🏢 Beijing Institute of Technology
Target-Guided Adversarial Point Cloud Transformer Towards Recognition Against Real-world Corruptions
·3740 words·18 mins·
loading
·
loading
AI Generated
Computer Vision
3D Vision
🏢 Beijing Institute of Technology
APCT: a novel architecture enhances 3D point cloud recognition by using an adversarial feature erasing mechanism to improve global structure capture and robustness against real-world corruptions.
NoiseGPT: Label Noise Detection and Rectification through Probability Curvature
·2389 words·12 mins·
loading
·
loading
Natural Language Processing
Large Language Models
🏢 Beijing Institute of Technology
NoiseGPT uses multi-modal LLMs to detect & fix noisy image labels by identifying probability curvature differences between clean and noisy examples.
LaKD: Length-agnostic Knowledge Distillation for Trajectory Prediction with Any Length Observations
·1999 words·10 mins·
loading
·
loading
AI Applications
Autonomous Vehicles
🏢 Beijing Institute of Technology
LaKD: a novel length-agnostic knowledge distillation framework enables accurate trajectory prediction regardless of observation length, overcoming limitations of existing methods.
CriticEval: Evaluating Large-scale Language Model as Critic
·4755 words·23 mins·
loading
·
loading
Natural Language Processing
Large Language Models
🏢 Beijing Institute of Technology
CRITICEVAL: A new benchmark reliably evaluates LLMs’ ability to identify and correct flaws in their responses, addressing limitations of existing methods by offering comprehensive and reliable evaluat…
Bridge the Points: Graph-based Few-shot Segment Anything Semantically
·3214 words·16 mins·
loading
·
loading
Image Segmentation
🏢 Beijing Institute of Technology
GF-SAM: A novel graph-based few-shot semantic segmentation method leverages SAM’s power efficiently via positive-negative prompt alignment and mask clustering for superior accuracy and speed.