490 citations
- National Institute for AstrophysicsIT3 papers
- California Institute of TechnologyUS2 papers
- Centre National de la Recherche ScientifiqueFR2 papers
- Durham UniversityGB2 papers
- Goddard Space Flight CenterUS2 papers
- Herzberg Institute of AstrophysicsCA2 papers
- Jet Propulsion LaboratoryUS2 papers
- Space Telescope Science InstituteUS2 papers
- Stockholm UniversitySE2 papers
- Technical University of DenmarkDK2 papers
- UK Astronomy Technology CentreGB2 papers
- Université Côte d'AzurFR2 papers
18 papers
Spectral Compact Training: Pre-Training Large Language Models via Permanent Truncated SVD and Stiefel QR Retraction
Björn Roman Kohlberger
The memory wall remains the primary bottleneck for training large language models on consumer hardware. We introduce Spectral Compact Training (SCT), a method that replaces dense w…
The factors that influence protostellar multiplicity II. Gas temperature and mass in Perseus with APEX
N. M. Murillo, C. M. Fuchs, D. Harsono +5
Protostellar multiplicity is a common outcome of the star formation process. To fully understand the formation and evolution of these systems, the physical parameters of the molecu…
Psyzkaller: Learning from Historical and On-the-Fly Execution Data for Smarter Seed Generation in OS kernel Fuzzing
Boyu Liu, Yang Zhang, Liang Cheng +6
OS Kernel fuzzers such as Syzkaller often struggle to generate syscall sequences that respect intrinsic Syscall Dependency Relations (SDRs), resulting in seeds that either violate…
MetAdv: A Unified and Interactive Adversarial Testing Platform for Autonomous Driving
Aishan Liu, Jiakai Wang, Tianyuan Zhang +6
Evaluating and ensuring the adversarial robustness of autonomous driving (AD) systems is a critical and unresolved challenge. This paper introduces MetAdv, a novel adversarial test…
A New Method to Capturing Compositional Knowledge in Linguistic Space
Jiahe Wan
Compositional understanding allows visual language models to interpret complex relationships between objects, attributes, and relations in images and text. However, most existing m…
USTCCTSU at SemEval-2024 Task 1: Reducing Anisotropy for Cross-lingual Semantic Textual Relatedness Task
Jianjian Li, Shengwei Liang, Yong Liao +2
Cross-lingual semantic textual relatedness task is an important research task that addresses challenges in cross-lingual communication and text understanding. It helps establish se…