arXiv preprints from January 1, 2026 through September 9, 2026 — 23:23:05 EST
Time Series foundation models (TSFMs) deliver strong forecasting performance through large-scale pretraining, but their large parameter sizes make deployment costly. While knowledge distillation offers a natural and effective approach for model compression, techniques developed for general machine learning tasks are not directly...
Reinforcement learning (RL) post-training has become pivotal for enhancing the capabilities of modern large models. A recent trend is to develop RL systems with a fully disaggregated architecture, which decouples the three RL phases (rollout, reward, and training) onto separate resources and executes them asynchronously. However, two...
Referring Expression Comprehension (REC) aims to localize the image region corresponding to a natural language query. Recent neuro-symbolic REC approaches leverage large language models (LLMs) and vision-language models (VLMs) to perform compositional reasoning, decomposing queries into structured programs and executing them...
In this paper, we initiate the study of Extended Gabidulin codes with a Kronecker product structure and propose three enhanced variants of the Rank Quasi-Cyclic (RQC) (Melchor et.al., IEEE IT, 2018) cryptosystem. First, we establish precise bounds on the minimum rank distance of Gabidulin-Kronecker product codes under two distinct...
Given an input image and set of class names, panoptic segmentation aims to label each pixel in an image with class labels and instance labels. In comparison, Open Vocabulary Panoptic Segmentation aims to facilitate the segmentation of arbitrary classes according to user input. The challenge is that a panoptic segmentation system...
Research on data-driven ocean models has progressed rapidly in recent years; however, the application of these models to global eddy-resolving ocean forecasting remains limited. The accurate representation of ocean dynamics across a wide range of spatial scales remains a major challenge in such applications. This study proposes a...
The unmanned aerial vehicle (UAV) network plays important roles in emergency communications. However, it is challenging to design reliable routing strategies that ensure low latency, energy efficiency, and security in the dynamic and attack-prone environments. To this end, we design a secure routing architecture integrating...
Large language models (LLMs) possess extensive world knowledge, yet methods for effectively eliciting this knowledge remain underexplored. Nationality and region prediction tasks require understanding of not only linguistic features but also cultural and historical background, making LLM world knowledge particularly valuable. However,...
Building one-shot 3D animatable head avatars is an important yet challenging problem. Existing methods generally collapse under large camera pose variations, compromising the realism of 3D avatars. In this work, we propose a new framework to tackle the novel setting of one-shot 3D full-head animatable avatar reconstruction in a single...
Video-text retrieval (VTR) aims to locate relevant videos using natural language queries. Current methods, often based on pre-trained models like CLIP, are hindered by video's inherent redundancy and their reliance on coarse, final-layer features, limiting matching accuracy. To address this, we introduce the HVP-Net (Hierarchical...
Zero-shot Vision-and-Language Navigation (VLN) agents leveraging Large Language Models (LLMs) excel in generalization but suffer from insufficient spatial perception. Focusing on complex continuous environments, we categorize key perceptual bottlenecks into three spatial challenges: door interaction,multi-room navigation, and...
Source-Free Object Detection (SFOD) has garnered much attention in recent years by eliminating the need of source-domain data in cross-domain tasks, but existing SFOD methods suffer from the Source Bias problem, i.e. the adapted model remains skewed towards the source domain, leading to poor generalization and error accumulation...
Embedding models are a fundamental component of modern AI systems such as semantic search and retrieval-augmented generation. Recent advances in large foundation models have substantially accelerated the development of embedding models, including those based on Large Language Models (LLMs), Vision Language Models (VLMs), and...
Dynamic community detection plays a crucial role in understanding the temporal evolution of community structures in complex networks. Existing methods based on nonnegative tensor RESCAL decomposition typically require the decomposition rank to equal the number of communities, which limits model flexibility. This paper proposes an...
Equipping Large Language Models (LLMs) with external tools enables them to solve complex real-world problems. However, the robustness of existing methods remains a critical challenge when confronting novel or evolving tools. Existing trajectory-centric paradigms primarily rely on memorizing static solution paths during training, which...
Video diffusion models, trained on large-scale datasets, naturally capture correspondences of shared features across frames. Recent works have exploited this property for tasks such as optical flow prediction and tracking in a zero-shot setting. Motivated by these findings, we investigate whether supervised training can more fully...
Transformer hidden states encode information as high-dimensional vectors, yet whether direction (orientation in representational space) and magnitude (vector norm) serve distinct functional roles remains unclear. Studying Pythia-family models, we discover a striking cross-over dissociation: angular perturbations cause up to 42.9 more...
As large language models are increasingly used in high-stakes domains, it is essential that their outputs reflect not average} human preference, rather range of varying perspectives. Achieving such pluralism, however, remains challenging. Existing approaches consider limited values or rely on prompt-level interventions, lacking value...
This study investigates the integration of Large Language Models (LLMs) into the feedback mechanisms of the architectural design studio, shifting the focus from generative production to reflective pedagogy. Employing a mixed-methods approach with surveys and semi structured interviews with 22 architecture students at the Singapore...
Time series forecasting in specialized domains is often constrained by limited data availability, where conventional models typically require large-scale datasets to effectively capture underlying temporal dynamics. To tackle this few-shot challenge, we propose LTSM-DIFF (Large-scale Temporal Sequential Memory with Diffusion), a novel...
Large language models (LLMs) are increasingly used for mental health support, yet they can produce responses that are overly directive, inconsistent, or clinically misaligned, particularly in sensitive or high-risk contexts. Existing approaches to mitigating these risks largely rely on implicit alignment through training or prompting,...
We present SoundPlot, an open-source framework for analyzing avian vocalizations through acoustic feature extraction, dimensionality reduction, and neural audio synthesis. The system transforms audio signals into a multi-dimensional acoustic feature space, enabling real-time visualization of temporal dynamics in 3D using web-based...
We propose a novel expressivity framework for Graph Neural Networks (GNNs) grounded in Boolean function theory, enabling a fine-grained analysis of their ability to capture complex subpopulation structures. We introduce the notion of \textit{Subpopulation Boolean Isomorphism} (SBI) as an invariant that strictly subsumes existing...
The main contribution of this paper resides in providing novel algorithmic advances and analytical insights for the sequential hiring problem, a recently introduced dynamic optimization model where a firm adaptively fills a limited number of positions from a pool of applicants with known values and acceptance probabilities. While...
Autonomous driving relies on accurate perception to ensure safe driving. Collaborative perception improves accuracy by mitigating the sensing limitations of individual vehicles, such as limited perception range and occlusion-induced blind spots. However, collaborative perception often suffers from high communication overhead due to...