Stay updated with the latest research and technology news
arXiv:2602.20323v2 Announce Type: replace Abstract: Reliable object manipulation requires understanding physical properties that vary across objects and environments. Vision-language model (VLM) planners can reason about...
arXiv:2602.20541v3 Announce Type: replace Abstract: We study the problem of fairly allocating indivisible goods when limited sharing is allowed, that is, each good may be...
arXiv:2602.20833v5 Announce Type: replace Abstract: We introduce DRESS, a deterministic, parameter-free framework that iteratively refines the structural similarity of edges in a graph to produce...
arXiv:2602.20880v3 Announce Type: replace Abstract: Text-to-Image (T2I) diffusion models have demonstrated significant advancements in generating high-quality images, while raising potential safety concerns regarding harmful content...
arXiv:2602.21100v2 Announce Type: replace Abstract: Reconstructing high-fidelity 3D head geometry from images is critical for a wide range of applications, yet existing methods face fundamental...
arXiv:2602.21395v2 Announce Type: replace Abstract: Multimodal learning that integrates genomics and histopathology has shown strong potential in cancer diagnosis, yet its clinical translation is hindered...
arXiv:2602.21473v2 Announce Type: replace Abstract: A key challenge in translating Visual Place Recognition (VPR) from the lab to long-term deployment is ensuring a priori that...
arXiv:2602.21996v2 Announce Type: replace Abstract: Numerical simulations of contaminant dispersion, as after a gas leakage incident on a chemical plant, can provide valuable insights for...
arXiv:2602.22056v2 Announce Type: replace Abstract: Generative manipulation policies can fail catastrophically under deployment-time distribution shift, yet many failures are near-misses: the robot reaches almost-correct poses...
arXiv:2602.22134v2 Announce Type: replace Abstract: Semantic communication (SemCom) redefines wireless communication from reproducing symbols to transmitting task-relevant semantics. However, this AI-native architecture also introduces new...
arXiv:2602.22227v3 Announce Type: replace Abstract: Despite their impressive capabilities, Multimodal Large Language Models (MLLMs) exhibit perceptual fragility when confronted with visually complex scenes. This weakness...
arXiv:2602.22469v2 Announce Type: replace Abstract: Vision-Language Models (VLMs) often hallucinate objects that are not present in the input image. We identify a contributing cause of...
arXiv:2602.22730v2 Announce Type: replace Abstract: This paper introduces a novel Czech dataset in the restaurant domain for aspect-based sentiment analysis (ABSA), enriched with annotations of...
arXiv:2602.22769v2 Announce Type: replace Abstract: Large Language Models (LLMs) are deployed as autonomous agents in increasingly complex applications, where enabling long-horizon memory is critical for...
arXiv:2602.23530v2 Announce Type: replace Abstract: Large-scale e-commerce search must surface a broad set of items from a vast catalog, ranging from bestselling products to new,...
arXiv:2602.23541v2 Announce Type: replace Abstract: Previous work establishing completeness results for counterfactual identification has been circumscribed to the setting where the input data belongs to...
arXiv:2602.24065v2 Announce Type: replace Abstract: Recent advancements in neural surface reconstruction have significantly enhanced 3D reconstruction. However, current real world datasets mainly focus on benchmarking...
arXiv:2603.00183v2 Announce Type: replace Abstract: Context: Test case prioritization (TCP) is a technique widely used by software development organizations to accelerate regression testing. Objectives: We...
arXiv:2603.00251v2 Announce Type: replace Abstract: Modern engineering design platforms excel at discipline-specific tasks such as CAD, CAM, and CAE, but often lack native systems engineering...
arXiv:2603.00399v2 Announce Type: replace Abstract: Charting the intellectual evolution of a scientific discipline is crucial for identifying its core contributions, challenges, and future directions. The...
arXiv:2603.00542v2 Announce Type: replace Abstract: In real-world vision systems,haze removal is required not only to enhance image visibility but also to meet the specific needs...
arXiv:2603.00610v2 Announce Type: replace Abstract: While music generation models have evolved to handle complex multimodal inputs mixing text, lyrics, and reference audio, evaluation mechanisms have...
arXiv:2603.00766v2 Announce Type: replace Abstract: A black hole is a malicious node in a graph that destroys resources entering into it without leaving any trace....
arXiv:2603.00884v2 Announce Type: replace Abstract: Optical Character Recognition (OCR) is a critical but error-prone stage in digital humanities text pipelines. While OCR correction improves usability...