Africa
LLMDF A: Analyzing Dataflow in Code with Large Language Models
Dataflow analysis is a fundamental code analysis technique that identifies dependencies between program values.
FreeLong: Training-Free Long Video Generation with SpectralBlend Temporal Attention Y u Lu
Our project page is at: https://yulu.net.cn/freelong .
Backdoor Attacks on Multivariate Time Series Forecasting
Unlike traditional backdoor attacks that focus on specific class labels, our approach aims to induce poisoned models to predict future data as a predefined target pattern.
Paralinguistics-A ware Speech-Empowered Large Language Models for Natural Conversation
Recent work shows promising results in expanding the capabilities of large language models (LLM) to directly understand and synthesize speech.
Self-Guiding Exploration for Combinatorial Problems
They utilize prompting techniques such as Exploration-of-Thought, Decomposition, and Refinement to effectively navigate and solve intricate tasks.
Activation Map Compression through Tensor Decomposition for Deep Learning
The application of low-order decomposition results in considerable memory savings while preserving the features essential for learning, and also offers theoretical guarantees to convergence.
Information Re-Organization Improves Reasoning in Large Language Models
Improving the reasoning capabilities of large language models (LLMs) has attracted considerable interest.
Geometry-aware training of factorized layers in tensor Tucker format
Reducing parameter redundancies in neural network architectures is crucial for achieving feasible computational and memory requirements during training and inference phases.