arXiv:2406.14234v2 Announce Type: replace-cross Abstract: Magnetic fields from the brain are tiny relative to ambient fields which therefore need to be suppressed. The common solution of passive shielding is expensive, bulky and insufficiently effective, thus motivating research into the alternative of active shielding which comes in two flavours: feed-back and feed-forward. In feed-back designs (the […]
SimuRA: A World-Model-Driven Simulative Reasoning Architecture for General Goal-Oriented Agents
arXiv:2507.23773v2 Announce Type: replace Abstract: AI agents built on foundation models hold enormous promise. Current practice, however, focuses on a one-task-one-agent approach, which not only falls short of scalability and generality, but also faces practical limitations from black-box autoregressive reasoning, where decisions unfold token by token without explicit simulation or counterfactual evaluation of outcomes. Humans, […]
L$^2$M: Mutual Information Scaling Law for Long-Context Language Modeling
arXiv:2503.04725v2 Announce Type: replace-cross Abstract: We present a universal theoretical framework for understanding long-context language modeling based on a bipartite mutual information scaling law that we rigorously verify in natural language. We demonstrate that bipartite mutual information captures multi-token interactions distinct from and scaling independently of conventional two-point mutual information, and show that this provides […]
Does Model Size Matter? A Comparison of Small and Large Language Models for Requirements Classification
arXiv:2510.21443v1 Announce Type: cross Abstract: [Context and motivation] Large language models (LLMs) show notable results in natural language processing (NLP) tasks for requirements engineering (RE). However, their use is compromised by high computational cost, data sharing risks, and dependence on external services. In contrast, small language models (SLMs) offer a lightweight, locally deployable alternative. [Question/problem] […]
Cultural Alien Sampler: Open-ended art generation balancing originality and coherence
arXiv:2510.20849v1 Announce Type: new Abstract: In open-ended domains like art, autonomous agents must generate ideas that are both original and internally coherent, yet current Large Language Models (LLMs) either default to familiar cultural patterns or sacrifice coherence when pushed toward novelty. We address this by introducing the Cultural Alien Sampler (CAS), a concept-selection method that […]
Sample By Step, Optimize By Chunk: Chunk-Level GRPO For Text-to-Image Generation
arXiv:2510.21583v1 Announce Type: cross Abstract: Group Relative Policy Optimization (GRPO) has shown strong potential for flow-matching-based text-to-image (T2I) generation, but it faces two key limitations: inaccurate advantage attribution, and the neglect of temporal dynamics of generation. In this work, we argue that shifting the optimization paradigm from the step level to the chunk level can […]
This EEG Looks Like These EEGs: Interpretable Interictal Epileptiform Discharge Detection With ProtoEEG-kNN
arXiv:2510.20846v1 Announce Type: new Abstract: The presence of interictal epileptiform discharges (IEDs) in electroencephalogram (EEG) recordings is a critical biomarker of epilepsy. Even trained neurologists find detecting IEDs difficult, leading many practitioners to turn to machine learning for help. While existing machine learning algorithms can achieve strong accuracy on this task, most models are uninterpretable […]
Wider or Deeper? Scaling LLM Inference-Time Compute with Adaptive Branching Tree Search
arXiv:2503.04412v4 Announce Type: replace Abstract: Recent advances demonstrate that increasing inference-time computation can significantly boost the reasoning capabilities of large language models (LLMs). Although repeated sampling (i.e., generating multiple candidate outputs) is a highly effective strategy, it does not leverage external feedback signals for refinement, which are often available in tasks like coding. In this […]
Integrated representational signatures strengthen specificity in brains and models
arXiv:2510.20847v1 Announce Type: new Abstract: The extent to which different neural or artificial neural networks (models) rely on equivalent representations to support similar tasks remains a central question in neuroscience and machine learning. Prior work has typically compared systems using a single representational similarity metric, yet each captures only one facet of representational structure. To […]
On the Sample Complexity of Differentially Private Policy Optimization
arXiv:2510.21060v1 Announce Type: cross Abstract: Policy optimization (PO) is a cornerstone of modern reinforcement learning (RL), with diverse applications spanning robotics, healthcare, and large language model training. The increasing deployment of PO in sensitive domains, however, raises significant privacy concerns. In this paper, we initiate a theoretical study of differentially private policy optimization, focusing explicitly […]