72 citations · 289 across the 69 of their papers we have counts for
11 papers · 1 filter
Beyond Binary Rewards: Training LMs to Reason About Their Uncertainty
Mehul Damani, Isha Puri, Stewart Slocum +4
When language models (LMs) are trained via reinforcement learning (RL) to generate natural language "reasoning chains", their performance improves on a variety of difficult questio…
ZipNN: Lossless Compression for AI Models
Moshik Hershcovitch, Andrew Wood, Leshem Choshen +7
With the growth of model sizes and the scale of their deployment, their sheer size burdens the infrastructure requiring more network and more storage to accommodate these. While th…
A Survey on Model MoErging: Recycling and Routing Among Specialized Experts for Collaborative Learning
Prateek Yadav, Colin Raffel, Mohammed Muqeeth +6
The availability of performant pre-trained models has led to a proliferation of fine-tuned expert models that are specialized to a particular domain or task. Model MoErging methods…
Asymmetry in Low-Rank Adapters of Foundation Models
Jiacheng Zhu, Kristjan Greenewald, Kimia Nadjahi +6
Parameter-efficient fine-tuning optimizes large, pre-trained foundation models by updating a subset of parameters; in this class, Low-Rank Adaptation (LoRA) is particularly effecti…
ComPEFT: Compression for Communicating Parameter Efficient Updates via Sparsification and Quantization
Prateek Yadav, Leshem Choshen, Colin Raffel +1
Parameter-efficient fine-tuning (PEFT) techniques make it possible to efficiently adapt a language model to create "expert" models that specialize to new tasks or domains. Recent t…
TIES-Merging: Resolving Interference When Merging Models
Prateek Yadav, Derek Tam, Leshem Choshen +2
Transfer learning - i.e., further fine-tuning a pre-trained model on a downstream task - can confer significant advantages, including improved downstream performance, faster conver…
Knowledge is a Region in Weight Space for Fine-tuned Language Models
Almog Gueta, Elad Venezian, Colin Raffel +3
Research on neural networks has focused on understanding a single model trained on a single dataset. However, relatively little is known about the relationships between different m…
ColD Fusion: Collaborative Descent for Distributed Multitask Finetuning
Shachar Don-Yehiya, Elad Venezian, Colin Raffel +3
We propose a new paradigm to continually evolve pretrained models, denoted ColD Fusion. It provides the benefits of multitask learning but leverages distributed computation with li…
Are You Convinced? Choosing the More Convincing Evidence with a Siamese Network
Martin Gleize, Eyal Shnarch, Leshem Choshen +4
With the advancement in argument detection, we suggest to pay more attention to the challenging task of identifying the more convincing arguments. Machines capable of responding an…
Let's Agree to Agree: Neural Networks Share Classification Order on Real Datasets
Guy Hacohen, Leshem Choshen, Daphna Weinshall
We report a series of robust empirical observations, demonstrating that deep Neural Networks learn the examples in both the training and test sets in a similar order. This phenomen…
DORA The Explorer: Directed Outreaching Reinforcement Action-Selection
Leshem Choshen, Lior Fox, Yonatan Loewenstein
Exploration is a fundamental aspect of Reinforcement Learning, typically implemented using stochastic action-selection. Exploration, however, can be more efficient if directed towa…