The University of Hong Kong

university

Verified

https://www.hku.hk

AI & ML interests

None defined yet.

Recent Activity

YuuTennYi submitted a paper about 4 hours ago

EVATok: Adaptive Length Video Tokenization for Efficient Visual Autoregressive Generation

linius submitted a paper 9 days ago

Surgical Post-Training: Cutting Errors, Keeping Knowledge

ltzhu submitted a paper 17 days ago

AssetFormer: Modular 3D Assets Generation with Autoregressive Transformer

View all activity

Papers

EVATok: Adaptive Length Video Tokenization for Efficient Visual Autoregressive Generation

Surgical Post-Training: Cutting Errors, Keeping Knowledge

View all Papers

hkuhk 's Papers 14

Submitted by

Tianwei Xiong

EVATok: Adaptive Length Video Tokenization for Efficient Visual Autoregressive Generation

hkuhk

The University of Hong Kong

Submitted by

Linius Lin

Surgical Post-Training: Cutting Errors, Keeping Knowledge

hkuhk

The University of Hong Kong

Submitted by

taesiri

The Art of Efficient Reasoning: Data, Reward, and Optimization

hkuhk

The University of Hong Kong

Submitted by

Lingting Zhu

AssetFormer: Modular 3D Assets Generation with Autoregressive Transformer

hkuhk

The University of Hong Kong

Submitted by

Sima

χ_{0}: Resource-Aware Robust Manipulation via Taming Distributional Inconsistencies

hkuhk

The University of Hong Kong

Submitted by

Liangqiong Qu

Unveiling Implicit Advantage Symmetry: Why GRPO Struggles with Exploration and Difficulty Adaptation

hkuhk

The University of Hong Kong

Submitted by

Shansan Gong

Dream-VL & Dream-VLA: Open Vision-Language and Vision-Language-Action Models with Diffusion Language Model Backbone

hkuhk

The University of Hong Kong

Submitted by

Wei Huang

Learning to Reason in 4D: Dynamic Spatial Understanding for Vision Language Models

hkuhk

The University of Hong Kong

Submitted by

Yifei Yu

VideoSSM: Autoregressive Long Video Generation with Hybrid State-Space Memory

hkuhk

The University of Hong Kong

2

Submitted by

Yukun Huang

OmniX: From Unified Panoramic Generation and Perception to Graphics-Ready 3D Scenes

hkuhk

The University of Hong Kong

Submitted by

Weiyang Jin

SRUM: Fine-Grained Self-Rewarding for Unified Multimodal Models

hkuhk

The University of Hong Kong

Submitted by

Rongyao Fang

CodePlot-CoT: Mathematical Visual Reasoning by Thinking with Code-Driven Images

hkuhk

The University of Hong Kong

Submitted by

Taki WU

Revisiting Model Interpolation for Efficient Reasoning

hkuhk

The University of Hong Kong

Submitted by

CAO

Compose Your Policies! Improving Diffusion-based or Flow-based Robot Policies via Test-time Distribution-level Composition

hkuhk

The University of Hong Kong