Stay updated with the latest research and technology news
arXiv:2512.02002v3 Announce Type: replace Abstract: Recent advances in Large language models (LLMs) have demonstrated their promising capabilities of generating robot operation code to enable LLM-driven...
arXiv:2512.03005v4 Announce Type: replace Abstract: The rapid advancement of large language models (LLMs) has opened new possibilities for AI for good applications. As LLMs increasingly...
arXiv:2512.07352v2 Announce Type: replace Abstract: Existing speech anti-spoofing benchmarks rely on a narrow set of public models, creating a substantial gap from real-world scenarios in...
arXiv:2512.08910v3 Announce Type: replace Abstract: In empirical software engineering (SE) research, researchers have considerable freedom to decide how to process data, what operationalizations to use,...
arXiv:2512.09435v2 Announce Type: replace Abstract: Part-level 3D generation is essential for applications requiring decomposable and structured 3D synthesis. However, existing methods either rely on implicit...
arXiv:2512.16602v3 Announce Type: replace Abstract: We introduce Refusal Steering, an inference-time method to exercise fine-grained control over Large Language Models refusal behaviour on politically sensitive...
arXiv:2512.18337v2 Announce Type: replace Abstract: The rapid development of large language model (LLM)-based agents has unlocked new possibilities for autonomous multi-turn reasoning and tool-augmented decision-making....
arXiv:2512.20340v2 Announce Type: replace Abstract: Although diffusion transformer (DiT)-based video virtual try-on (VVT) has made significant progress in synthesizing realistic videos, existing methods still struggle...
arXiv:2512.23447v2 Announce Type: replace Abstract: Mixture-of-Experts (MoE) models lack explicit constraints to ensure the router's decisions align well with the experts' capabilities, which ultimately limits...
arXiv:2512.23502v2 Announce Type: replace Abstract: Radio Access Network (RAN) slicing enables multiple logical networks to exist on top of the same physical infrastructure by allocating...
arXiv:2512.24787v2 Announce Type: replace Abstract: Slate recommendation, which presents users with a ranked item list in a single display, is ubiquitous across mainstream online platforms....
arXiv:2601.00548v2 Announce Type: replace Abstract: This paper presents a decentralized control framework for distribution matching in multi-agent systems (MAS), where agents collectively achieve a prescribed...
arXiv:2601.01874v3 Announce Type: replace Abstract: Despite significant progress, multimodal large language models continue to struggle with visual mathematical problem solving. Some recent works recognize that...
arXiv:2601.03868v2 Announce Type: replace Abstract: This paper presents a comprehensive empirical study on the safety alignment capabilities. We evaluate what matters for safety alignment in...
arXiv:2601.08194v2 Announce Type: replace Abstract: Conversational agents are increasingly expected to adapt across contexts and evolve their personalities through interactions, yet most remain static once...
arXiv:2601.09708v2 Announce Type: replace Abstract: Vision-Language-Action (VLA) tasks require reasoning over complex visual scenes and executing adaptive actions in dynamic environments. While recent studies on...
arXiv:2601.11283v2 Announce Type: replace Abstract: Attention Deficit Hyperactivity Disorder (ADHD) is a prevalent neurodevelopmental disorder with limited objective diagnostic tools, highlighting the urgent need for...
arXiv:2601.11675v3 Announce Type: replace Abstract: Human vision combines low-resolution "gist" information from the visual periphery with sparse but high-resolution information from fixated locations to construct...
arXiv:2601.12149v2 Announce Type: replace Abstract: Terahertz (THz) systems inherently introduce frequency-dependent degradation effects, resulting in low-frequency blurring and high-frequency noise in amplitude images. Conventional image...
arXiv:2601.13134v2 Announce Type: replace Abstract: Geospatial Foundation Models (GFMs) provide powerful representations, but high compute costs hinder their widespread use. Pre-computed embedding data products offer...
arXiv:2601.13270v2 Announce Type: replace Abstract: Bayesian networks are a canonical formalism for representing probabilistic dependencies, yet their integration within logic programming frameworks remains a nontrivial...
arXiv:2601.15571v3 Announce Type: replace Abstract: We study physical information sufficiency as a decision-theoretic meta-problem. For $\mathcal{D}=(A,S,U)$ with factored state space $S=X_1\times\cdots\times X_n$, a coordinate set...
arXiv:2601.16522v2 Announce Type: replace Abstract: Phase-field simulations are a practical but also expensive tool to calculate microstructural evolution. This work aims to compare explicit time...
arXiv:2601.16694v2 Announce Type: replace Abstract: In skeleton-based human activity understanding, existing methods often adopt the contrastive learning paradigm to construct a discriminative feature space. However,...