arXiv:2609.36081v1 Announce Type: new
Abstract: Representations continually change as a network learns new tasks. We ask whether early representational changes naturally form a geometric structure th...
By Yuantao Deng, Jinnuo Liu, Kaizhen Tan, Yuchen Liu
The paper argues that finite brains generalize to arbitrarily long inputs by using spatial memory that grows with input size while the learner’s observations remain finite. It proposes that this memory is structured as cycles—grid modules, place cells, and hippocampal indices—controlled by a prefrontal system that never directly observes the cycles. Experiments show a neural network trained on strings up to 40 symbols achieves high accuracy on longer sequences, outperforming LSTMs and Transformers on several benchmarks and correctly reversing strings up to 15,015 symbols.
By Yuhang He, Si Wu
The paper investigates when a language model actually learns task information versus when its readout (unembedding matrix) learns to express that information. Using a new parameter‑trajectory cross‑coding method, the authors find that hidden states can encode task data early in training, but the readout reorganizes only in a narrow window (0.4–1.1% of Pythia’s pretraining). By varying the readout learning rate, they show that faster readout learning reduces the gap between hidden‑state encoding and output expression without affecting final performance.
By Matteo He, William F. Shen, Alex Iacob, Andrej Jovanovic, Xinchi Qiu, Nicholas D. Lane
arXiv:2606. 06479v1 Announce Type: new Abstract: Training recurrent neural networks (RNNs) requires assigning credit across long sequences of computations.
By Akarsh Kumar, Phillip Isola
arXiv:2605. 10795v2 Announce Type: replace-cross Abstract: Large language models excel at factual recall, yet the fundamental limits of storing input--output associations with neural networks remain unclear.
By Alessio Giorlandino, Sebastian Goldt, Antoine Maillard
The paper investigates continual machine unlearning, where models must forget data over time. It identifies a fundamental issue called plasticity collapse, where successive unlearning requests cause geometric constraints that saturate parameter space, leading to two failure modes: forward failure (reduced forgetting quality) and backward failure (re‑memorization). Experiments across architectures and datasets confirm that plasticity collapse is a pervasive problem in continual unlearning.
By Yingdan Shi, Xiang Xu, Kaize Ding, Alfred O. Hero, Ren Wang