Deep Learning
Lisa: Lazy Safety Alignment for Large Language Models against Harmful Fine-tuning Attack
Fine-tuning services for Large Language Models (LLMs) have emerged as a new paradigm.
DiffusionFake: Enhancing Generalization in Deepfake Detection via Guided Stable Diffusion
The rapid progress of Deepfake technology has made face swapping highly realistic, raising concerns about the malicious use of fabricated facial content.
Can neural operators always be continuously discretized? Takashi Furuya
We consider the problem of discretization of neural operators between Hilbert spaces in a general framework including skip connections. We focus on bijec-tive neural operators through the lens of diffeomorphisms in infinite dimensions.
MixEval: Deriving Wisdom of the Crowd from LLM Benchmark Mixtures Jinjie Ni
Evaluating large language models (LLMs) is challenging.
Classic GNNs are Strong Baselines: Reassessing GNNs for Node Classification
Our study aims to promote a higher standard of empirical rigor in the field of graph machine learning, encouraging more accurate comparisons and evaluations of model capabilities.
Convolutions and More as Einsum: AT ensor Network Perspective with Advances for Second-Order Methods
Our TN implementation accelerates a recently-proposed KFAC variant up to 4.5 x while removing the
