Picture for Xu Yang

Xu Yang

DTA: Dual Temporal-channel-wise Attention for Spiking Neural Networks

Add code
Mar 13, 2025
Viaarxiv icon

LMM-R1: Empowering 3B LMMs with Strong Reasoning Abilities Through Two-Stage Rule-Based RL

Add code
Mar 11, 2025
Viaarxiv icon

AppAgentX: Evolving GUI Agents as Proficient Smartphone Users

Add code
Mar 04, 2025
Viaarxiv icon

STHFL: Spatio-Temporal Heterogeneous Federated Learning

Add code
Jan 10, 2025
Viaarxiv icon

VinT-6D: A Large-Scale Object-in-hand Dataset from Vision, Touch and Proprioception

Add code
Jan 06, 2025
Figure 1 for VinT-6D: A Large-Scale Object-in-hand Dataset from Vision, Touch and Proprioception
Figure 2 for VinT-6D: A Large-Scale Object-in-hand Dataset from Vision, Touch and Proprioception
Figure 3 for VinT-6D: A Large-Scale Object-in-hand Dataset from Vision, Touch and Proprioception
Figure 4 for VinT-6D: A Large-Scale Object-in-hand Dataset from Vision, Touch and Proprioception
Viaarxiv icon

Video Repurposing from User Generated Content: A Large-scale Dataset and Benchmark

Add code
Dec 12, 2024
Viaarxiv icon

RL2: Reinforce Large Language Model to Assist Safe Reinforcement Learning for Energy Management of Active Distribution Networks

Add code
Dec 02, 2024
Figure 1 for RL2: Reinforce Large Language Model to Assist Safe Reinforcement Learning for Energy Management of Active Distribution Networks
Figure 2 for RL2: Reinforce Large Language Model to Assist Safe Reinforcement Learning for Energy Management of Active Distribution Networks
Figure 3 for RL2: Reinforce Large Language Model to Assist Safe Reinforcement Learning for Energy Management of Active Distribution Networks
Figure 4 for RL2: Reinforce Large Language Model to Assist Safe Reinforcement Learning for Energy Management of Active Distribution Networks
Viaarxiv icon

DaDu-E: Rethinking the Role of Large Language Model in Robotic Computing Pipeline

Add code
Dec 02, 2024
Figure 1 for DaDu-E: Rethinking the Role of Large Language Model in Robotic Computing Pipeline
Figure 2 for DaDu-E: Rethinking the Role of Large Language Model in Robotic Computing Pipeline
Figure 3 for DaDu-E: Rethinking the Role of Large Language Model in Robotic Computing Pipeline
Figure 4 for DaDu-E: Rethinking the Role of Large Language Model in Robotic Computing Pipeline
Viaarxiv icon

BPQP: A Differentiable Convex Optimization Framework for Efficient End-to-End Learning

Add code
Nov 28, 2024
Viaarxiv icon

Devils in Middle Layers of Large Vision-Language Models: Interpreting, Detecting and Mitigating Object Hallucinations via Attention Lens

Add code
Nov 23, 2024
Figure 1 for Devils in Middle Layers of Large Vision-Language Models: Interpreting, Detecting and Mitigating Object Hallucinations via Attention Lens
Figure 2 for Devils in Middle Layers of Large Vision-Language Models: Interpreting, Detecting and Mitigating Object Hallucinations via Attention Lens
Figure 3 for Devils in Middle Layers of Large Vision-Language Models: Interpreting, Detecting and Mitigating Object Hallucinations via Attention Lens
Figure 4 for Devils in Middle Layers of Large Vision-Language Models: Interpreting, Detecting and Mitigating Object Hallucinations via Attention Lens
Viaarxiv icon