January 2026

arXiv:2601.18945v1 Announce Type: new Abstract: Presumably, peer reviewers and Large Language Models (LLMs) do very different things when asked to assess research. Still, recent evidence has shown that LLMs have a moderate ability to predict quality scores of published academic journal articles. One untested potential application of LLMs is for internal departmental review, which may be used to support appointment and promotion decisions or to select outputs for national assessments. This study assesses for the first time the […]

Ver mais

arXiv:2601.18944v1 Announce Type: new Abstract: Theorem proving is fundamental to program verification, where the automated proof of Verification Conditions (VCs) remains a primary bottleneck. Real-world program verification frequently encounters hard VCs that existing Automated Theorem Provers (ATPs) cannot prove, leading to a critical need for extensive manual proofs that burden practical application. While Neural Theorem Proving (NTP) has achieved significant success in mathematical competitions, demonstrating the potential of machine learning approaches to formal reasoning, its application to program […]

Ver mais

arXiv:2601.18943v1 Announce Type: new Abstract: Probabilistic bits (p-bits) have recently been employed in neural networks (NNs) as stochastic neurons with sigmoidal probabilistic activation functions. Nonetheless, there remain a wealth of other probabilistic activation functions that are yet to be explored. Here we re-engineer the p-bit by decoupling its stochastic signal path from its input data path, giving rise to a modular p-bit that enables the realization of probabilistic neurons (p-neurons) with a range of configurable probabilistic activation functions, […]

Ver mais

arXiv:2601.18939v1 Announce Type: new Abstract: Behavioral alignment in large language models (LLMs) is often achieved through broad fine-tuning, which can result in undesired side effects like distributional shift and low interpretability. We propose a method for alignment that identifies and updates only the neurons most responsible for a given behavior, a targeted approach that allows for fine-tuning with significantly less data. Using sparse autoencoders (SAEs) and linear probes, we isolate the 3% of MLP neurons most predictive of […]

Ver mais

arXiv:2601.18936v1 Announce Type: new Abstract: We study a bi-level online provisioning and scheduling problem motivated by network resource allocation, where provisioning decisions are made at a slow time scale while queue-/state-dependent scheduling is performed at a fast time scale. We model this two-time-scale interaction using an upper-level online convex optimization (OCO) problem and a lower-level constrained Markov decision process (CMDP). Existing OCO typically assumes stateless decisions and thus cannot capture MDP network dynamics such as queue evolution. Meanwhile, […]

Ver mais

arXiv:2601.18934v1 Announce Type: new Abstract: Across cultures, water has served as a recipient of human confession, a yielding medium that receives vulnerability where rigid surfaces cannot. We present Whispering Water, an interactive installation that materializes human-AI dialogue through cymatic patterns on water. Participants confess secrets to a water surface, triggering a four-phase ritual: confession, contemplation, response, and release. The user’s speech sentiment is directly transmitted into the water to prime its state, while semantic content enters a multi-agent […]

Ver mais

arXiv:2601.18933v1 Announce Type: new Abstract: Traditional evaluations of reasoning capabilities of language models are dominated by adult-centric benchmarks that presuppose broad world knowledge, complex instruction following, and mature pragmatic competence. These assumptions are mismatched to baby language models trained on developmentally plausible input such as child-directed speech and early-childhood narratives, and they obscure which reasoning abilities (if any) emerge under such constraints. We introduce BabyReasoningBench, a GPT-5.2 generated benchmark of 19 reasoning tasks grounded in classic paradigms from […]

Ver mais

arXiv:2601.18930v1 Announce Type: new Abstract: We are interested in enabling autonomous agents to learn and reason about systems with hidden states, such as furniture with hidden locking mechanisms. We cast this problem as learning the parameters of a discrete Partially Observable Markov Decision Process (POMDP). The agent begins with knowledge of the POMDP’s actions and observation spaces, but not its state space, transitions, or observation models. These properties must be constructed from action-observation sequences. Spectral approaches to learning […]

Ver mais

arXiv:2601.18929v1 Announce Type: new Abstract: Vision foundation models (VFMs) have emerged as powerful tools for surgical scene understanding. However, current approaches predominantly rely on unimodal RGB pre-training, overlooking the complex 3D geometry inherent to surgical environments. Although several architectures support multimodal or geometry-aware inputs in general computer vision, the benefits of incorporating depth information in surgical settings remain underexplored. We conduct a large-scale empirical study comparing eight ViT-based VFMs that differ in pre-training domain, learning objective, and input […]

Ver mais

arXiv:2601.18924v1 Announce Type: new Abstract: Large Language Models (LLMs) are increasingly relied upon for complex workflows, yet their ability to maintain flow of instructions remains underexplored. Existing benchmarks conflate task complexity with structural ordering, making it difficult to isolate the impact of prompt topology on performance. We introduce RIFT, Reordered Instruction Following Testbed, to assess instruction following by disentangling structure from content. Using rephrased Jeopardy! question-answer pairs, we test LLMs across two prompt structures: linear prompts, which progress […]

Ver mais