106 citations · 234 across the 32 of their papers we have counts for
35 papers
Learning to Read Out: Unembedding Dynamics in Language Model Pretraining
Matteo He, William F. Shen, Alex Iacob +3
When does a language model acquire a capability? Developmental studies usually answer this by tracking when models start producing the correct token. But that prediction passes thr…
Can AI Scientists Coordinate at Runtime?
Zijian Liu, Yangzhixin Luo, Junyu Lu +6
Multi-agent AI scientists have shown improving performance across a diverse range of tasks. Yet a common approach is design-time agentic orchestration, which typically relies on fi…
Sparse Readout Prism: Explaining Logit-Lens Scores in Features Instead of Tokens
Matteo He, William F. Shen, Xinchi Qiu +1
A language model's prediction of its next token develops across layers, and lens methods track this process by decoding intermediate hidden states into tokens. But a lens reading r…
How LLM Task-Adaptation Reshapes Alignment: A Multi-dimensional Study of Behavioral and Representational Drift
James Elcock, William F. Shen, Xinchi Qiu +1
Post-training is a key mechanism for adapting large language models to downstream tasks. While prior work suggests that task adaptation can alter a model's pre-existing alignment,…
Rethinking Rubric Generation for Improving LLM Judge and Reward Modeling for Open-ended Tasks
William F. Shen, Xinchi Qiu, Chenxi Whitehouse +6
Recently, rubrics have been used to guide LLM judges in capturing subjective, nuanced, multi-dimensional human preferences, and have been extended from evaluation to reward signals…
LoRDO: Distributed Low-Rank Optimization with Infrequent Communication
Andrej Jovanović, Alex Iacob, Mher Safaryan +6
Distributed training of foundation models via is limited by interconnect bandwidth. While infrequent communication strategies reduce synchronization frequency, they…
MT-DAO: Multi-Timescale Distributed Adaptive Optimizers with Local Updates
Alex Iacob, Andrej Jovanovic, Mher Safaryan +6
Training large models with distributed data parallelism (DDP) requires frequent communication of gradients across workers, which can saturate bandwidth. Infrequent communication st…
Hallucination reduction with CASAL: Contrastive Activation Steering For Amortized Learning
Wannan, Yang, Xinchi Qiu +6
Large Language Models (LLMs) exhibit impressive capabilities but often hallucinate, confidently providing incorrect answers instead of admitting ignorance. Prior work has shown tha…
AbbIE: Autoregressive Block-Based Iterative Encoder for Efficient Sequence Modeling
Preslav Aleksandrov, Meghdad Kurmanji, Fernando Garcia Redondo +7
We introduce the Autoregressive Block-Based Iterative Encoder (AbbIE), a novel recursive generalization of the encoder-only Transformer architecture, which achieves better perplexi…
Breaking Physical and Linguistic Borders: Multilingual Federated Prompt Tuning for Low-Resource Languages
Wanru Zhao, Yihong Chen, Royson Lee +4
Pre-trained large language models (LLMs) have become a cornerstone of modern natural language processing, with their capabilities extending across a wide range of applications and…
SEAT: Sparse Entity-Aware Tuning for Knowledge Adaptation while Preserving Epistemic Abstention
William F. Shen, Xinchi Qiu, Nicola Cancedda +1
Adapting LLMs with new knowledge is increasingly important, but standard fine-tuning often erodes aligned epistemic abstention: the ability to acknowledge when the model does not k…
DES-LOC: Desynced Low Communication Adaptive Optimizers for Training Foundation Models
Alex Iacob, Lorenzo Sani, Mher Safaryan +8
Scaling foundation model training with Distributed Data Parallel (DDP) methods is bandwidth-limited. Existing infrequent communication methods like Local SGD were designed to synch…
Editing as Unlearning: Are Knowledge Editing Methods Strong Baselines for Large Language Model Unlearning?
Zexi Li, Xiangzhu Wang, William F. Shen +5
Large language Model (LLM) unlearning, i.e., selectively removing information from LLMs, is vital for responsible model deployment. Differently, LLM knowledge editing aims to modif…
LLM Unlearning via Neural Activation Redirection
William F. Shen, Xinchi Qiu, Meghdad Kurmanji +5
The ability to selectively remove knowledge from LLMs is highly desirable. However, existing methods often struggle with balancing unlearning efficacy and retain model utility, and…
Photon: Federated LLM Pre-Training
Lorenzo Sani, Alex Iacob, Zeyu Cao +8
Scaling large language models (LLMs) demands extensive data and computing resources, which are traditionally constrained to data centers by the high-bandwidth requirements of distr…
DEPT: Decoupled Embeddings for Pre-training Language Models
Alex Iacob, Lorenzo Sani, Meghdad Kurmanji +5
Language Model pre-training uses broad data mixtures to enhance performance across domains and languages. However, training on such heterogeneous text corpora requires extensive an…
FLea: Addressing Data Scarcity and Label Skew in Federated Learning via Privacy-preserving Feature Augmentation
Tong Xia, Abhirup Ghosh, Xinchi Qiu +1
Federated Learning (FL) enables model development by leveraging data distributed across numerous edge devices without transferring local data to a central server. However, existing…
How Data Inter-connectivity Shapes LLMs Unlearning: A Structural Unlearning Perspective
Xinchi Qiu, William F. Shen, Yihong Chen +4
While unlearning knowledge from large language models (LLMs) is receiving increasing attention, one important aspect remains unexplored. Existing approaches and benchmarks assume d…
Sheaf HyperNetworks for Personalized Federated Learning
Bao Nguyen, Lorenzo Sani, Xinchi Qiu +2
Graph hypernetworks (GHNs), constructed by combining graph neural networks (GNNs) with hypernetworks (HNs), leverage relational data across various domains such as neural architect…
The Future of Large Language Model Pre-training is Federated
Lorenzo Sani, Alex Iacob, Zeyu Cao +8
Generative pre-trained large language models (LLMs) have demonstrated impressive performance over a wide range of tasks, thanks to the unprecedented amount of data they have been t…
FedAnchor: Enhancing Federated Semi-Supervised Learning with Label Contrastive Loss for Unlabeled Clients
Xinchi Qiu, Yan Gao, Lorenzo Sani +6
Federated learning (FL) is a distributed learning paradigm that facilitates collaborative training of a shared global model across devices while keeping data localized. The deploym…
FLea: Addressing Data Scarcity and Label Skew in Federated Learning via Privacy-preserving Feature Augmentation
Tong Xia, Abhirup Ghosh, Xinchi Qiu +1
Federated Learning (FL) enables model development by leveraging data distributed across numerous edge devices without transferring local data to a central server. However, existing…
FedL2P: Federated Learning to Personalize
Royson Lee, Minyoung Kim, Da Li +4
Federated learning (FL) research has made progress in developing algorithms for distributed learning of global models, as well as algorithms for local personalization of those comm…
Pollen: High-throughput Federated Learning Simulation via Resource-Aware Client Placement
Lorenzo Sani, Pedro Porto Buarque de Gusmão, Alex Iacob +5
Federated Learning (FL) is a privacy-focused machine learning paradigm that collaboratively trains models directly on edge devices. Simulation plays an essential role in FL adoptio…