Knowledge catalogue
arXiv:2609.24657v1 Announce Type: cross Abstract: Language models can be adapted by changing the computations applied to individual tokens. Quantum circuits offer one such approach, but evaluating wid
arXiv:2609.22632v1 Announce Type: new Abstract: We study binary classification with abstention under separate class-conditional error constraints, with the objective of minimizing abstention while kee
arXiv:2609.24287v1 Announce Type: new Abstract: Classifier-free guidance (CFG) improves conditional generation in Flow Matching, but strong guidance can distort the generated distribution and reduce d
Yesterday was Grok 4.7 (pelicans) and MiMo v2.6 Flash/Pro (more pelicans). Today Anthropic released Claude Opus 5.5, and around an hour later OpenAI released GPT-6 Sol and GPT-6 Luna. It's going to ta
Claude Opus 5.5 is now available as the Standard effort level in Perplexity Computer. On our WANDR benchmark, it scored 0.610 at $4.13 per task, slightly outperforming Claude Fable 5.1 while costing 6
Claude Opus 5.5, Anthropic's most capable Opus model for agentic coding, knowledge work, and long-running tasks, is now available on Amazon Bedrock and Claude Platform on AWS. This post covers what's
Claude Opus 5.5 is the first Opus variant that can automatically fall back from its main model to a reduced‑capability version when executing a small set of specialized tasks associated with frontier
arXiv:2609.22183v1 Announce Type: new Abstract: Public benchmark scores may reflect skill, prior exposure to the questions, or both, and for most models the training data are unknown. We present Clean
arXiv:2609.22950v1 Announce Type: new Abstract: While compressed-sensing regularizers enable interpretable reconstruction of 4D Flow CMR through transparent variational objectives, their hand-crafted
arXiv:2609.24394v1 Announce Type: new Abstract: Climate variability influences whether a market disruption escalates into a food crisis, yet broad climate patterns like El Nino, tracked months before
arXiv:2609.22734v1 Announce Type: new Abstract: Clinical domain classification plays an important role in organizing and analyzing large volumes of unstructured medical text. However, medical transcri
arXiv:2504.14280v2 Announce Type: replace Abstract: As machine learning evolves, domain generalization (DG) and domain adaptation (DA) have become crucial for improving model robustness across diverse
arXiv:2609.24141v1 Announce Type: new Abstract: On-policy distillation (OPD) pays twice for each fresh batch: the student generates trajectories and a stronger teacher scores them. Existing methods im
arXiv:2508.03749v2 Announce Type: replace Abstract: Accurately estimating urban rail platform occupancy can support more informed operational decision-making by transit agencies, particularly during p
arXiv:2604.06487v2 Announce Type: replace Abstract: Conventional end-to-end automatic speech recognition (ASR) systems rely on paired speech-text data for domain adaptation. Recent LLM-based ASR archi
arXiv:2609.22166v1 Announce Type: new Abstract: The rapid advancement of Internet of Things (IoT) technology has led to the widespread deployment of smart, interconnected devices across a range of dom
arXiv:2609.24494v1 Announce Type: new Abstract: Accurate monocular depth estimation serves as a core enabler for single camera scene understanding. However, existing self-supervised monocular depth es
arXiv:2609.22232v1 Announce Type: new Abstract: Millions worldwide require Renal Replacement Therapy (RRT) as a treatment essential for survival. However, optimizing RRT strategies via AI is challengi
arXiv:2609.23321v1 Announce Type: cross Abstract: Low-rank adaptation (LoRA) has become a key technology for serving large-scale personalized large language models and diffusion models in the cloud. H
arXiv:2609.24208v1 Announce Type: new Abstract: We ask how little geometry a person has to draw to control both where people stand and where the camera moves in a generated video. Our answer is a grou
Sophie Shulman / CTech: Cognex agrees to acquire robotics and 3D computer vision company RealSense in a ~600M deal, including 500M in cash; Intel spun off RealSense in July 2025 — The Haifa-based robo
arXiv:2603.03768v2 Announce Type: replace Abstract: Full-stack human-robot collaboration (HRC) can become brittle when replacing a planner, partner model, coordination policy, or controller changes th
arXiv:2609.23486v1 Announce Type: cross Abstract: Robots operating in human-centered environments are typically designed to execute explicit instructions, and most robot-learning datasets likewise pai
arXiv:2609.23883v1 Announce Type: new Abstract: We present a collaborative streaming anomaly detection system for high-speed data streams that explicitly integrates human analysts into the decision lo
arXiv:2609.23592v1 Announce Type: cross Abstract: End-to-end document parsers increasingly offer an optional reasoning mode for complex pages. On a 180-page entropy-stratified discovery sample with on
arXiv:2609.23961v1 Announce Type: new Abstract: Monocular colonoscopic 3D reconstruction is important for surgical robotic colonoscopy, but remains challenging due to weak texture, specular reflection
arXiv:2301.12254v5 Announce Type: replace-cross Abstract: Assortment optimization has received active explorations in the past few decades due to its practical importance. Despite the extensive litera
arXiv:2609.22896v1 Announce Type: new Abstract: Autonomous vehicles operating in open-world scenarios are inevitably confronted with previously unknown objects, such as exotic animals or loose cargo.
arXiv:2609.22361v1 Announce Type: new Abstract: Joint audio--video generators are trained on data in which what an event looks like and what it sounds like are strongly, often spuriously, correlated:
arXiv:2609.22813v1 Announce Type: new Abstract: We present commonsense ranked search (CoRS), a novel path planner that turns an abstract instruction into a route that follows commonsense. While existi
arXiv:2609.23619v1 Announce Type: new Abstract: Snapshot hyperspectral imaging avoids sequential scanning, but systems that jointly achieve stable reconstruction, low cost, and compact optics remain l
arXiv:2609.22105v1 Announce Type: cross Abstract: Automatic sleep staging from polysomnography (PSG) is a well-studied task, but PSG itself is expensive, clinic-based, and burdensome to manually score
arXiv:2609.23832v1 Announce Type: new Abstract: Automated grading of conjunctival photographs could reduce the cost and variability of trachoma prevalence surveys, but the relative value of modern pre
arXiv:2609.23476v1 Announce Type: cross Abstract: A potential path forward is Quantum Machine Learning (QML), which aims to leverage quantum computing in conjunction with classical machine learning to
arXiv:2609.24440v1 Announce Type: new Abstract: The quadratic scaling of Transformer self-attention has driven the adoption of sub-quadratic Selective State Space Models (SSMs) like Mamba, which compr
arXiv:2609.22284v1 Announce Type: new Abstract: Talking-face (TF) deepfakes are detected unevenly by rPPG-based methods across generators. We study two lightweight visual-only cues, rPPG-derived wavef
arXiv:2609.24797v1 Announce Type: new Abstract: Linear RNNs based on the delta-rule enable efficient sequence modeling, but their linear updates with a low-rank correction constrain their expressivity
arXiv:2609.22415v1 Announce Type: new Abstract: Complex-valued Transformers have inherited softmax attention over the raw complex inner product. Outside natively complex domains this standard form sta
arXiv:2609.24423v1 Announce Type: cross Abstract: We consider a standard convex composite optimization problem with either smooth or nonsmooth objective function, and under quadratic growth. In recent
arXiv:2411.10163v3 Announce Type: replace Abstract: Large language models (LLMs) demonstrate remarkable performance across various tasks, prompting researchers to develop diverse evaluation benchmarks
arXiv:2609.23005v1 Announce Type: new Abstract: 3D Gaussian Splatting (3DGS) enables high-quality novel view synthesis but incurs high storage and transmission costs due to dense Gaussian primitives.
arXiv:2603.18503v2 Announce Type: replace-cross Abstract: Efficient coordination for collective spatial distribution is a fundamental challenge in multi-agent systems. Prior research on Density-Driven
arXiv:2609.22919v1 Announce Type: new Abstract: Reinforcement learning in real-life applications requires safety guarantees during exploration. Typical reinforcement learning algorithms do not provide
arXiv:2609.23614v1 Announce Type: new Abstract: Contact-rich manipulation, requiring robots to regulate not only motion but also how they yield to external forces, has emerged as the next frontier for
arXiv:2609.22614v1 Announce Type: new Abstract: Process model forecasting (PMF) aims to predict the process model that will characterize a future period, thereby providing a process-level view of how
arXiv:2609.23815v1 Announce Type: new Abstract: Medical image segmentation models typically rely on large amounts of densely annotated volumetric data, limiting their scalability across tasks and imag
arXiv:2609.23454v1 Announce Type: cross Abstract: Two groups of autonomous, anonymous, and oblivious mobile robots are deployed in the two-dimensional Euclidean plane, each assigned a distinct task. W
arXiv:2609.23170v1 Announce Type: cross Abstract: Modern prediction-driven decision systems often rely on black-box predictors, but a point forecast alone does not provide the uncertainty scale requir
arXiv:2609.24929v1 Announce Type: cross Abstract: In this paper, we study nonasymptotic L^p error bounds for interval length and conditional coverage in split conformalized quantile regression (CQR).
arXiv:2606.20002v2 Announce Type: replace-cross Abstract: This work presents a general framework for training large language models (LLMs) to 'Connect the Dots' (CoD), a meta-capability required by lo
arXiv:2609.22441v1 Announce Type: new Abstract: In large-scale recommendation systems like the LinkedIn Feed, content generated by a member's network (connections and follows) makes up over 70% of imp
arXiv:2609.22983v1 Announce Type: cross Abstract: Robotic grasping is typically formulated as the problem of identifying successful actions from a space of candidate grasp poses. However, the organiza
arXiv:2609.22641v1 Announce Type: new Abstract: Autoregressive video world models enable temporally coherent generation for a single observer. Extending them to multiple agents requires consistency ac
arXiv:2609.23742v1 Announce Type: new Abstract: Small open-source large language models (LLMs) in the 0.6B-4B parameter range are increasingly deployed for structured output generation (JSON, function
arXiv:2609.23800v1 Announce Type: new Abstract: High-precision connector insertion remains challenging for robotic systems due to tight mechanical tolerances, partial observability during contact, and
arXiv:2609.22101v1 Announce Type: new Abstract: Large language models can process increasingly long prompts, yet their ability to locate and use decisive evidence may degrade as irrelevant or confusab
arXiv:2609.22409v1 Announce Type: new Abstract: Understanding contextual causality is critical for large language models (LLMs), as it enables them to accurately identify causal relations in specific
arXiv:2609.22360v1 Announce Type: new Abstract: Electrical submersible pumps (ESPs) are essential in offshore oil production, where unexpected failures can result in significant operational and financ
arXiv:2609.22175v1 Announce Type: cross Abstract: World models trained via pixel reconstruction can struggle in visually complex environments, where irrelevant information dominates the objective and
arXiv:2609.23567v1 Announce Type: cross Abstract: We reconsider the theory of probabilistic formal languages generated by n-gram models and by probabilistic context-free grammars (PCFGs). The expected