Search Results for author:
Found 7 papers, 3 papers with code
MiniCPM: Unveiling the Potential of Small Language Models with Scalable Training Strategies
For data scaling, we introduce a Warmup-Stable-Decay (WSD) learning rate scheduler (LRS), conducive to continuous training and domain adaptation.
A Unified Model Selection Technique for Spectral Clustering Based Motion Segmentation
Motion segmentation is a fundamental problem in computer vision and is crucial in various applications such as robotics, autonomous driving and action recognition.
Ouroboros: Speculative Decoding with Large Model Enhanced Drafting
In this paper, we introduce Ouroboros, which constructs a phrase candidate pool from the verification process of LLMs to provide candidates for draft generation of the small model.
Motion Segmentation from a Moving Monocular Camera
We then construct two robust affinity matrices representing the pairwise object motion affinities throughout the whole video using epipolar geometry and the motion information provided by optical flow.
CPET: Effective Parameter-Efficient Tuning for Compressed Large Language Models
Parameter-efficient tuning (PET) has been widely explored in recent years because it tunes much fewer parameters (PET modules) than full-parameter fine-tuning (FT) while still stimulating sufficient knowledge from large language models (LLMs) for downstream tasks.
Agile gesture recognition for capacitive sensing devices: adapting on-the-job
However, there is growing demand for gesture recognition technology that can be implemented on low-power devices using limited sensor data instead of high-dimensional inputs like hand images.
Tool Learning with Foundation Models
Considering the lack of a systematic tool learning evaluation in prior works, we experiment with 18 representative tools and show the potential of current foundation models in skillfully utilizing tools.
