Search Results for author:
Found 11 papers, 5 papers with code
HELENE: Hessian Layer-wise Clipping and Gradient Annealing for Accelerating Fine-tuning LLM with Zeroth-order Optimization
Experimental results on RoBERTa-large and OPT-1. 3B across multiple tasks show that HELENE achieves up to a 20x speedup compared to MeZO, with average accuracy improvements of 1. 5%.
OWLed: Outlier-weighed Layerwise Pruning for Efficient Autonomous Driving Framework
The integration of Large Language Models (LLMs) into autonomous driving systems offers promising enhancements in environmental understanding and decision-making.
A Systematic Assessment of OpenAI o1-Preview for Higher Order Thinking in Education
This study evaluates OpenAI o1-preview's ability to perform higher-order cognitive tasks across 14 dimensions, including critical thinking, systems thinking, computational thinking, design thinking, metacognition, data literacy, creative thinking, abstract reasoning, quantitative reasoning, logical reasoning, analogical reasoning, and scientific reasoning.
Evaluation of OpenAI o1: Opportunities and Challenges of AGI
-Impressive performance in chip design tasks, outperforming specialized models in areas such as EDA script generation and bug analysis.
Revisiting semi-supervised training objectives for differentiable particle filters
Differentiable particle filters combine the flexibility of neural networks with the probabilistic nature of sequential Monte Carlo methods.
Learning Differentiable Particle Filter on the Fly
Differentiable particle filters are an emerging class of sequential Bayesian inference techniques that use neural networks to construct components in state space models.
Unraveling Feature Extraction Mechanisms in Neural Networks
The underlying mechanism of neural networks in capturing precise knowledge has been the subject of consistent research efforts.
Decomposed Prompt Tuning via Low-Rank Reparameterization
While prompt tuning approaches have achieved competitive performance with high efficiency, we observe that they invariably employ the same initialization process, wherein the soft prompt is either randomly initialized or derived from an existing embedding vocabulary.
HRGCN: Heterogeneous Graph-level Anomaly Detection with Hierarchical Relation-augmented Graph Neural Networks
To address the problem, we propose HRGCN, an unsupervised deep heterogeneous graph neural network, to model complex heterogeneous relations between different entities in the system for effectively identifying these anomalous behaviour graphs.
Contextual Distortion Reveals Constituency: Masked Language Models are Implicit Parsers
To leverage this knowledge, we propose a novel chart-based method for extracting parse trees from masked language models (LMs) without the need to train separate parsers.
Deep-Learning Tool for Early Identifying Non-Traumatic Intracranial Hemorrhage Etiology based on CT Scan
Conclusions: The proposed deep learning algorithms can be an effective tool for early identification of hemorrhage etiologies based on NCCT scans.
