5 papers · 1 filter
VLM-AD: End-to-End Autonomous Driving through Vision-Language Model Supervision
Yi Xu, Yuxin Hu, Zaiwei Zhang +5
Human drivers rely on commonsense reasoning to navigate diverse and dynamic real-world scenarios. Existing end-to-end (E2E) autonomous driving (AD) models are typically optimized t…
Flash3D: Super-scaling Point Transformers through Joint Hardware-Geometry Locality
Liyan Chen, Gregory P. Meyer, Zaiwei Zhang +2
Recent efforts recognize the power of scale in 3D learning (e.g. PTv3) and attention mechanisms (e.g. FlashAttention). However, current point cloud backbones fail to holistically u…
VLMine: Long-Tail Data Mining with Vision Language Models
Mao Ye, Gregory P. Meyer, Zaiwei Zhang +4
Ensuring robust performance on long-tail examples is an important problem for many real-world applications of machine learning, such as autonomous driving. This work focuses on the…
VLM-KD: Knowledge Distillation from VLM for Long-Tail Visual Recognition
Zaiwei Zhang, Gregory P. Meyer, Zhichao Lu +3
For visual recognition, knowledge distillation typically involves transferring knowledge from a large, well-trained teacher model to a smaller student model. In this paper, we intr…
ViP-LLaVA: Making Large Multimodal Models Understand Arbitrary Visual Prompts
Mu Cai, Haotian Liu, Dennis Park +4
While existing large vision-language multimodal models focus on whole image understanding, there is a prominent gap in achieving region-specific comprehension. Current approaches t…