Picture for Ivor Tsang

Ivor Tsang

Nanyang Technological University

Exploring the Effectiveness and Interpretability of Texts in LLM-based Time Series Models

Add code
Apr 09, 2025
Viaarxiv icon

Balanced Image Stylization with Style Matching Score

Add code
Mar 10, 2025
Viaarxiv icon

Mastering Continual Reinforcement Learning through Fine-Grained Sparse Network Allocation and Dormant Neuron Exploration

Add code
Mar 07, 2025
Viaarxiv icon

Fast Direct: Query-Efficient Online Black-box Guidance for Diffusion-model Target Generation

Add code
Feb 02, 2025
Viaarxiv icon

Active Sampling for Node Attribute Completion on Graphs

Add code
Jan 14, 2025
Figure 1 for Active Sampling for Node Attribute Completion on Graphs
Figure 2 for Active Sampling for Node Attribute Completion on Graphs
Figure 3 for Active Sampling for Node Attribute Completion on Graphs
Figure 4 for Active Sampling for Node Attribute Completion on Graphs
Viaarxiv icon

MAGIC: Mastering Physical Adversarial Generation in Context through Collaborative LLM Agents

Add code
Dec 11, 2024
Figure 1 for MAGIC: Mastering Physical Adversarial Generation in Context through Collaborative LLM Agents
Figure 2 for MAGIC: Mastering Physical Adversarial Generation in Context through Collaborative LLM Agents
Figure 3 for MAGIC: Mastering Physical Adversarial Generation in Context through Collaborative LLM Agents
Figure 4 for MAGIC: Mastering Physical Adversarial Generation in Context through Collaborative LLM Agents
Viaarxiv icon

SceneTAP: Scene-Coherent Typographic Adversarial Planner against Vision-Language Models in Real-World Environments

Add code
Nov 28, 2024
Figure 1 for SceneTAP: Scene-Coherent Typographic Adversarial Planner against Vision-Language Models in Real-World Environments
Figure 2 for SceneTAP: Scene-Coherent Typographic Adversarial Planner against Vision-Language Models in Real-World Environments
Figure 3 for SceneTAP: Scene-Coherent Typographic Adversarial Planner against Vision-Language Models in Real-World Environments
Figure 4 for SceneTAP: Scene-Coherent Typographic Adversarial Planner against Vision-Language Models in Real-World Environments
Viaarxiv icon

ExpertFlow: Optimized Expert Activation and Token Allocation for Efficient Mixture-of-Experts Inference

Add code
Oct 23, 2024
Figure 1 for ExpertFlow: Optimized Expert Activation and Token Allocation for Efficient Mixture-of-Experts Inference
Figure 2 for ExpertFlow: Optimized Expert Activation and Token Allocation for Efficient Mixture-of-Experts Inference
Figure 3 for ExpertFlow: Optimized Expert Activation and Token Allocation for Efficient Mixture-of-Experts Inference
Figure 4 for ExpertFlow: Optimized Expert Activation and Token Allocation for Efficient Mixture-of-Experts Inference
Viaarxiv icon

Sharpness-Aware Black-Box Optimization

Add code
Oct 16, 2024
Viaarxiv icon

Self-Assessed Generation: Trustworthy Label Generation for Optical Flow and Stereo Matching in Real-world

Add code
Oct 14, 2024
Figure 1 for Self-Assessed Generation: Trustworthy Label Generation for Optical Flow and Stereo Matching in Real-world
Figure 2 for Self-Assessed Generation: Trustworthy Label Generation for Optical Flow and Stereo Matching in Real-world
Figure 3 for Self-Assessed Generation: Trustworthy Label Generation for Optical Flow and Stereo Matching in Real-world
Figure 4 for Self-Assessed Generation: Trustworthy Label Generation for Optical Flow and Stereo Matching in Real-world
Viaarxiv icon