The Chinese University of Hong Kong

university

Activity Feed Request to join this org

AI & ML interests

Artificial Intelligence

Recent Activity

IvanLam authored a paper 3 days ago

ImagenWorld: Stress-Testing Image Generation Models with Explainable Human Evaluation on Open-ended Real-World Tasks

BrandonLiu submitted a paper about 1 month ago

Streaming Autoregressive Video Generation via Diagonal Distillation

harryhsing authored a paper about 1 month ago

Omni-Captioner: Data Pipeline, Models, and Benchmark for Omni Detailed Perception

View all activity

Papers

MemDLM: Memory-Enhanced DLM Training

Streaming Autoregressive Video Generation via Diagonal Distillation

View all Papers

authored a paper 4 days ago

Vero: An Open RL Recipe for General Visual Reasoning

Paper • 2604.04917 • Published 5 days ago • 26

submitted a paper to Daily Papers about 1 month ago

Streaming Autoregressive Video Generation via Diagonal Distillation

Paper • 2603.09488 • Published Mar 10 • 5

authored a paper 2 months ago

PatchAlign3D: Local Feature Alignment for Dense 3D Shape understanding

Paper • 2601.02457 • Published Jan 5 • 1

authored a paper 3 months ago

Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models

Paper • 2601.14004 • Published Jan 20 • 47

authored 2 papers 6 months ago

ScreenCoder: Advancing Visual-to-Code Generation for Front-End Automation via Modular Multimodal Agents

Paper • 2507.22827 • Published Jul 30, 2025 • 101

VR-Thinker: Boosting Video Reward Models through Thinking-with-Image Reasoning

Paper • 2510.10518 • Published Oct 12, 2025 • 19

authored 4 papers 6 months ago

Efficient OpAmp Adaptation for Zoom Attention to Golden Contexts

Paper • 2502.12502 • Published Feb 18, 2025

On-Policy Optimization with Group Equivalent Preference for Multi-Programming Language Understanding

Paper • 2505.12723 • Published May 19, 2025

ToTRL: Unlock LLM Tree-of-Thoughts Reasoning Potential through Puzzles Solving

Paper • 2505.12717 • Published May 19, 2025 • 1

One-Token Rollout: Guiding Supervised Fine-Tuning of LLMs with Policy Gradient

Paper • 2509.26313 • Published Sep 30, 2025 • 5

authored a paper 7 months ago

Reinforcement Learning on Pre-Training Data

Paper • 2509.19249 • Published Sep 23, 2025 • 67

authored 2 papers 9 months ago

Mitigating Hallucinations in Large Vision-Language Models via DPO: On-Policy Data Hold the Key

Paper • 2501.09695 • Published Jan 16, 2025 • 1

Do Not Let Low-Probability Tokens Over-Dominate in RL for LLMs

Paper • 2505.12929 • Published May 19, 2025 • 3

authored 4 papers 10 months ago

EndoDAC: Efficient Adapting Foundation Model for Self-Supervised Depth Estimation from Any Endoscopic Camera

Paper • 2405.08672 • Published May 14, 2024

Rectifying Noisy Labels with Sequential Prior: Multi-Scale Temporal Feature Affinity Learning for Robust Video Segmentation

Paper • 2307.05898 • Published Jul 12, 2023 • 1

Learning to Efficiently Adapt Foundation Models for Self-Supervised Endoscopic 3D Scene Reconstruction from Any Cameras

Paper • 2503.15917 • Published Mar 20, 2025

Endo-4DGS: Endoscopic Monocular Scene Reconstruction with 4D Gaussian Splatting

Paper • 2401.16416 • Published Jan 29, 2024

authored 3 papers over 1 year ago

Question Answering as Programming for Solving Time-Sensitive Questions

Paper • 2305.14221 • Published May 23, 2023

AutoConv: Automatically Generating Information-seeking Conversations with Large Language Models

Paper • 2308.06507 • Published Aug 12, 2023 • 1

Unchosen Experts Can Contribute Too: Unleashing MoE Models' Power by Self-Contrast

Paper • 2405.14507 • Published May 23, 2024