Remote Sensing Temporal Vision-Language Models: A Comprehensive Survey
Low-Bit Quantization Favors Undertrained LLMs: Scaling Laws for Quantized LLMs with 100T Training Tokens
We reveal that low-bit quantization favors undertrained large language models (LLMs) by
observing that models with larger sizes or fewer training tokens experience less quantization …
observing that models with larger sizes or fewer training tokens experience less quantization …
MetaOpenFOAM 2.0: Large Language Model Driven Chain of Thought for Automating CFD Simulation and Post-Processing
Computational Fluid Dynamics (CFD) is widely used in aerospace, energy, and biology to
model fluid flow, heat transfer, and chemical reactions. While Large Language Models …
model fluid flow, heat transfer, and chemical reactions. While Large Language Models …
MixLLM: LLM Quantization with Global Mixed-precision between Output-features and Highly-efficient System Design
Z Zheng, X Song, C Liu - arxiv preprint arxiv:2412.14590, 2024 - arxiv.org
Quantization has become one of the most effective methodologies to compress LLMs into
smaller size. However, the existing quantization solutions still show limitations of either non …
smaller size. However, the existing quantization solutions still show limitations of either non …
The Race to Efficiency: A New Perspective on AI Scaling Laws
CP Lu - arxiv preprint arxiv:2501.02156, 2025 - arxiv.org
As large-scale AI models expand, training becomes costlier and sustaining progress grows
harder. Classical scaling laws (eg, Kaplan et al.(2020), Hoffmann et al.(2022)) predict …
harder. Classical scaling laws (eg, Kaplan et al.(2020), Hoffmann et al.(2022)) predict …
[PDF][PDF] HeteroLLM: Accelerating Large Language Model Inference on Mobile SoCs with Heterogeneous AI Accelerators
With the rapid advancement of artificial intelligence technologies such as ChatGPT, AI
agents and video generation, contemporary mobile systems have begun integrating these AI …
agents and video generation, contemporary mobile systems have begun integrating these AI …