Picture for Kai Lu

Kai Lu

MADLLM: Multivariate Anomaly Detection via Pre-trained LLMs

Add code
Apr 13, 2025
Viaarxiv icon

RUNA: Object-level Out-of-Distribution Detection via Regional Uncertainty Alignment of Multimodal Representations

Add code
Mar 28, 2025
Viaarxiv icon

RefSAM3D: Adapting SAM with Cross-modal Reference for 3D Medical Image Segmentation

Add code
Dec 07, 2024
Viaarxiv icon

Hammer: Towards Efficient Hot-Cold Data Identification via Online Learning

Add code
Nov 22, 2024
Viaarxiv icon

InteLiPlan: Interactive Lightweight LLM-Based Planner for Domestic Robot Autonomy

Add code
Sep 22, 2024
Viaarxiv icon

See, Imagine, Plan: Discovering and Hallucinating Tasks from a Single Image

Add code
Mar 24, 2024
Figure 1 for See, Imagine, Plan: Discovering and Hallucinating Tasks from a Single Image
Figure 2 for See, Imagine, Plan: Discovering and Hallucinating Tasks from a Single Image
Figure 3 for See, Imagine, Plan: Discovering and Hallucinating Tasks from a Single Image
Figure 4 for See, Imagine, Plan: Discovering and Hallucinating Tasks from a Single Image
Viaarxiv icon

Value-Driven Mixed-Precision Quantization for Patch-Based Inference on Microcontrollers

Add code
Jan 24, 2024
Viaarxiv icon

DynPoint: Dynamic Neural Point For View Synthesis

Add code
Oct 31, 2023
Figure 1 for DynPoint: Dynamic Neural Point For View Synthesis
Figure 2 for DynPoint: Dynamic Neural Point For View Synthesis
Figure 3 for DynPoint: Dynamic Neural Point For View Synthesis
Figure 4 for DynPoint: Dynamic Neural Point For View Synthesis
Viaarxiv icon

Shoggoth: Towards Efficient Edge-Cloud Collaborative Real-Time Video Inference via Adaptive Online Learning

Add code
Jun 27, 2023
Figure 1 for Shoggoth: Towards Efficient Edge-Cloud Collaborative Real-Time Video Inference via Adaptive Online Learning
Figure 2 for Shoggoth: Towards Efficient Edge-Cloud Collaborative Real-Time Video Inference via Adaptive Online Learning
Figure 3 for Shoggoth: Towards Efficient Edge-Cloud Collaborative Real-Time Video Inference via Adaptive Online Learning
Figure 4 for Shoggoth: Towards Efficient Edge-Cloud Collaborative Real-Time Video Inference via Adaptive Online Learning
Viaarxiv icon

Multi-body SE(3) Equivariance for Unsupervised Rigid Segmentation and Motion Estimation

Add code
Jun 08, 2023
Viaarxiv icon