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

CultureForest: Understanding and Evaluating Cultural Norm Grounded Reasoning in LLMs

xiachongfeng authored a paper 4 days ago

OMIBench: Benchmarking Olympiad-Level Multi-Image Reasoning in Large Vision-Language Model

xiachongfeng authored a paper 4 days ago

Cross-Lingual Text-Rich Visual Comprehension: An Information Theory Perspective

View all activity

Papers

Nested Sparsity for Scalable Pretraining and Continual Learning

TILDE: Teacher-in-the-Loop Distillation from Embodied Foundation Models

View all Papers

authored 3 papers 4 days ago

CultureForest: Understanding and Evaluating Cultural Norm Grounded Reasoning in LLMs

Paper • 2606.01879 • Published Jun 1

OMIBench: Benchmarking Olympiad-Level Multi-Image Reasoning in Large Vision-Language Model

Paper • 2604.20806 • Published Apr 22 • 2

Cross-Lingual Text-Rich Visual Comprehension: An Information Theory Perspective

Paper • 2412.17787 • Published Dec 23, 2024

submitted a paper to Daily Papers 14 days ago

Nested Sparsity for Scalable Pretraining and Continual Learning

Paper • 2610.31818 • Published 19 days ago • 10

submitted a paper to Daily Papers 18 days ago

TILDE: Teacher-in-the-Loop Distillation from Embodied Foundation Models

Paper • 2610.25376 • Published 23 days ago • 9

submitted a paper to Daily Papers 22 days ago

Execution Before Memory: Diagnosing Memory Failures in Video World Models

Paper • 2610.23542 • Published 25 days ago • 28

authored a paper 26 days ago

DIAL: Position-Debiased LLM Judges with Adaptive Human Preference Calibration

Paper • 2609.31215 • Published Sep 25

submitted a paper to Daily Papers 27 days ago

CineRecon: Benchmarking Frontier Models for Agentic Cinematic Reconstruction

Paper • 2610.16577 • Published 29 days ago • 23

submitted a paper to Daily Papers about 1 month ago

Recursive Game Creator: An Agentic Product-Level Experience-Oriented Game Harness

Paper • 2610.08621 • Published Oct 6 • 70

submitted a paper to Daily Papers about 1 month ago

Understanding On-Policy Distillation: A Mechanistic Interpretability Perspective via Sparse Crosscoders

Paper • 2609.35210 • Published Sep 28 • 4

submitted a paper to Daily Papers about 2 months ago

TempCloze: Can Video-LLMs Identify the Missing Middle?

Paper • 2609.01515 • Published Sep 1 • 10

submitted a paper to Daily Papers 2 months ago

SceneMosaic: Efficient and Diverse Simulation-Ready Scene Generation via Hybrid Agentic Layout Evolution

Paper • 2609.05594 • Published Sep 4 • 19

submitted a paper to Daily Papers 4 months ago

UniClawBench: A Universal Benchmark for Proactive Agents on Real-World Tasks

Paper • 2607.08768 • Published Jul 9 • 35

submitted a paper to Daily Papers 5 months ago

Decoupled Residual Denoising Diffusion Models for Unified and Data Efficient Image-to-Image Translation

Paper • 2606.01048 • Published May 31 • 13

submitted a paper to Daily Papers 6 months ago

DexHoldem: Playing Texas Hold'em with Dexterous Embodied System

Paper • 2605.18727 • Published May 18 • 4

submitted a paper to Daily Papers 6 months ago

From Pixels to Concepts: Do Segmentation Models Understand What They Segment?

Paper • 2605.09591 • Published May 10 • 2

authored a paper 6 months ago

The Granularity Axis: A Micro-to-Macro Latent Direction for Social Roles in Language Models

Paper • 2605.06196 • Published May 7 • 8

authored a paper 7 months ago

SAVOIR: Learning Social Savoir-Faire via Shapley-based Reward Attribution

Paper • 2604.18982 • Published Apr 21 • 4

submitted a paper to Daily Papers 7 months ago

SAVOIR: Learning Social Savoir-Faire via Shapley-based Reward Attribution

Paper • 2604.18982 • Published Apr 21 • 4

authored a paper 7 months ago

Stratagem: Learning Transferable Reasoning via Trajectory-Modulated Game Self-Play

Paper • 2604.17696 • Published Apr 20 • 6