Knowledge catalogue
arXiv:2605.09190v1 Announce Type: new Abstract: We present AQMP, a novel image codec combining Adaptive Quadtree Refinement with Matching Pursuit. Unlike conventional Matching Pursuit methods that ope
arXiv:2603.10126v2 Announce Type: replace-cross Abstract: We propose a standalone autoregressive (AR) Action Expert that generates actions as a continuous causal sequence while conditioning on refresh
arXiv:2605.10107v1 Announce Type: new Abstract: Assertion-based Verification (ABV) is essential for ensuring that hardware designs conform to their intended specifications. However, existing automated
arXiv:2605.08853v1 Announce Type: new Abstract: Mechanistic interpretability assumes that circuit analysis becomes harder as models scale. We challenge this assumption by showing that the attention ar
arXiv:2502.09891v4 Announce Type: replace-cross Abstract: Retrieval-Augmented Generation (RAG) has proven effective in integrating external knowledge into large language models (LLMs) for solving ques
arXiv:2512.15977v3 Announce Type: replace Abstract: Vision-language models (VLMs) are increasingly proposed as general-purpose solutions for visual recognition tasks, yet their reliability for agricul
arXiv:2504.19451v3 Announce Type: cross Abstract: This paper presents two concrete applications of Artificial Intelligence to algorithmic and analytic number theory. Recent benchmarks of large languag
arXiv:2605.09659v1 Announce Type: new Abstract: Koopman operator theory provides a powerful framework for representing nonlinear dynamics through a linear operator acting on lifted observables, enabli
arXiv:2605.10480v1 Announce Type: new Abstract: Over the years, research in system identification has provided a rich set of methods for learning dynamical models, together with well-established theor
arXiv:2605.10876v1 Announce Type: cross Abstract: Recent advances in machine learning and large-scale biological data collections have revived the prospect of building a virtual cell, a computational
arXiv:2605.08831v1 Announce Type: new Abstract: In flexible assembly systems, existing task planning methods require a time-consuming configuration process by multiple experts to establish a productio
arXiv:2510.13397v3 Announce Type: replace Abstract: Dropout is common in clinical studies, with up to half of patients leaving early due to side effects or other reasons. When dropout is informative (
arXiv:2508.13813v2 Announce Type: replace-cross Abstract: As AI systems increasingly rely on training data, assessing dataset trustworthiness has become critical, particularly for properties like fair
arXiv:2605.09533v1 Announce Type: cross Abstract: Large Language Models (LLMs) are increasingly employed in enterprise question-answering (QA) systems, requiring adaptation to domain-specific knowledg
arXiv:2605.10168v1 Announce Type: new Abstract: Document-based question answering (QA) increasingly includes abstract questions that require synthesizing scattered information from long documents or a
arXiv:2603.11969v2 Announce Type: replace Abstract: Image-based surface reconstruction and characterization are crucial for missions to small celestial bodies (e.g., asteroids), as it informs mission
arXiv:2605.08612v1 Announce Type: new Abstract: Addressing the escalating security vulnerabilities in Vision-Language-Action (VLA) models, this study investigates backdoor attacks targeting the visual
arXiv:2605.09425v1 Announce Type: cross Abstract: Recent conditional image generation methods can improve controllability by generating images that are faithful to conditions such as sketches, human p
arXiv:2605.08679v1 Announce Type: cross Abstract: Graph neural networks (GNNs) aim to learn well-trained representations in a lower-dimension space for downstream tasks while preserving the topologica
arXiv:2605.09992v1 Announce Type: cross Abstract: Speculative decoding accelerates LLM inference by drafting future tokens with a small model, but drafter models degrade sharply under template perturb
arXiv:2511.13415v2 Announce Type: replace-cross Abstract: Visual document retrieval requires understanding heterogeneous and multi-modal content to satisfy implicit information needs. Recent advances
arXiv:2605.09644v1 Announce Type: new Abstract: Visual Geometry Grounded Transformer (VGGT) advances 3D reconstruction via scalable Transformer architecture, but the quadratic complexity of global att
arXiv:2402.02286v4 Announce Type: replace-cross Abstract: U-shaped architectures have long dominated the field of medical image segmentation, while Transformers are widely employed for modeling long-r
arXiv:2605.09313v1 Announce Type: new Abstract: Attention sinks -- tokens that receive disproportionate attention mass -- are assumed to be functionally important in autoregressive language models, bu
arXiv:2605.10871v1 Announce Type: cross Abstract: This work proposes Attractor-Vascular Coupling Theory (AVCT), a mathematical framework showing that cardiac attractor geometry encodes blood pressure
arXiv:2605.09780v1 Announce Type: new Abstract: Attribution techniques explain the outcome of an AI model by assigning a numerical score to its inputs. So far, these techniques have mainly focused on
arXiv:2509.08031v3 Announce Type: replace-cross Abstract: Large Audio Language Models (LALMs) are rapidly advancing, but evaluating them remains challenging due to inefficient and non-standardized too
arXiv:2604.02151v2 Announce Type: replace Abstract: We consider multi-objective reinforcement learning problems where objectives come from an identical family -- such as the class of reachability obje
arXiv:2511.14045v2 Announce Type: replace-cross Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) has become a core training stage in recent large language models (LLMs). Its reliance on
arXiv:2605.08172v1 Announce Type: new Abstract: Anatomical mesh segmentation requires models that operate directly on irregular surface geometry while remaining robust to arbitrary patient pose and me
arXiv:2602.09534v2 Announce Type: replace Abstract: Realistic talking-head video generation is critical for virtual avatars, film production, and interactive systems. Current methods struggle with nua
arXiv:2605.08354v1 Announce Type: new Abstract: Aligning multimodal generative models with human preferences demands reward signals that respect the compositional, multi-dimensional structure of human
In this post, we'll show you how our multi-document discovery feature solves this problem. It serves as an automated pre-processing step, analyzing unknown documents, clustering them by type, and gene
arXiv:2605.10169v1 Announce Type: new Abstract: Reachability games are two-player games played on a graph, where the objective of exttt{REACH} player is to reach the target set whereas the objective o
arXiv:2409.19379v2 Announce Type: replace-cross Abstract: TxGraffiti is a data-driven, heuristic-based computer program developed to automate the process of generating conjectures across various mathe
arXiv:2605.10464v1 Announce Type: new Abstract: Zebrafish embryos are a valuable model for drug discovery due to their optical transparency and genetic similarity to humans. However, current evaluatio
arXiv:2605.10449v1 Announce Type: new Abstract: Quantifying fish community structure is essential for understanding biodiversity and ecosystem responses in a changing environment, yet existing survey
arXiv:2605.09050v1 Announce Type: cross Abstract: Monitoring moisture level of land in a large-scale plantation is tedious. The main objective of this project is to use a robotic kit in collaboration
arXiv:2602.10356v2 Announce Type: replace Abstract: Real-world digital environments are highly diverse and dynamic. These characteristics cause agents to frequently encounter unseen environments and d
arXiv:2605.10370v1 Announce Type: new Abstract: Scientific knowledge on the Web is published as passive assertions and cannot decide when to validate evidence, reconcile contradictions, or update conf
AutoScout24, a leading European online automotive marketplace, implemented AI-powered workflows to optimize and scale their engineering operations. The implementation likely leveraged OpenAI's technol
Amazon Web Services Inc. is trying to get rid of the bottleneck between architectural planning and code execution with a number of upgrades to its artificial intelligence software development tool Kir
arXiv:2605.10455v1 Announce Type: new Abstract: Short-term ocean forecast skill depends strongly on the three-dimensional ocean structure of the upper ocean, which governs stratification, subsurface h
Build b9114 introduces a NCCL-free AllReduce implementation for tensor-parallel inference that pipelines device-to-host copy, cross-GPU communication, and reduction in a single CUDA kernel. The releas
Build b9119 of llama.cpp introduces CUDA optimizations including an NCCL-free AllReduce implementation for tensor-parallel inference and updates to the llama-bench tool for managing reduction provider
Release b9122 of llama.cpp addresses precision issues for multimodal models through ggml-webgpu, including fixes for GELU functions, flash attention tile implementations, and type conflict resolution.
b9123 is a release of llama.cpp created on May 12, 2026 . llama.cpp is an open source software library that performs inference on various large language models such as Llama , providing LLM inference
B9124 is a build release from the llama.cpp project, created on May 12, 2026 . Llama.cpp is an open source software library that performs inference on various large language models such as Llama, deve
arXiv:2605.10845v1 Announce Type: cross Abstract: As global cross-lingual communication intensifies, language barriers in visually rich documents such as PDFs remain a practical bottleneck. Existing d
arXiv:2605.10170v1 Announce Type: new Abstract: Urban traffic congestion presents a significant challenge for modern cities, which impacts mobility and sustainability. Traditional traffic light contro
arXiv:2605.08110v1 Announce Type: cross Abstract: Low-Rank Adaptation (LoRA) has become the standard for fine-tuning large pre-trained models at reduced computational cost. However, its low-rank point
arXiv:2605.08214v1 Announce Type: cross Abstract: Automatic Speech Recognition (ASR) and speaker diarization in Bangla remain challenging due to long form recordings, diverse acoustic conditions, and
arXiv:2601.03042v4 Announce Type: replace Abstract: Reliable confidence is essential for trusting the outputs of LLMs, yet widely deployed post-trained LLMs (PoLLMs) typically compromise this trust wi
arXiv:2510.09877v3 Announce Type: replace-cross Abstract: Over the past couple of decades, many active learning acquisition functions have been proposed, leaving practitioners with an unclear choice o
arXiv:2601.02950v3 Announce Type: replace Abstract: Current Large Language Model reasoning systems process queries independently, discarding valuable cross-instance signals such as shared reasoning pa
arXiv:2605.10174v1 Announce Type: new Abstract: Through-water photogrammetry based on UAV imagery enables shallow-water bathymetry, but refraction at the air-water interface violates the straight-ray
arXiv:2605.09775v1 Announce Type: new Abstract: Bayesian optimization (BO) is an efficient framework for optimizing expensive black-box functions. However, it is typically formulated as learning an en
arXiv:2308.13222v3 Announce Type: replace-cross Abstract: We introduce an evidence-driven Bayesian formulation of physics-informed neural networks that enables automatic optimization of loss weights b
arXiv:2605.10655v1 Announce Type: new Abstract: Trellis-coded quantization sets the current 2-bit post-training frontier for LLMs (QTIP), but pushing below the PTQ ceiling requires quantization-aware
arXiv:2605.09662v1 Announce Type: new Abstract: Most Gaussian Splatting techniques that provide a 3D semantic representation of the scene do not optimize the underlying 3D geometry, making object-leve