Search Results for author:
Found 5 papers, 1 papers with code
Layer Skip: Enabling Early Exit Inference and Self-Speculative Decoding
We present LayerSkip, an end-to-end solution to speed-up inference of large language models (LLMs).
Decoding Data Quality via Synthetic Corruptions: Embedding-guided Pruning of Code Data
Armed with this knowledge, we devise novel pruning metrics that operate in embedding space to identify and remove low-quality entries in the Stack dataset.
Sieve: Multimodal Dataset Pruning Using Image Captioning Models
We propose a pruning signal, Sieve, that employs synthetic captions generated by image-captioning models pretrained on small, diverse, and well-aligned image-text pairs to evaluate the alignment of noisy image-text pairs.
Self-Supervised Image-to-Point Distillation via Semantically Tolerant Contrastive Loss
However, image-to point representation learning for autonomous driving datasets faces two main challenges: 1) the abundance of self-similarity, which results in the contrastive losses pushing away semantically similar point and image regions and thus disturbing the local semantic structure of the learned representations, and 2) severe class imbalance as pretraining gets dominated by over-represented classes.
Dense Voxel Fusion for 3D Object Detection
Sequential fusion methods suffer from a limited number of pixel and point correspondences due to point cloud sparsity, or their performance is strictly capped by the detections of one of the modalities.
