Sun Yat-sen University

Activity Feed Request to join this org

AI & ML interests

None defined yet.

Papers

X2SAM: Any Segmentation in Images and Videos

Clients Collaborate: Flexible Differentially Private Federated Learning with Guaranteed Improvement of Utility-Privacy Trade-off

View all Papers

authored a paper 9 days ago

Towards Agentic Robots: Model, Data, Environment, and Harness

Paper • 2610.20442 • Published 10 days ago • 43

authored 5 papers 24 days ago

Covering Human Action Space for Computer Use: Data Synthesis and Benchmark

Paper • 2605.12501 • Published May 12 • 17

UniG2U-Bench: Do Unified Models Advance Multimodal Understanding?

Paper • 2603.03241 • Published Mar 3 • 69

RESOURCE2SKILL: Distilling Executable Agent Skills from Human-Created Multimodal Resources

Paper • 2606.29538 • Published Jul 16 • 99

Argus: A General-Purpose Agentic Reasoning Runtime for Long-Horizon Tasks

Paper • 2608.05144 • Published Aug 7

Learning Native Reflection in Unified Models with Interleaved Reinforcement Learning

Paper • 2609.35767 • Published 26 days ago • 50

authored a paper 5 months ago

GAGPO: Generalized Advantage Grouped Policy Optimization

Paper • 2605.13217 • Published May 13 • 3

authored a paper 6 months ago

Image Quality Assessment for Machines: Paradigm, Large-scale Database, and Models

Paper • 2508.19850 • Published Aug 27, 2025

authored a paper 10 months ago

Context-Picker: Dynamic context selection using multi-stage reinforcement learning

Paper • 2512.14465 • Published Dec 16, 2025 • 1

authored a paper 11 months ago

IRG-MotionLLM: Interleaving Motion Generation, Assessment and Refinement for Text-to-Motion Generation

Paper • 2512.10730 • Published Dec 11, 2025 • 3

authored a paper about 1 year ago

LOVE-R1: Advancing Long Video Understanding with an Adaptive Zoom-in Mechanism via Multi-Step Reasoning

Paper • 2509.24786 • Published Sep 29, 2025 • 7

authored 3 papers about 1 year ago

Temporal Memory Attention for Video Semantic Segmentation

Paper • 2102.08643 • Published Feb 17, 2021

OV-DINO: Unified Open-Vocabulary Detection with Language-Aware Selective Fusion

Paper • 2407.07844 • Published Jul 10, 2024 • 1

X-SAM: From Segment Anything to Any Segmentation

Paper • 2508.04655 • Published Aug 6, 2025 • 1

authored a paper over 1 year ago

ViSpeak: Visual Instruction Feedback in Streaming Videos

Paper • 2503.12769 • Published Mar 17, 2025 • 8

authored a paper about 2 years ago

EgoExo-Fitness: Towards Egocentric and Exocentric Full-Body Action Understanding

Paper • 2406.08877 • Published Jun 13, 2024