The University of Hong Kong

university

Verified

https://www.hku.hk

AI & ML interests

None defined yet.

Recent Activity

xiachongfeng authored a paper 4 days ago

GlobeSumm: A Challenging Benchmark Towards Unifying Multi-lingual, Cross-lingual and Multi-document News Summarization

xiachongfeng authored a paper 4 days ago

Causal Tracing of Object Representations in Large Vision Language Models: Mechanistic Interpretability and Hallucination Mitigation

xiachongfeng authored a paper 4 days ago

Fine-Mem: Fine-Grained Feedback Alignment for Long-Horizon Memory Management

View all activity

Papers

ImplicitMemBench: Measuring Unconscious Behavioral Adaptation in Large Language Models

Video Generation Models as World Models: Efficient Paradigms, Architectures and Algorithms

View all Papers

authored 5 papers 4 days ago

GlobeSumm: A Challenging Benchmark Towards Unifying Multi-lingual, Cross-lingual and Multi-document News Summarization

Paper • 2410.04087 • Published Oct 5, 2024

Causal Tracing of Object Representations in Large Vision Language Models: Mechanistic Interpretability and Hallucination Mitigation

Paper • 2511.05923 • Published Nov 8, 2025

Fine-Mem: Fine-Grained Feedback Alignment for Long-Horizon Memory Management

Paper • 2601.08435 • Published Jan 13

Proxy Compression for Language Modeling

Paper • 2602.04289 • Published Feb 4 • 3

ImplicitMemBench: Measuring Unconscious Behavioral Adaptation in Large Language Models

Paper • 2604.08064 • Published 10 days ago • 8

submitted a paper to Daily Papers 8 days ago

ImplicitMemBench: Measuring Unconscious Behavioral Adaptation in Large Language Models

Paper • 2604.08064 • Published 10 days ago • 8

submitted a paper to Daily Papers 18 days ago

Video Generation Models as World Models: Efficient Paradigms, Architectures and Algorithms

Paper • 2603.28489 • Published 19 days ago • 30

submitted a paper to Daily Papers 22 days ago

MACRO: Advancing Multi-Reference Image Generation with Structured Long-Context Data

Paper • 2603.25319 • Published 23 days ago • 32

submitted a paper to Daily Papers 29 days ago

FASTER: Rethinking Real-Time Flow VLAs

Paper • 2603.19199 • Published 30 days ago • 58

submitted a paper to Daily Papers 29 days ago

Cubic Discrete Diffusion: Discrete Visual Generation on High-Dimensional Representation Tokens

Paper • 2603.19232 • Published 30 days ago • 33

authored a paper about 1 month ago

EVATok: Adaptive Length Video Tokenization for Efficient Visual Autoregressive Generation

Paper • 2603.12267 • Published Mar 12 • 13

submitted a paper to Daily Papers about 1 month ago

EVATok: Adaptive Length Video Tokenization for Efficient Visual Autoregressive Generation

Paper • 2603.12267 • Published Mar 12 • 13

submitted a paper to Daily Papers about 2 months ago

Surgical Post-Training: Cutting Errors, Keeping Knowledge

Paper • 2603.01683 • Published Mar 2 • 12

submitted a paper to Daily Papers about 2 months ago

AssetFormer: Modular 3D Assets Generation with Autoregressive Transformer

Paper • 2602.12100 • Published Feb 12 • 2

submitted a paper to Daily Papers 2 months ago

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

Paper • 2602.09021 • Published Feb 9 • 24

submitted a paper to Daily Papers 2 months ago

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

Paper • 2602.05548 • Published Feb 5 • 13

submitted a paper to Daily Papers 4 months ago

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

Paper • 2512.22615 • Published Dec 27, 2025 • 50

submitted a paper to Daily Papers 4 months ago

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

Paper • 2512.20557 • Published Dec 23, 2025 • 51

submitted a paper to Daily Papers 4 months ago

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

Paper • 2512.04519 • Published Dec 4, 2025 • 6

authored a paper 4 months ago

Wan-Move: Motion-controllable Video Generation via Latent Trajectory Guidance

Paper • 2512.08765 • Published Dec 9, 2025 • 134