Knowledge catalogue
arXiv:2607.25357v1 Announce Type: cross Abstract: Long-context recall in linear-time sequence models highlights a tradeoff in how they write to memory. State-based linear models, such as state-space m
arXiv:2607.26043v1 Announce Type: new Abstract: Enhancing classification performance in mammography remains a persistent challenge across both small curated datasets and large-scale clinical cohorts.
arXiv:2607.25455v1 Announce Type: new Abstract: When it comes to the proper classification of ancient coins with respect to their time and issuer, the textual inscriptions on these coins, also known a
arXiv:2505.02271v2 Announce Type: replace Abstract: The proliferation of Generative Artificial Ingelligence (AI), especially Large Language Models, presents transformative opportunities for urban appl
arXiv:2607.24771v1 Announce Type: new Abstract: Knowledge injection updates pretrained MLLMs with new factual or domain-specific knowledge, but fitting full authoritative answers can cause drift in no
arXiv:2607.25448v1 Announce Type: new Abstract: Zero-shot ObjectNav methods increasingly use vision-language priors, but direct object-object similarity in the latent space is often a weak proxy for s
arXiv:2607.25422v1 Announce Type: new Abstract: Knowledge-intensive multimodal question answering (KI-MMQA) sits at the intersection of three expensive primitives: long visual token sequences, dense r
arXiv:2607.25135v1 Announce Type: new Abstract: Recent advances in RAG aim to optimize for performance by paying high ingestion costs for knowledge ingestion: building knowledge graphs or extracting S
arXiv:2607.25984v1 Announce Type: new Abstract: Predicting how a scene may evolve from partial observations requires reasoning about multiple possible futures rather than committing to a single trajec
arXiv:2607.24803v1 Announce Type: cross Abstract: Scientific claims often spread on social media faster than they can be verified, while posts rarely link to the original scholarly sources. To tackle
arXiv:2607.25119v1 Announce Type: new Abstract: We propose a score-based stabilization framework for numerical simulation of partial differential equations, in which a learned score model defines a st
arXiv:2607.25467v1 Announce Type: cross Abstract: Stateful multimodal assistants encode an image once but may answer questions about it many turns later. Attention-guided visual-KV eviction assumes th
arXiv:2607.24796v1 Announce Type: cross Abstract: Parkinson's disease (PD) affects multiple, dissociable stages of motor and cognitive control. We ask whether passively-collected keystroke dynamics ca
arXiv:2607.25122v1 Announce Type: new Abstract: Search Trajectory Networks (STNs) are a graph-based tool for visualizing and characterizing the behavior of optimization algorithms. STNs' reliance on d
arXiv:2607.25818v1 Announce Type: new Abstract: Recent multimodal large language models (MLLMs), such as Qwen2.5-VL and InternVL3, generate large numbers of vision tokens for high-resolution inputs, l
arXiv:2605.05811v2 Announce Type: replace Abstract: Workbook-scale spreadsheet understanding is increasingly important for language-model-based data analysis agents, but remains challenging because re
arXiv:2607.24953v1 Announce Type: cross Abstract: Reducing training precision is a key lever for improving the e ciency of large language model (LLM) training, but pushing beyond FP8 to 4-bit oating p
arXiv:2607.24777v1 Announce Type: new Abstract: Architected metamaterials derive their functions from structure, creating vast opportunities to program physical responses through topology design. Howe
arXiv:2607.25880v1 Announce Type: cross Abstract: LLM provenance testing asks whether a suspect LLM belongs to the same lineage as a source. Existing black-box methods largely infer this relationship
arXiv:2607.24827v1 Announce Type: cross Abstract: We prove two lower bounds for the first order oracle complexity of minimizing a d-dimensional 1-Lipschitz convex function over the unit ball with m bi
arXiv:2607.24767v1 Announce Type: cross Abstract: Retrieval-Augmented Generation (RAG) systems have emerged as a powerful process for allowing large language models (LLMs) to retrieve relevant informa
arXiv:2607.25894v1 Announce Type: new Abstract: Recent diffusion models have achieved remarkable realism in facial image synthesis, posing growing challenges to artificial intelligence-generated conte
arXiv:2412.18756v2 Announce Type: replace Abstract: A primary advantage of neural networks lies in their feature learning characteristics, which is challenging to theoretically analyze due to the comp
arXiv:2509.06924v3 Announce Type: replace Abstract: Neutron reflectometry (NR) is a key enabling technology for many areas of scientific development. Although the forward reflectivity model is well-kn
arXiv:2607.25393v1 Announce Type: new Abstract: Histopathological examination primarily relies on hematoxylin and eosin (H&E) and immunohistochemistry (IHC) staining. Although IHC provides critical mo
arXiv:2607.25798v1 Announce Type: new Abstract: An often overlooked factor of robot manipulation performance is the embodiment of the robot itself. Motivated by this problem, we study motion-condition
arXiv:2607.25471v1 Announce Type: new Abstract: Graph Neural Networks (GNNs) and Large Language Models (LLMs) have each advanced recommendation systems by modeling structural and semantic signals, res
Everyone is talking about Kimi K3, but if you jump straight into the technical report, you’ll quickly realize it’s standing on years of research -- just like any breakthrough is! If you want to unders
arXiv:2607.24783v1 Announce Type: new Abstract: Job understanding is critical to LinkedIn's mission of connecting talent with opportunity. This task involves transforming unstructured and noisy job po
arXiv:2607.14137v2 Announce Type: cross Abstract: To answer a question about a program, move the program to where the question is decidable. Every such move is a translation, and every translation is
arXiv:2607.25870v1 Announce Type: cross Abstract: Voice activity detection (VAD) triggers downstream speech processing in always-on systems under strict memory, latency, and compute constraints. Recen
arXiv:2510.09733v2 Announce Type: replace Abstract: Visual Retrieval-Augmented Generation (VRAG) has emerged as a promising paradigm for equipping Vision-Language Models (VLMs) with external visual ev
arXiv:2607.25537v1 Announce Type: cross Abstract: In the age of foundation models, a model is only as good as its prompt. For this reason, prompt engineering has become an essential technique for impr
arXiv:2607.25234v1 Announce Type: new Abstract: Stereo depth estimation for driving, robotics and augmented reality must run at high resolution under tight latency budgets, yet in transformer-based ma
arXiv:2607.26037v1 Announce Type: new Abstract: We present Wonder, a general-purpose video world model for real-time, camera-controllable world exploration. Given an image or a conditional video, Wond
arXiv:2607.25298v1 Announce Type: new Abstract: The high proportion of wind power connected to the grid places higher demands on fine-grained knowledge of regional wind fields. Since the wind informat
arXiv:2607.22740v1 Announce Type: new Abstract: Weakly supervised pipelines for medical imaging have become increasingly popular over the years. These systems often include multiple stages and compone
arXiv:2607.22567v1 Announce Type: cross Abstract: Zeroth-order Newton-type methods are useful when gradients and Hessians are unavailable, but they behave quite differently from first-order gradient-f
arXiv:2601.09624v2 Announce Type: replace-cross Abstract: Machine unlearning is becoming essential for building trustworthy and compliant language models. Yet unlearning success varies considerably ac
arXiv:2607.24525v1 Announce Type: cross Abstract: Automated solar filament detection using deep learning faces several challenges. Semantic segmentation of solar filaments is a complicated multiscale
arXiv:2607.22722v1 Announce Type: cross Abstract: Almost all adversarial attacks add an imperceptible perturbation to fool a model. We instead study the opposite: a large, clearly visible perturbation
arXiv:2607.24317v1 Announce Type: new Abstract: The dynamics of a holonomically constrained rigid body can be modeled by Newton-Euler equations subjected to geometric constraints. This is frequently f
arXiv:2607.23321v1 Announce Type: cross Abstract: Evaluating camera image signal processing (ISP) pipelines requires measuring low-level artifacts introduced by operations such as denoising, demosaici
arXiv:2607.24024v1 Announce Type: new Abstract: Stereo matching and surface normal estimation are fundamental tasks in 3D vision. However, existing feed-forward stereo methods still struggle to produc
Across eight case studies spanning industry and academia, we explore what this shift means for scientific computing—and why human verification, stewardship, and long-term maintenance matter. https://o
arXiv:2607.23602v1 Announce Type: cross Abstract: Controllers based on sampling and latent world models assign a predicted terminal cost to each candidate action sequence, choose the minimum, execute
arXiv:2607.23040v1 Announce Type: cross Abstract: This work proposes an actuator-aware spatiotemporal tube (STT) synthesis framework to accomplish temporal reach-avoid-stay (T-RAS) tasks for an unknow
arXiv:2607.23058v1 Announce Type: cross Abstract: Multilingual reasoning evaluation overwhelmingly relies on translating English benchmarks, a practice that introduces linguistic artifacts and fails t
arXiv:2607.22891v1 Announce Type: new Abstract: Medical image segmentation is a fundamental task in computer-aided diagnosis, yet it remains challenging due to the complexity of anatomical structures
arXiv:2607.22746v1 Announce Type: cross Abstract: Rapid post-disaster response requires timely, building-level information on whether structures remain intact, are damaged, or are destroyed. Post-even
arXiv:2607.23882v1 Announce Type: new Abstract: Modern System-on-Chip (SoCs) often contain hundreds of millions to tens of billions of gates, making existing Hardware Trojan (HT) detection methods imp
arXiv:2607.23002v1 Announce Type: cross Abstract: Large language models increasingly write both code and the tests meant to check it; coverage records what ran, not what was verified. We study an adve
arXiv:2602.16579v2 Announce Type: replace-cross Abstract: Reliable global streamflow forecasting is essential for flood preparedness and water resource management, yet data-driven models often suffer
arXiv:2606.13811v2 Announce Type: replace-cross Abstract: Can Large Language Models (LLMs) understand and reason about quantum operators? Despite their remarkable capabilities in mathematics and symbo
arXiv:2607.23026v1 Announce Type: cross Abstract: Mean-field games (MFGs) offer a unifying lens on continuous-time generative modeling: a cost tuple recovering twelve prominent models---Continuous Nor
arXiv:2607.24384v1 Announce Type: new Abstract: Electric joint systems are significant elements of an underwater manipulator for its actuation, drive, and control. Working in an underwater environment
arXiv:2607.22934v1 Announce Type: cross Abstract: Learning causal graphs from interventional data is a challenging problem with broad applications. In molecular biology, for example, a central goal is
arXiv:2607.23486v1 Announce Type: new Abstract: Dissolved gas analysis (DGA) is crucial for diagnosing early power transformer failures. Traditional DGA interpretation methods like Duval Triangle, IEC
arXiv:2603.07841v2 Announce Type: replace Abstract: Recent advances in large language models have strengthened Text2SQL systems that translate natural language questions into database queries. A persi
arXiv:2607.23675v1 Announce Type: cross Abstract: The embedding of word sequences into continuous vector spaces has been one of the most important developments in Natural Language Processing in the re