Stay updated with the latest research and technology news
arXiv:2602.05192v1 Announce Type: new Abstract: To assess the ability of current AI systems to correctly answer research-level mathematics questions, we share a set of ten...
arXiv:2602.05193v1 Announce Type: new Abstract: A pangenome captures the genetic diversity across multiple individuals simultaneously, providing a more comprehensive reference for genome analysis than a...
arXiv:2602.05195v1 Announce Type: new Abstract: Retrieval-augmented generation (RAG) promises grounded question answering, yet domain settings with multiple heterogeneous knowledge bases (KBs) remain challenging. In Chinese...
arXiv:2602.05198v1 Announce Type: new Abstract: Environmental monitoring robots often need to reconstruct spatial fields (e.g., salinity, temperature, bathymetry) under tight distance and energy constraints. Classical...
arXiv:2602.05200v1 Announce Type: new Abstract: A growing suite of research illustrates the negative impact of social media bots in amplifying harmful information with widespread social...
arXiv:2602.05202v1 Announce Type: new Abstract: Aligning video generative models with human preferences remains challenging: current approaches rely on Vision-Language Models (VLMs) for reward modeling, but...
arXiv:2602.05204v1 Announce Type: new Abstract: Accurate forecasting of extreme weather events such as heavy rainfall or storms is critical for risk management and disaster mitigation....
arXiv:2602.05205v1 Announce Type: new Abstract: Most services built on powerful large-scale language models (LLMs) add citations to their output to enhance credibility. Recent research has...
arXiv:2602.05211v1 Announce Type: new Abstract: The academia and industry are characterized by a reciprocal shaping and dynamic feedback mechanism. Despite distinct institutional logics, they have...
arXiv:2602.05213v1 Announce Type: new Abstract: While recent neural codecs achieve strong performance at low bitrates when optimized for perceptual quality, their effectiveness deteriorates significantly under...
arXiv:2602.05214v1 Announce Type: new Abstract: Disentangled representation learning aims to capture the underlying explanatory factors of observed data, enabling a principled understanding of the data-generating...
arXiv:2602.05215v1 Announce Type: new Abstract: Despite recent advances in Video Large Language Models (Vid-LLMs), Temporal Video Grounding (TVG), which aims to precisely localize time segments...
arXiv:2602.05216v1 Announce Type: new Abstract: Searching for mathematical results remains difficult: most existing tools retrieve entire papers, while mathematicians and theorem-proving agents often seek a...
arXiv:2602.05217v1 Announce Type: new Abstract: Cross-Domain Few-Shot Segmentation aims to segment categories in data-scarce domains conditioned on a few exemplars. Typical methods first establish few-shot...
arXiv:2602.05218v1 Announce Type: new Abstract: Motivated by the success of the Segment Anything Model (SAM) in promptable segmentation, recent studies leverage SAM to develop training-free...
arXiv:2602.05219v1 Announce Type: new Abstract: We study differentially private prediction introduced by Dwork and Feldman (COLT 2018): an algorithm receives one labeled sample set $S$...
arXiv:2602.05220v1 Announce Type: new Abstract: Current audio foundation models typically rely on rigid, task-specific supervision, addressing isolated factors of audio rather than the whole. In...
arXiv:2602.05228v1 Announce Type: new Abstract: Harmful fine-tuning can invalidate safety alignment of large language models, exposing significant safety risks. In this paper, we utilize the...
arXiv:2602.05230v1 Announce Type: new Abstract: Linear attention methods offer Transformers $O(N)$ complexity but typically underperform standard softmax attention. We identify two fundamental limitations affecting these...
arXiv:2602.05232v1 Announce Type: new Abstract: Graph anomaly detection (GAD) is crucial in applications like fraud detection and cybersecurity. Despite recent advancements using graph neural networks...
arXiv:2602.05233v1 Announce Type: new Abstract: Vision-language-action models have advanced robotic manipulation but remain constrained by reliance on the large, teleoperation-collected datasets dominated by the static,...
arXiv:2602.05234v1 Announce Type: new Abstract: Intervention-based model steering offers a lightweight and interpretable alternative to prompting and fine-tuning. However, by adapting strong optimization objectives from...
arXiv:2602.05235v1 Announce Type: new Abstract: Retrieval-Augmented Generation (RAG) enhances Large Language Models (LLMs) by grounding generation in external knowledge to improve factuality and reduce hallucinations....
arXiv:2602.05238v1 Announce Type: new Abstract: Die casting plays a crucial role across various industries due to its ability to craft intricate shapes with high precision...