1.1k citations · 2.1k across the 19 of their papers we have counts for
13 papers · 1 filter
General Preference Reinforcement Learning
Muhammad Umer, Muhammad Ahmed Mohsin, Ahsan Bilal +5
Post-training has split large language model (LLM) alignment into two largely disconnected tracks. Online reinforcement learning (RL) with verifiable rewards drives emergent reason…
Improving Latent Generalization Using Test-time Compute
Arslan Chaudhry, Sridhar Thiagarajan, Andrew Lampinen
Language Models (LMs) exhibit two distinct mechanisms for knowledge acquisition: in-weights learning (i.e., encoding information within the model weights) and in-context learning (…
A Comparative Analysis of LLM Adaptation: SFT, LoRA, and ICL in Data-Scarce Scenarios
Bernd Bohnet, Rumen Dangovski, Kevin Swersky +4
The remarkable capabilities of Large Language Models (LLMs) often need to be tailored for specific applications, requiring the integration of new knowledge or the acquisition of ne…
Latent learning: episodic memory complements parametric learning by enabling flexible reuse of experiences
Andrew Kyle Lampinen, Martin Engelcke, Yuxuan Li +2
When do machine learning systems fail to generalize, and what mechanisms could improve their generalization? Here, we draw inspiration from cognitive science to argue that one weak…
Is forgetting less a good inductive bias for forward transfer?
Jiefeng Chen, Timothy Nguyen, Dilan Gorur +1
One of the main motivations of studying continual learning is that the problem setting allows a model to accrue knowledge from past tasks to learn new tasks more efficiently. Howev…
NEVIS'22: A Stream of 100 Tasks Sampled from 30 Years of Computer Vision Research
Jorg Bornschein, Alexandre Galashov, Ross Hemsley +17
A shared goal of several machine learning communities like continual learning, meta-learning and transfer learning, is to design algorithms and models that efficiently and robustly…
When does mixup promote local linearity in learned representations?
Arslan Chaudhry, Aditya Krishna Menon, Andreas Veit +3
Mixup is a regularization technique that artificially produces new samples using convex combinations of original training points. This simple technique has shown strong empirical p…
Architecture Matters in Continual Learning
Seyed Iman Mirzadeh, Arslan Chaudhry, Dong Yin +4
A large body of research in continual learning is devoted to overcoming the catastrophic forgetting of neural networks by designing new algorithms that are robust to the distributi…
Wide Neural Networks Forget Less Catastrophically
Seyed Iman Mirzadeh, Arslan Chaudhry, Dong Yin +4
A primary focus area in continual learning research is alleviating the "catastrophic forgetting" problem in neural networks by designing new algorithms that are more robust to the…
Continual Learning in Low-rank Orthogonal Subspaces
Arslan Chaudhry, Naeemullah Khan, Puneet K. Dokania +1
In continual learning (CL), a learner is faced with a sequence of tasks, arriving one after the other, and the goal is to remember all the tasks once the continual learning experie…
Using Hindsight to Anchor Past Knowledge in Continual Learning
Arslan Chaudhry, Albert Gordo, Puneet K. Dokania +2
In continual learning, the learner faces a stream of data whose distribution changes over time. Modern neural networks are known to suffer under this setting, as they quickly forge…
On Tiny Episodic Memories in Continual Learning
Arslan Chaudhry, Marcus Rohrbach, Mohamed Elhoseiny +4
In continual learning (CL), an agent learns from a stream of tasks leveraging prior experience to transfer knowledge to future tasks. It is an ideal framework to decrease the amoun…
Efficient Lifelong Learning with A-GEM
Arslan Chaudhry, Marc'Aurelio Ranzato, Marcus Rohrbach +1
In lifelong learning, the learner is presented with a sequence of tasks, incrementally building a data-driven prior which may be leveraged to speed up learning of a new task. In th…