activity
20242026
collaborators
Showing 2024Show all

9 papers · 1 filter

cs.CL2024

LoRA Soups: Merging LoRAs for Practical Skill Composition Tasks

Akshara Prabhakar, Yuanzhi Li, Karthik Narasimhan +3

Low-Rank Adaptation (LoRA) is a popular technique for parameter-efficient fine-tuning of Large Language Models (LLMs). We study how different LoRA modules can be merged to achieve…

cs.LG2024

Loss-to-Loss Prediction: Scaling Laws for All Datasets

David Brandfonbrener, Nikhil Anand, Nikhil Vyas +2

While scaling laws provide a reliable methodology for predicting train loss across compute scales for a single data distribution, less is known about how these predictions should c…

cs.LG2024

Transcendence: Generative Models Can Outperform The Experts That Train Them

Edwin Zhang, Vincent Zhu, Naomi Saphra +5

Generative models are trained with the simple objective of imitating the conditional probability distribution induced by the data they are trained on. Therefore, when trained on da…

cs.LG2024

Don't Stop Me Now: Embedding Based Scheduling for LLMs

Rana Shahout, Eran Malach, Chunwei Liu +3

Efficient scheduling is crucial for interactive Large Language Model (LLM) applications, where low request completion time directly impacts user engagement. Size-based scheduling a…

cs.CL2024

On the Power of Decision Trees in Auto-Regressive Language Modeling

Yulu Gan, Tomer Galanti, Tomaso Poggio +1

Originally proposed for handling time series data, Auto-regressive Decision Trees (ARDTs) have not yet been explored for language modeling. This paper delves into both the theoreti…

cs.LG2024

Auto-Regressive Next-Token Predictors are Universal Learners

Eran Malach

Large language models display remarkable capabilities in logical and mathematical reasoning, allowing them to solve complex tasks. Interestingly, these abilities emerge in networks…