arXiv Machine Learning

Cortex and subcortex play distinct roles over learning when cortical memory is limited

arXiv:2606. 00667v1 Announce Type: cross Abstract: It has been proposed that the brain integrates flexible, computationally expensive cortical processing with simpler, lower-cost subcortical mechanisms to achieve resource-efficient performance greater than that of either system alone.

arXiv Machine Learning
Sep 22

Improving the adaptive and continuous learning capabilities of artificial neural networks: Lessons from multi-neuromodulatory dynamics

The paper investigates how multi‑neuromodulatory dynamics—driven by dopamine, acetylcholine, serotonin, and noradrenaline—can improve artificial neural networks’ continuous adaptive learning and mitigate catastrophic forgetting. It demonstrates that neuromodulators interact across multiple spatial and temporal scales, creating a complex many‑to‑many mapping between neuromodulators and tasks. The authors propose neuromodulation‑aware learning rules, architectural formulations, and a conceptual Go/No‑Go study to illustrate how biologically inspired mechanisms can enhance ANN robustness and adaptability.

By Jie Mei, Alejandro Rodriguez-Garcia, Daigo Takeuchi, Gabriel Wainstein, Nina Hubig, Yalda Mohsenzadeh, Srikanth Ramaswamy
arXiv AI
Oct 16

Co2In: a Bi-level Memory Incremental Learning Framework with Knowledge Encoding, Consolidation, and Integration

Co2In is a bi‑level memory incremental learning framework that mimics human memory mechanisms. It uses a working memory to encode new knowledge and a long‑term memory to retain it, with a consolidation step that extracts patterns and compresses them into a compact representation. Experiments on CIFAR‑10, CIFAR‑100, and Tiny‑ImageNet demonstrate state‑of‑the‑art performance while keeping memory usage efficient.

By Wenju Sun, Qingyong Li, Boyang Li, Wen Wang, Siyu Zhang, Yi Wei, Yangliao Geng
arXiv Machine Learning
Oct 15

Do LLMs Learn from Rewards in Context? : Rethinking the role of reward in In-Context RL

The paper investigates whether large language models (LLMs) can learn from rewards presented in context, a process termed in-context reinforcement learning (ICRL). Experiments across four benchmarks and six models show that while LLMs read reward signals, altering or removing these rewards has little impact on performance, and shuffled or corrupted trajectories are as effective as real ones. These findings suggest that direct ICRL behaves more like in-context learning (ICL) than true inference-time reinforcement learning.

By Minchan Kwon, Seunghee Koh, Sunghyun Baek, Minsung Bae, Junmo Kim
arXiv Computation and Language
Nov 5

Sparse Reward Subsystem in Large Language Models

The paper demonstrates that reward-related information in large language models is concentrated in a sparse subset of neurons. Two types of neurons are identified: value neurons, which predict state value, and dopamine neurons, which encode step-level temporal difference errors. These neurons form a reward subsystem that is robust across datasets and models, and can be used to predict model confidence and guide inference-time search.

By Guowei Xu, Mert Yuksekgonul, James Zou
arXiv Machine Learning
Oct 9

Do LLMs Learn from Rewards in Context? : Rethinking the role of reward in In-Context Reinforcement Learning

The paper investigates whether large language models (LLMs) can learn from rewards presented in context, a process termed in‑context reinforcement learning (ICRL). Through experiments on four benchmarks and six models, the authors find that while LLMs read reward signals, altering or removing these signals has little effect on performance, and that trajectory structure—rather than reward content—drives improvement. These results suggest that direct ICRL behaves more like standard in‑context learning (ICL) than true inference‑time reinforcement learning.

By Minchan Kwon, Seunghee Koh, Sunghyun Baek, Minsung Bae, Junmo Kim
arXiv AI
Jun 18

Structured Representation Learning with Locally Linear Embeddings and Adaptive Feature Fusion

arXiv:2606. 18469v1 Announce Type: cross Abstract: Neuroscientific research has revealed that the brain encodes complex behaviors by leveraging structured, low-dimensional manifolds and dynamically fusing multiple sources of information through adaptive gating mechanisms.

By Somjit Nath, Jackson J Cone, Derek Nowrouzezahrai, Samira Ebrahimi Kahou