Stay updated with the latest research and technology news
arXiv:2602.09534v1 Announce Type: new Abstract: Realistic talking-head video generation is critical for virtual avatars, film production, and interactive systems. Current methods struggle with nuanced emotional...
arXiv:2602.09536v1 Announce Type: new Abstract: Unmanned Aerial Vehicles (UAVs) are crucial for advancing railway communication by offering reliable connectivity, adaptive coverage, and mobile edge services...
arXiv:2602.09538v1 Announce Type: new Abstract: Multi-objective alignment aims to align LLM responses with multiple human preference objectives. Among existing methods, guiding the generation of frozen...
arXiv:2602.09539v1 Announce Type: new Abstract: The factorization of three-dimensional data continues to gain attention due to its relevance in representing and compressing large-scale datasets. The...
arXiv:2602.09540v1 Announce Type: new Abstract: Can large language model agents develop industry-level mobile applications? We introduce \textbf{SWE-Bench Mobile}, a benchmark for evaluating coding agents on...
arXiv:2602.09541v1 Announce Type: new Abstract: Rapid progress in large vision-language models (LVLMs) has achieved unprecedented performance in vision-language tasks. However, due to the strong prior...
arXiv:2602.09543v1 Announce Type: new Abstract: This study delves into the causes and trends of disability-related health burdens across Indian states. Through multiple Disability-Adjusted Life Years...
arXiv:2602.09548v1 Announce Type: new Abstract: Binary Function Similarity (BFS), the problem of determining whether two binary functions originate from the same source code, has been...
arXiv:2602.09551v1 Announce Type: new Abstract: Given two polygonal curves $P$ and $Q$ defined by $n$ and $m$ vertices with $m\leq n$, we show that the...
arXiv:2602.09552v1 Announce Type: new Abstract: Conversational question answering increasingly relies on retrieval-augmented generation (RAG) to ground large language models (LLMs) in external knowledge. Yet, most...
arXiv:2602.09554v1 Announce Type: new Abstract: Industrial domains such as automotive, robotics, and aerospace are rapidly evolving to satisfy the increasing demand for machine-learning-driven Autonomy, Connectivity,...
arXiv:2602.09555v1 Announce Type: new Abstract: Recent advances in block diffusion language models have demonstrated competitive performance and strong scalability on reasoning tasks. However, existing BDLMs...
arXiv:2602.09563v1 Announce Type: new Abstract: Trajectory tracking for microswimmers remains a key challenge in microrobotics, where low-Reynolds-number dynamics make control design particularly complex. In this...
arXiv:2602.09566v1 Announce Type: new Abstract: Deep learning has achieved expert-level performance in automated electrocardiogram (ECG) diagnosis, yet the "black-box" nature of these models hinders their...
arXiv:2602.09569v1 Announce Type: new Abstract: Deep learning has revolutionized modern society but faces growing energy and latency constraints. Deep physical neural networks (PNNs) are interconnected...
arXiv:2602.09570v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly used to access legal information. Yet, their deployment in multilingual legal settings is constrained...
arXiv:2602.09572v1 Announce Type: new Abstract: The purpose of predictive modeling on relational data is to predict future or missing values in a relational database, for...
arXiv:2602.09573v1 Announce Type: new Abstract: We study the reconfiguration of odd matchings of combinatorial graphs. Odd matchings are matchings that cover all but one vertex...
arXiv:2602.09574v1 Announce Type: new Abstract: Tree-search decoding is an effective form of test-time scaling for large language models (LLMs), but real-world deployment imposes a fixed...
arXiv:2602.09576v1 Announce Type: new Abstract: We present a structural classification of constraint satisfaction problems (CSP) described by reflexive complete $2$-edge-coloured graphs. In particular, this classification...
arXiv:2602.09577v1 Announce Type: new Abstract: A finite semifield is a division algebra over a finite field where multiplication is not necessarily associative. We consider here...
arXiv:2602.09578v1 Announce Type: new Abstract: Despite algorithm-level innovations for multi-agent reinforcement learning (MARL), the underlying networked infrastructure for large-scale MARL training remains underexplored. Existing training...
arXiv:2602.09580v1 Announce Type: new Abstract: Real-world fine-tuning of dexterous manipulation policies remains challenging due to limited real-world interaction budgets and highly multimodal action distributions. Diffusion-based...
arXiv:2602.09581v1 Announce Type: new Abstract: Deep generative models that can tractably compute input likelihoods, including normalizing flows, often assign unexpectedly high likelihoods to out-of-distribution (OOD)...