Stay updated with the latest research and technology news
arXiv:2602.11745v1 Announce Type: new Abstract: Graph models are fundamental to data analysis in domains rich with complex relationships. Text-to-Graph-Query-Language (Text-to-GQL) systems act as a translator,...
arXiv:2602.11743v1 Announce Type: new Abstract: Mainstream Test-Time Adaptation (TTA) methods for adapting vision-language models, e.g., CLIP, typically rely on Shannon Entropy (SE) at test time...
arXiv:2602.11741v1 Announce Type: new Abstract: Designing a rate limiter that is simultaneously accurate, available, and scalable presents a fundamental challenge in distributed systems, primarily due...
arXiv:2602.11740v1 Announce Type: new Abstract: Efficient exploration is critical for multiagent systems to discover coordinated strategies, particularly in open-ended domains such as search and rescue...
arXiv:2602.11738v1 Announce Type: new Abstract: Probabilistic forecasting of irregularly sampled time series is crucial in domains such as healthcare and finance, yet it remains a...
arXiv:2602.11737v1 Announce Type: new Abstract: We study object hallucination in Multimodal Large Language Models (MLLMs) and improve visual contrastive decoding (VCD) by constructing an object-aligned...
arXiv:2602.11735v1 Announce Type: new Abstract: Cooperative path planning for heterogeneous UAV swarms poses significant challenges for Multi-Agent Reinforcement Learning (MARL), particularly in handling asymmetric inter-agent...
arXiv:2602.11733v1 Announce Type: new Abstract: E-commerce product understanding demands by nature, strong multimodal comprehension from text, images, and structured attributes. General-purpose Vision-Language Models (VLMs) enable...
arXiv:2602.11732v1 Announce Type: new Abstract: We study the fundamental problem of fairly dividing a set of indivisible goods among agents with additive valuations. Here, envy-freeness...
arXiv:2602.11731v1 Announce Type: new Abstract: Existing multimodal large language models have achieved high-fidelity visual perception and exploratory visual generation. However, a precision paradox persists in...
arXiv:2602.11730v1 Announce Type: new Abstract: In vision-language models (VLMs), misalignment between textual descriptions and visual coordinates often induces hallucinations. This issue becomes particularly severe in...
arXiv:2602.11729v1 Announce Type: new Abstract: Model diffing, the process of comparing models' internal representations to identify their differences, is a promising approach for uncovering safety-critical...
arXiv:2602.11726v1 Announce Type: new Abstract: Parameter-efficient fine-tuning (PEFT) methods such as \lora{} adapt large pretrained models by adding small weight-space updates. While effective, weight deltas...
arXiv:2602.11724v1 Announce Type: new Abstract: Visual language model (VLM) agents show great promise in automating end-to-end (E2E) web testing against requirements in natural language. However,...
arXiv:2602.11719v1 Announce Type: new Abstract: Generative Recommendation has emerged as a transformative paradigm, reformulating recommendation as an end-to-end autoregressive sequence generation task. Despite its promise,...
arXiv:2602.11717v1 Announce Type: new Abstract: Model merging has emerged as a promising paradigm for composing the capabilities of large language models by directly operating in...
arXiv:2602.11716v1 Announce Type: new Abstract: In 2015, Kawarabayashi and Kreutzer proved the Directed Grid Theorem - the generalisation of the well-known Excluded Grid Theorem to...
arXiv:2602.11715v1 Announce Type: new Abstract: Diffusion large language models (dLLMs) have emerged as a compelling alternative to autoregressive (AR) LLMs, owing to their capacity for...
arXiv:2602.11714v1 Announce Type: new Abstract: We propose GSO-SLAM, a real-time monocular dense SLAM system that leverages Gaussian scene representation. Unlike existing methods that couple tracking...
arXiv:2602.11712v1 Announce Type: new Abstract: We introduce potential-energy gating, a method for robust state estimation in systems governed by double-well stochastic dynamics. The observation noise...
arXiv:2602.11710v1 Announce Type: new Abstract: This paper introduces the notion of affective extended reality (XR) to characterise XR systems that use biodata to enable understanding...
arXiv:2602.11708v1 Announce Type: new Abstract: Cryptocurrency markets exhibit pronounced momentum effects and regime-dependent volatility, presenting both opportunities and challenges for systematic trading strategies. We propose...
arXiv:2602.11707v1 Announce Type: new Abstract: As geopolitical, organizational, and technological fragmentation deepens, resilient digital collaboration becomes imperative. This paper develops a spectrum framework of polycentric...
arXiv:2602.11706v1 Announce Type: new Abstract: Procedural generation techniques in 3D rendering engines have revolutionized the creation of complex environments, reducing reliance on manual design. Recent...