forgetting of (Replay-based) Continual Learning via Feature Learning: Angle Matters

On the Role of Label Noise in the Feature Learning Process

Provable In-Context Vector Arithmetic via Retrieving Task Concepts

Multinoulli Extension: A Lossless Yet Effective Probabilistic Framework for Subset Selection over Partition Constraints

GRU: Mitigating the Trade-off between Unlearning and Retention for LLMs

On the Feature Learning in Diffusion Models

Label Noise Gradient Descent Improves Generalization in the Low SNR Regime

The Role of Label Noise in the Feature Learning Process

Node-wise Filtering in Graph Neural Networks: A Mixture of Experts Approach