arXiv preprints from January 1, 2026 through September 11, 2026 — 02:13:49 EST
Hierarchical reasoning model (HRM) achieves extraordinary performance on various reasoning tasks, significantly outperforming large language model-based reasoners. To understand the strengths and potential failure modes of HRM, we conduct a mechanistic study on its reasoning patterns and find three surprising facts: (a) Failure of...
It is well-known in the field of lossless data compression that probabilistic next-symbol prediction can be used to compress sequences of symbols. Deep neural networks are able to capture rich dependencies in data, offering a powerful means of estimating these probabilities and hence an avenue towards more effective compression...
This work investigates the use of quantum resources in distributed storage systems. Consider an $(n,k,d)$ distributed storage system in which a file is stored across $n$ nodes such that any $k$ nodes suffice to reconstruct the file. When a node fails, any $d$ helper nodes transmit information to a newcomer to rebuild the system. In...
Training and serving Large Language Models (LLMs) require partitioning data across multiple accelerators, where collective operations are frequently bottlenecked by network bandwidth. Lossless compression using Huffman codes is an effective way to alleviate the issue, however, its three-stage design requiring on-the-fly frequency...
Sustainability is becoming increasingly critical in the maritime transport, encompassing both environmental and social impacts, such as Greenhouse Gas (GHG) emissions and navigational safety. Traditional vessel navigation heavily relies on human experience, often lacking autonomy and emission awareness, and is prone to human errors...
Human motion generation from text prompts has made remarkable progress in recent years. However, existing methods primarily rely on either sequence-level or action-level descriptions due to the absence of fine-grained, part-level motion annotations. This limits their controllability over individual body parts. In this work, we...
Networking is central to the growth and visibility of software engineering research and researchers. However, opportunities and capacities to build such networks are not easily identified and often are unevenly distributed. While networking is often viewed as an individual skill, a researchers workplace, culture and environment...
Numerous offline and model-based reinforcement learning systems incorporate world models to emulate the inherent environments. A world model is particularly important in scenarios where direct interactions with the real environment is costly, dangerous, or impractical. The efficacy and interpretability of such world models are notably...
Serverless computing has achieved widespread adoption, with over 70% of AWS organizations using serverless solutions [1]. Meanwhile, machine learning inference workloads increasingly migrate to Function-as-a-Service (FaaS) platforms for their scalability and cost-efficiency [2], [3], [4]. However, this convergence introduces critical...
The ARC-AGI benchmark series serves as a critical measure of few-shot generalization on novel tasks, a core aspect of intelligence. The ARC Prize 2025 global competition targeted the newly released ARC-AGI-2 dataset, which features greater task complexity compared to its predecessor. The Kaggle competition attracted 1,455 teams and...
With the rising popularity of interdisciplinary work and increasing institutional incentives in this direction, there is a growing need to understand how resulting publications incorporate ideas from multiple disciplines. Existing computational approaches, such as affiliation diversity, keywords, and citation patterns, do not account...
We explore a novel problem in streaming submodular maximization, inspired by the dynamics of news-recommendation platforms. We consider a setting where users can visit a news website at any time, and upon each visit, the website must display up to $k$ news items. User interactions are inherently stochastic: each news item presented to...
LLMs are increasingly used as third-party judges, yet their reliability when evaluating speakers in dialogue remains poorly understood. We show that LLMs judge identical claims differently depending on framing: the same content receives different verdicts when presented as a statement to verify ("Is this statement correct?") versus...
The growing complexity and information content of data, together with the need to understand both the complex structures, relationships, and phenomena present in these data spaces, compounded with the emerging need to understand the results produced by AI tools used to analyze the data, requires development of novel, effective data...
Post-training quantization (PTQ) methods for large language models rely on heuristics that implicitly estimate which weight channels most strongly influence model behavior. Two dominant paradigms have emerged: activation-aware methods such as AWQ prioritize channels with large activation magnitudes, while second-order methods such as...
In the spanning-tree congestion problem ($\mathsf{STC}$), we are given a graph $G$, and the objective is to compute a spanning tree of $G$ that minimizes the maximum edge congestion. While $\mathsf{STC}$ is known to be $\mathbb{NP}$-hard, even for some restricted graph classes, several key questions regarding its computational...
Detecting vulnerable road users (VRUs), particularly children and adolescents, in low light and adverse weather conditions remains a critical challenge in computer vision, surveillance, and autonomous vehicle systems. This paper presents a purpose-built lightweight object detection model designed to identify young pedestrians in...
Promptable segmentation foundation models such as SAM3 have demonstrated strong generalization capabilities through interactive and concept-based prompting. However, their direct applicability to medical image segmentation remains limited by severe domain shifts, the absence of privileged spatial prompts, and the need to reason over...
Visual navigation for robotics is inspired by the human ability to navigate environments using visual cues and memory, eliminating the need for detailed maps. In unseen, unmapped, or GPS-denied settings, traditional metric map-based methods fall short, prompting a shift toward learning-based approaches with minimal exploration. In...
Open access to publication, software and hardware is central to robotics: it lowers barriers to entry, supports reproducible science and accelerates reliable system development. However, openness also exacerbates the inherent dual-use risks associated with research and innovation in robotics. It lowers barriers for states and...
We study d-way balanced allocation, which assigns each incoming job to the lightest loaded among d randomly chosen servers. While prior work has extensively studied the performance of the basic scheme, there has been less published work on adapting this technique to many aspects of large-scale systems. Based on our experience in...
Deep neural networks constructed from linear maps and positively homogeneous nonlinearities (e.g., ReLU) possess a fundamental gauge symmetry: the network function is invariant to node-wise diagonal rescalings. However, standard gradient descent is not equivariant to this symmetry, causing optimization trajectories to depend heavily...
Surface wettability, governed by both topography and chemistry, plays a critical role in applications such as heat transfer, lubrication, microfluidics, and surface coatings. In this study, we present a machine learning (ML) framework capable of accurately predicting the wettability of laser-textured metal alloys using experimentally...
We study the problem of adaptive privacy budgeting under generalized differential privacy. Consider the setting where each user $i\in [n]$ holds a tuple $x_i\in U:=U_1\times \dotsb \times U_T$, where $x_i(l)\in U_l$ represents the $l$-th component of their data. For every $l\in [T]$ (or a subset), an untrusted analyst wishes to...
Static Application Security Testing (SAST) tools using taint analysis are widely viewed as providing higher-quality vulnerability detection results compared to traditional pattern-based approaches. However, performing static taint analysis for JavaScript poses two major challenges. First, JavaScript's dynamic features complicate data...