arXiv:2511.07572v1 Announce Type: new Abstract: Mechanistic interpretability aims to decompose neural networks into interpretable features and map their connecting circuits. The standard approach trains sparse autoencoders (SAEs) on each layer’s activations. However, SAEs trained in isolation don’t encourage sparse cross-layer…
arXiv:2505.01386v4 Announce Type: replace Abstract: Machine learning solutions are rapidly adopted to enable a variety of key use cases, from conversational AI assistants to scientific discovery. This growing adoption is expected to increase the associated lifecycle carbon footprint, including both…
arXiv:2511.07585v1 Announce Type: new Abstract: Financial institutions deploy Large Language Models (LLMs) for reconciliations, regulatory reporting, and client communications, but nondeterministic outputs (output drift) undermine auditability and trust. We quantify drift across five model architectures (7B-120B parameters) on regulated financial…
arXiv:2508.05164v2 Announce Type: replace Abstract: Auditory attention detection (AAD) aims to decode listeners’ focus in complex auditory environments from electroencephalography (EEG) recordings, which is crucial for developing neuro-steered hearing devices. Despite recent advancements, EEG-based AAD remains hindered by the absence…
arXiv:2511.07603v1 Announce Type: new Abstract: A common practice in heterogeneous graph neural networks (HGNNs) is to condition parameters on node/edge types, assuming types reflect semantic roles. However, this can cause overreliance on surface-level labels and impede cross-type knowledge transfer. We…
arXiv:2510.07286v2 Announce Type: replace Abstract: Predicting the fitness impact of mutations is central to protein engineering but constrained by limited assays relative to the size of sequence space. Protein language models (pLMs) trained with masked language modeling (MLM) exhibit strong…
arXiv:2511.07629v1 Announce Type: new Abstract: Offline multi-agent reinforcement learning (MARL) is severely hampered by the challenge of evaluating out-of-distribution (OOD) joint actions. Our core finding is that when the behavior policy is factorized – a common scenario where agents act…
arXiv:2511.07198v2 Announce Type: replace Abstract: Large language models (LLMs) demonstrate impressive generalization abilities, yet adapting them effectively across multiple heterogeneous domains remains challenging due to inter-domain interference. To overcome this challenge, we propose a partition-based multi-stage fine-tuning framework designed to…
arXiv:2511.07633v1 Announce Type: new Abstract: We introduce FlowTIE, a neural-network-based framework for phase reconstruction from 4D-Scanning Transmission Electron Microscopy (STEM) data, which integrates the Transport of Intensity Equation (TIE) with a flow-based representation of the phase gradient. This formulation allows…
arXiv:2505.00661v3 Announce Type: replace-cross Abstract: Large language models exhibit exciting capabilities, yet can show surprisingly narrow generalization from finetuning. E.g. they can fail to generalize to simple reversals of relations they are trained on, or fail to make simple logical…
