activity
20242026
collaborators
Showing cs.LGShow all

33 papers · 1 filter

cs.LG2026

Loss Smoothing for Stable Adaptation Under Distribution Shift

Darshan Patil, Ekaterina Lobacheva, Razvan Pascanu +1

In settings such as fine-tuning and reinforcement learning, neural networks are often adapted under distribution shift. Standard adaptation methods typically optimize the target ob…

cs.LG2026

From Markov to Laplace: How Mamba In-Context Learns Markov Chains

Marco Bondaschi, Nived Rajaraman, Xiuying Wei +5

While transformer-based language models have driven the AI revolution thus far, their computational complexity has spurred growing interest in viable alternatives, such as structur…

cs.LG2026

MesaNet: Sequence Modeling by Locally Optimal Test-Time Training

Johannes von Oswald, Nino Scherrer, Seijin Kobayashi +14

Sequence modeling is currently dominated by causal transformer architectures that use softmax self-attention. Although widely adopted, transformers require scaling memory and compu…

cs.LG2026

Mining Generalizable Activation Functions

Alex Vitvitskyi, Michael Boratko, Matej Grcic +3

The choice of activation function is an active area of research, with different proposals aimed at improving optimization, while maintaining expressivity. Additionally, the activat…

cs.LG2026

Perplexity Cannot Always Tell Right from Wrong

Petar Veličković, Federico Barbero, Christos Perivolaropoulos +2

Perplexity -- a function measuring a model's overall level of "surprise" when encountering a particular output -- has gained significant traction in recent years, both as a loss fu…

cs.LG2025

Maxwell's Demon at Work: Efficient Pruning by Leveraging Saturation of Neurons

Simon Dufort-Labbé, Pierluca D'Oro, Evgenii Nikishin +3

When training neural networks, dying neurons -- units becoming inactive or saturated -- are traditionally seen as harmful. This paper sheds new light on this phenomenon. By explori…