Knowledge catalogue
arXiv:2512.11108v3 Announce Type: replace Abstract: Good quality explanations strengthen the understanding of language models and data. Feature attribution methods, such as Integrated Gradient, are a
arXiv:2604.17879v1 Announce Type: new Abstract: Camouflaged Object Detection is challenging due to the high degree of similarity between camouflaged objects and their surrounding backgrounds. Current
arXiv:2604.18296v1 Announce Type: new Abstract: Static concreteness ratings are widely used in NLP, yet a word's concreteness can shift with context, especially in figurative language such as metaphor
arXiv:2502.13637v2 Announce Type: replace Abstract: Human affordance learning investigates contextually relevant novel pose prediction such that the estimated pose represents a valid human action with
arXiv:2604.16757v1 Announce Type: new Abstract: The expression of emotions that serve social purposes, such as asserting independence or fostering interdependence, is central to human interactions and
arXiv:2505.22226v2 Announce Type: replace Abstract: Recent theoretical advances reveal that the Hadamard product induces nonlinear representations and implicit high-dimensional mappings for the field
arXiv:2604.18168v1 Announce Type: new Abstract: Few-step generation has been a long-standing goal, with recent one-step generation methods exemplified by MeanFlow achieving remarkable results. Existin
arXiv:2604.16865v1 Announce Type: cross Abstract: In this paper, we consider the problem of extraction of most informative features from time series that are regarded as observed values of stochastic
arXiv:2604.16450v1 Announce Type: cross Abstract: Intersectional biases in healthcare data can produce compound disparities in clinical machine learning models, yet most fairness evaluations assess de
arXiv:2604.16610v1 Announce Type: cross Abstract: Machine learning models often inherit biases from historical data, raising critical concerns about fairness and accountability. Conventional fairness
arXiv:2604.16780v1 Announce Type: new Abstract: This paper presents FairNVT, a lightweight debiasing framework for pretrained transformer-based encoders that improves both representation and predictio
arXiv:2506.12176v5 Announce Type: replace Abstract: In explainable AI, surrogate models are commonly evaluated by their fidelity to a neural network's predictions. Fidelity, however, measures alignmen
arXiv:2601.11886v2 Announce Type: replace Abstract: In high-stakes domains like medicine, it may be generally desirable for models to faithfully adhere to the context provided. But what happens if the
arXiv:2512.20182v3 Announce Type: replace Abstract: Recognizing whether outputs from large language models (LLMs) contain faithfulness hallucination is crucial for real-world applications, e.g., retri
SpaceX's Falcon rockets conduct frequent launches occurring every few days, with public viewing opportunities available at launch facilities in Florida and California. This statement reflects SpaceX's
Famegrid Checkpoint ZIB is built on Z-Image Base and produces modern, social-media-style photography with a natural look, designed to create polished yet believable images with good composition and li
arXiv:2604.16522v1 Announce Type: new Abstract: This paper proposes a fast and online method for jointly performing 3D multi-object tracking and pose estimation using multiple monocular cameras. Our a
arXiv:2604.18491v1 Announce Type: new Abstract: Computational Fluid Dynamics (CFD) is central to race-car aerodynamic development, yet its cost -- tens of thousands of core-hours per high-fidelity eva
arXiv:2604.17956v1 Announce Type: new Abstract: Machine learning has become integral to medical research and is increasingly applied in clinical settings to support diagnosis and decision-making; howe
arXiv:2604.16778v1 Announce Type: new Abstract: LLM-powered agents often reason from scratch when presented with a new problem instance and lack automatic mechanisms to transfer learned skills to othe
arXiv:2604.16612v1 Announce Type: new Abstract: Traffic prediction plays a central role in intelligent transportation systems (ITS) by supporting real-time decision-making, congestion management, and
arXiv:2604.16574v1 Announce Type: new Abstract: Federated Learning (FL) faces challenges from client data heterogeneity and resource-constrained mobile devices, which can degrade model accuracy. Perso
Ashley Gold / Axios: Filing: Anthropic spent 1.6M and OpenAI 1M on lobbying in Q1, vs. 360K and 560K in Q1 2025, respectively; Meta topped Big Tech lobbying spending with 7.1M — Both Anthropic and Ope
Echo Wang / Reuters: Filing: SpaceX tells investors that orbital AI data centers use “unproven technologies” and may not achieve “commercial viability” due to space-related risks — SpaceX warned inves
Bloomberg: Filings: crypto PACs amassed a ~180M war chest for the 2026 midterms, including Fairshake's 166M, giving them the ability to outspend some GOP super PACs — Political groups tied to the cryp
arXiv:2510.24942v2 Announce Type: replace-cross Abstract: Despite their impressive performance, vision-language models (VLMs) still struggle on culturally situated inputs. To understand how VLMs proce
arXiv:2511.17171v4 Announce Type: replace Abstract: Predicting wildfire risk is a reasoning-intensive spatial problem that requires the integration of visual, climatic, and geographic factors to infer
arXiv:2604.17919v1 Announce Type: new Abstract: Recent advances in flow-based offline reinforcement learning (RL) have achieved strong performance by parameterizing policies via flow matching. However
The 2026 edition of Adobe Summit this week marks a historic turning point for the software giant. It not only showcased the next frontier of “agentic artificial intelligence” but also served as the sw
arXiv:2604.16649v1 Announce Type: new Abstract: Directed energy deposition (DED) produces complex thermo-mechanical responses that can lead to distortion and reduced dimensional accuracy of a manufact
arXiv:2604.17344v1 Announce Type: cross Abstract: When task-specific labels are not available, it becomes difficult to select an embedding model for a specific target corpus. Existing labelless measur
arXiv:2604.17513v1 Announce Type: new Abstract: Simulation frameworks such as Isaac Sim have enabled scalable robot learning for locomotion and rigid-body manipulation; however, contact-rich simulatio
arXiv:2604.17720v1 Announce Type: cross Abstract: Point-based Neural Networks (PNNs) have become a key approach for point cloud processing. However, a core operation in these models, Farthest Point Sa
Flexible Aspect Ratios ChatGPT Images 2.0 supports aspect ratios as wide as 3:1 and as tall as 1:3. It can generate outputs that are ready to fit the formats you need, from wide banners and presentati
arXiv:2511.00868v2 Announce Type: replace Abstract: Large Language Model (LLM) serving is increasingly constrained by the growing size of the key-value (KV) cache, which scales with both context lengt
arXiv:2604.18109v1 Announce Type: new Abstract: This paper presents factorized linear projection (FLiP) models for understanding pretrained sentence embedding spaces. We train FLiP models to recover t
Alex Ebert / Bloomberg Law: Florida AG James Uthmeier issues criminal subpoenas to OpenAI to investigate if ChatGPT's role in planning a mass shooting constitutes criminal liability — Florida is sendi
Florida is opening a criminal investigation into ChatGPT following new details in the mass shooting at Florida State University last year. Investigators say the shooter used ChatGPT to plan the attack
arXiv:2509.18611v2 Announce Type: replace Abstract: Pretraining on large-scale collections of PDE-governed spatiotemporal trajectories has recently shown promise for building generalizable models of d
arXiv:2510.09204v2 Announce Type: replace-cross Abstract: Centralized trajectory optimization in the joint space of multiple robots allows access to a larger feasible space that can result in smoother
arXiv:2604.17625v1 Announce Type: new Abstract: This paper introduces a novel methodology for generating fast and memory-efficient video continuations. Our method, dubbed FlowC2S, fine-tunes a pre-tra
arXiv:2604.17149v1 Announce Type: cross Abstract: Accurate autoregressive prediction of 3D turbulent flows remains challenging for neural PDE solvers, as small errors in fine-scale structures can accu
arXiv:2604.16448v1 Announce Type: cross Abstract: As edge AI deployments scale to billions of devices running always-on, real-time compound AI pipelines, they represent a massive and largely unmanaged
arXiv:2603.19857v2 Announce Type: replace-cross Abstract: Recent Video-to-Audio (V2A) methods have achieved remarkable progress, enabling the synthesis of realistic, high-quality audio. However, they
arXiv:2505.11140v3 Announce Type: replace Abstract: We introduce fs1, a simple yet effective method that improves the factuality of reasoning traces by collecting them from large reasoning models and
Following the announcement of Mythos and a bit of confusion that's arisen, we at @huggingface decided to share some of what we've been discussing about defensive cybersecurity, openness, and AI agents
For clarity, we're running a small test on ~2% of new prosumer signups. Existing Pro and Max subscribers aren't affected. Anthropic just pulled Claude Code from the Pro plan. Pro users wanting it need
NATO is a military and political alliance established in 1949 as a collective defense organization, where member countries commit to mutual defense under Article 5, meaning an attack on one is conside
arXiv:2604.17194v1 Announce Type: cross Abstract: Converting betting odds into accurate outcome probabilities is a fundamental challenge in order to use betting odds as a benchmark for sports forecast
arXiv:2604.18379v1 Announce Type: new Abstract: Most data-driven ionospheric forecasting models operate on gridded products, which do not preserve the time-varying sampling structure of satellite-base
arXiv:2601.06803v2 Announce Type: replace Abstract: While Chain-of-Thought empowers Large Vision-Language Models with multi-step reasoning, explicit textual rationales suffer from an information bandw
arXiv:2601.03938v2 Announce Type: replace-cross Abstract: Continual learning (CL) for large language models (LLMs) aims to enable sequential knowledge acquisition without catastrophic forgetting. Memo
arXiv:2604.17785v1 Announce Type: new Abstract: Unlearning in large language models (LLMs) has emerged as a promising safeguard against adversarial behaviors. When the forgetting loss is applied unifo
arXiv:2603.26475v2 Announce Type: replace Abstract: Electrocardiograms (ECGs) are among the most widely available clinical signals and play a central role in cardiovascular diagnosis. While recent fou
arXiv:2604.16376v1 Announce Type: new Abstract: This study investigates the applicability of authorship attribution based on stylistic features to support actor analysis in threat intelligence. As a f
arXiv:2604.17268v1 Announce Type: new Abstract: AI-generated imagery has reached near-photorealistic fidelity, yet this technology poses significant threats to information security and societal trust.
arXiv:2603.09721v2 Announce Type: replace Abstract: High-fidelity video generation remains challenging for diffusion models due to the difficulty of modeling complex spatio-temporal dynamics efficient
arXiv:2603.07690v2 Announce Type: replace Abstract: Streaming Visual Geometry Transformers such as StreamVGGT enable strong online 3D perception, but their KV-cache grows unbounded over long streams,
The Framework Laptop 13 Pro is a complete redesign featuring a new full-CNC aluminum chassis, a much larger 74Wh battery, LPCAMM2 memory support, a power-optimized display with touch support, and a ha
Framework announced a new Laptop 13 Pro with pre-installed Ubuntu Linux as its first certified Linux option, while navigating ongoing RAM and storage supply chain shortages. The laptop features Intel