HKUSTGZ

university

AI & ML interests

None defined yet.

Recent Activity

zhxzpn20000506 submitted a paper 4 days ago

Trust Region Policy Distillation

YuMOOOOOOO submitted a paper about 2 months ago

BatteryMFormer: Multi-level Learning for Battery Degradation Trajectory Forecasting

hp-l33 submitted a paper 5 months ago

Mano: Restriking Manifold Optimization for LLM Training

View all activity

Papers

Trust Region Policy Distillation

BatteryMFormer: Multi-level Learning for Battery Degradation Trajectory Forecasting

View all Papers

HKUSTGZ 's papers 15

Submitted by

Zhengpeng Xie

Trust Region Policy Distillation

Submitted by

Ruifeng Tan

BatteryMFormer: Multi-level Learning for Battery Degradation Trajectory Forecasting

Submitted by

Haotian Wang

UniT: Unified Geometry Learning with Group Autoregressive Transformer

Submitted by

Sicheng Feng

PASA: A Principled Embedding-Space Watermarking Approach for LLM-Generated Text under Semantic-Invariant Attacks

Submitted by

Sudong Wang

Beyond SFT-to-RL: Pre-alignment via Black-Box On-Policy Distillation for Multimodal RL

TimeRFT: Stimulating Generalizable Time Series Forecasting for TSFMs via Reinforcement Finetuning

Submitted by

Zikai Zhou

Optimizing Few-Step Generation with Adaptive Matching Distillation

2

Submitted by

Haopeng Li

PISA: Piecewise Sparse Attention Is Wiser for Efficient Diffusion Transformers

Submitted by

Haopeng Li

Mano: Restriking Manifold Optimization for LLM Training

Submitted by

ZhiFei Chen

A Mechanistic View on Video Generation as World Models: State and Dynamics

Submitted by

Guibao SHEN

StereoPilot: Learning Unified and Efficient Stereo Conversion via Generative Priors

Submitted by

Yifan Shen

MedSAM3: Delving into Segment Anything with Medical Concepts

Submitted by

Wenxuan Song

Unified Diffusion VLA: Vision-Language-Action Model via Joint Discrete Denoising Diffusion Process

Submitted by

Zhen Yang

Less is More: Improving LLM Reasoning with Minimal Test-Time Intervention

Submitted by

Wenxuan Song

Spatial Forcing: Implicit Spatial Representation Alignment for Vision-language-action Model