Picture for Ming Tang

Ming Tang

Foundation Model Research Center, Institute of Automation, Chinese Academy of Sciences

Pushing DSP-Free Coherent Interconnect to the Last Inch by Optically Analog Signal Processing

Add code
Mar 14, 2025
Viaarxiv icon

PhysVLM: Enabling Visual Language Models to Understand Robotic Physical Reachability

Add code
Mar 13, 2025
Viaarxiv icon

MIGA: Mutual Information-Guided Attack on Denoising Models for Semantic Manipulation

Add code
Mar 11, 2025
Viaarxiv icon

LightPlanner: Unleashing the Reasoning Capabilities of Lightweight Large Language Models in Task Planning

Add code
Mar 11, 2025
Viaarxiv icon

FLARE: A Framework for Stellar Flare Forecasting using Stellar Physical Properties and Historical Records

Add code
Feb 25, 2025
Viaarxiv icon

Zero Token-Driven Deep Thinking in LLMs: Unlocking the Full Potential of Existing Parameters via Cyclic Refinement

Add code
Feb 17, 2025
Viaarxiv icon

Systematic Outliers in Large Language Models

Add code
Feb 10, 2025
Viaarxiv icon

Label Anything: An Interpretable, High-Fidelity and Prompt-Free Annotator

Add code
Feb 05, 2025
Figure 1 for Label Anything: An Interpretable, High-Fidelity and Prompt-Free Annotator
Figure 2 for Label Anything: An Interpretable, High-Fidelity and Prompt-Free Annotator
Figure 3 for Label Anything: An Interpretable, High-Fidelity and Prompt-Free Annotator
Figure 4 for Label Anything: An Interpretable, High-Fidelity and Prompt-Free Annotator
Viaarxiv icon

FiLo++: Zero-/Few-Shot Anomaly Detection by Fused Fine-Grained Descriptions and Deformable Localization

Add code
Jan 17, 2025
Viaarxiv icon

Enhancing Large Vision Model in Street Scene Semantic Understanding through Leveraging Posterior Optimization Trajectory

Add code
Jan 03, 2025
Viaarxiv icon