University of Hong Kong

university

Verified

https://www.cds.hku.hk/

Activity Feed Request to join this org

AI & ML interests

The University of Hong Kong School of Computing and Data Science

Recent Activity

Gausson authored a paper 29 days ago

SepLLM: Accelerate Large Language Models by Compressing One Segment into One Separator

Gausson authored a paper 29 days ago

Self-Adjust Softmax

Gausson authored a paper 29 days ago

Answer-Consistent Chain-of-thought Reinforcement Learning For Multi-modal Large Langauge Models

View all activity

Papers

Reinforcing Dual-Path Reasoning in Spatial Vision Language Models

iVGR: Internalizing Visually Grounded Reasoning for MLLMs with Reinforcement Learning

View all Papers

authored 2 papers 7 days ago

Macaron-V1: Towards Open Continual Learning with Self-Improvement and Mixture-of-LoRA

Paper • 2608.09819 • Published 10 days ago • 335

SONIC: Segmented Optimized Nexus for Information Compression in Key-Value Caching

Paper • 2601.21927 • Published Jan 29

authored a paper 22 days ago

Kimi K3: Open Frontier Intelligence

Paper • 2607.24653 • Published 24 days ago • 496

authored a paper 23 days ago

OSWorld2.0: Benchmarking Computer Use Agents on Long-Horizon Real-World Tasks

Paper • 2606.29537 • Published Jun 28 • 24

authored 2 papers about 2 months ago

Training-free CryoET Tomogram Segmentation

Paper • 2407.06833 • Published Jul 8, 2024

PatternGSL: A Structured Specification Language for Template-Free and Simulation-Ready 3D Garments

Paper • 2606.24564 • Published Jun 23

submitted a paper to Daily Papers 2 months ago

Reinforcing Dual-Path Reasoning in Spatial Vision Language Models

Paper • 2606.17539 • Published Jun 16 • 15

authored 2 papers 2 months ago

SQuTR: A Robustness Benchmark for Spoken Query to Text Retrieval under Acoustic Noise

Paper • 2602.12783 • Published Feb 13 • 246

Answer Presence Drives RAG Rewriting Gains

Paper • 2606.05633 • Published Jun 4 • 8

submitted a paper to Daily Papers 2 months ago

Answer Presence Drives RAG Rewriting Gains

Paper • 2606.05633 • Published Jun 4 • 8

authored a paper 2 months ago

On the Scaling of PEFT: Towards Million Personal Models of Trillion Parameters

Paper • 2606.02437 • Published Jun 1 • 243

authored a paper 3 months ago

RectifID: Personalizing Rectified Flow with Anchored Classifier Guidance

Paper • 2405.14677 • Published May 23, 2024 • 11

submitted a paper to Daily Papers 3 months ago

DecMem: Towards Minute-Long Consistent World Generation with Decoupled Memory

Paper • 2605.31336 • Published May 29 • 12

authored a paper 3 months ago

DecMem: Towards Minute-Long Consistent World Generation with Decoupled Memory

Paper • 2605.31336 • Published May 29 • 12

submitted a paper to Daily Papers 3 months ago

iVGR: Internalizing Visually Grounded Reasoning for MLLMs with Reinforcement Learning

Paper • 2605.31096 • Published May 29 • 7

authored 5 papers 3 months ago

MinT: Managed Infrastructure for Training and Serving Millions of LLMs

Paper • 2605.13779 • Published May 13 • 225

SSR: Speculative Parallel Scaling Reasoning in Test-time

Paper • 2505.15340 • Published May 21, 2025

EssayJudge: A Multi-Granular Benchmark for Assessing Automated Essay Scoring Capabilities of Multimodal Large Language Models

Paper • 2502.11916 • Published Feb 17, 2025 • 1

Janus-Q: End-to-End Event-Driven Trading via Hierarchical-Gated Reward Modeling

Paper • 2602.19919 • Published Feb 27

MDN: Parallelizing Stepwise Momentum for Delta Linear Attention

Paper • 2605.05838 • Published May 7 • 5