Knowledge catalogue
Clem Delangue, CEO of Hugging Face, announced a new collaboration via video post on X/Twitter. The specific details of the collaboration partner and nature of the partnership are not visible from the
arXiv:2606.23152v1 Announce Type: new Abstract: We introduce ShotcreteDepth, a bi-modal dataset from the construction domain that captures both an active shotcreting process and general construction e
arXiv:2606.21099v1 Announce Type: new Abstract: Variational inference (VI) is a powerful method for principled posterior inference for scientific inverse imaging. VI learns the posterior distribution,
arXiv:2606.21875v1 Announce Type: cross Abstract: Modern data analysis usually gives a prediction without showing whether the evidence behind it is clear, conflicting, or stable. Two cases can have th
arXiv:2606.20857v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) models enable robots to execute manipulation tasks from natural-language instructions grounded in visual observations. Ho
arXiv:2606.21085v1 Announce Type: new Abstract: Offline-to-online adaptation serves as a pivotal paradigm for mitigating the prohibitive cost of online exploration by bootstrapping reinforcement learn
arXiv:2312.07865v4 Announce Type: replace Abstract: Despite the success of diffusion-based customization methods on visual content creation, increasing concerns have been raised about such techniques
arXiv:2606.13589v2 Announce Type: replace Abstract: We present Simplex-Constrained Sparse Bagging (SCSB), a mathematically rigorous framework for post-training compression and probability calibration
arXiv:2510.02469v2 Announce Type: replace-cross Abstract: Driving scene manipulation using real-world sensor data has emerged as a promising alternative to traditional driving simulators. Despite adva
arXiv:2606.23536v1 Announce Type: new Abstract: We propose a method for estimating time-varying traffic flow patterns from sparse aggregated vehicle counts. The method partitions the study area into s
arXiv:2606.22873v1 Announce Type: new Abstract: Vision-language models (VLMs) are increasingly deployed in consumer, medical, financial, and enterprise applications. This broad deployment expands the
Single-shot generation still surfaces net-new kernels with no public reference: NeMo vocab-parallel log-probs, Hyena context parallelism, SAM 3 mask suppression. One GEMM + All-Gather kernel hit 87.9µ
arXiv:2603.05963v2 Announce Type: replace Abstract: Recent advances in large-scale pretrained vision models have demonstrated impressive capabilities across a wide range of downstream tasks, including
arXiv:2606.20659v1 Announce Type: cross Abstract: Agent skills encode reusable procedural knowledge that guides large language model agents across tasks and execution contexts. Existing evaluations pr
arXiv:2606.20636v1 Announce Type: cross Abstract: Computer-Use Agents (CUAs) are increasingly deployed in dynamic interactive environments, creating a growing need for continual skill learning during
arXiv:2606.23444v1 Announce Type: cross Abstract: Accurate dynamics models are critical for informed decision-making in robotic systems, particularly for agile aerial vehicles operating under uncertai
arXiv:2606.21096v1 Announce Type: new Abstract: Semi-supervised learning (SSL) on data streams is challenging due to the continuous evolution of high-volume data and the scarcity of labels. Existing m
arXiv:2606.14150v2 Announce Type: replace Abstract: Pruning promises a shortcut to strong small language models. In this work, we examine this promise by pruning Llama-3.1-8B at pruning ratios of 0.5-
Cybersecurity company Snyk Ltd. today launched Evo Agentic Development Security, a new layer of its artificial intelligence security platform built to police the autonomous coding agents that increasi
arXiv:2606.23357v1 Announce Type: new Abstract: Structured weight-uncertainty can improve many aspects of deep learning, but it remains costly to estimate and difficult to implement. Here, we show tha
arXiv:2606.21356v1 Announce Type: new Abstract: Many machine learning applications rely on heterogeneous event streams to make predictions, either causally as events arrive or bidirectionally over com
arXiv:2602.08690v2 Announce Type: replace Abstract: Deep Reinforcement Learning (DRL) has achieved remarkable success in domains requiring sequential decision-making, motivating its application to cyb
arXiv:2606.23575v1 Announce Type: new Abstract: Hyperparameter tuning almost always means search: fit the model at every value on a grid, score each by cross-validation, and keep the winner. For splin
Last week, Midjourney, an AI startup best known for its image generator, made an unusual pivot: medical imaging. The company announced a futuristic ultrasound scanner that would dunk users into a vat
Sony released the first trailer for Taika Waititi's dystopian sci-fi film 'Klara and the Sun,' starring Jenna Ortega, Amy Adams, and Natasha Lyonne. The film is based on Kazuo Ishiguro's New York Time
When Sony announced the Xperia 1 VIII last month, it promoted the phone by sharing some of the worst photos taken on a Sony camera in years. These weren't just any photos, though: they were taken with
Soros wants to end Western Civilization The open society and its enemy, Soros. While he named his Open Society Foundations after Karl Popper’s “The Open Society and Its Enemies,” his project stands as
Dinesh Nair / Bloomberg: Sources: Abu Dhabi's MGX has raised close to 50B from regional sovereign wealth funds, global pension funds, and others to accelerate spending on AI deals — Abu Dhabi's MGX ha
Bloomberg: Sources: Hadrian, which is building AI-powered factories to produce space and defense parts, is in talks to raise ~1B at a ~7.5B post-money valuation — Company runs AI-powered factories tha
New York Times: Sources: Meta is building a standalone prediction markets app called Arena, which would probably rely on video game-like points instead of money wagers — The experimental app, internal
Bloomberg: Sources: Miami-based cybersecurity company Varonis is exploring options including a potential sale after receiving takeover interest; VRNS jumps 6%+ — Cybersecurity company Varonis Systems
Eleanor Olcott / Financial Times: Sources: prices for Nvidia's AI chips on China's black market have more than doubled amid a US export crackdown; its flagship DGX B300 server has risen to $1.1M — US
Bloomberg: Sources: SpaceX, which is seeking to raise between 20B and 25B in its debut US bond sale, has drawn about 89B of demand — SpaceX Loses 600 Billion in Value Over Three Days — Video Player is
Bloomberg: Sources: Tencent is negotiating exits from several game studio investments in Japan, including Tokyo-traded Marvelous, as it reassesses its global portfolio — Tencent Holdings Ltd. is negot
New York Times: Sources: the Trump administration is pressing Meta to submit its AI models for voluntary review; Meta is the only major US AI developer without an agreement — Federal officials are urg
Chloe Taylor / CNBC: South Korea's tech-heavy Kospi index falls 10%, dragged down by SK Hynix and Samsung; STMicro and ASML fall ~7%, and US tech stocks fall in pre-market trading — Global stocks sold
arXiv:2606.20520v2 Announce Type: replace-cross Abstract: Autonomous agents are increasingly connected to cloud, deployment, and data-control workflows, but production mutation authority should not re
arXiv:2606.23041v1 Announce Type: new Abstract: Multimodal Large Language Models (MLLMs) have achieved remarkable success in visual understanding but remain constrained in visual generation due to the
arXiv:2606.20643v1 Announce Type: cross Abstract: Electrical circuit diagram QA tasks require complex mathematical reasoning, which remains challenging for multimodal LLMs. We present SPARC, a multi-a
arXiv:2601.20209v2 Announce Type: replace Abstract: Reinforcement learning has empowered large language models to act as intelligent agents, yet training them for long-horizon tasks remains challengin
arXiv:2606.21026v1 Announce Type: new Abstract: The ocean plays a critical role in sustainable development, particularly in climate change mitigation. Among marine ecosystems, blue carbon ecosystems a
arXiv:2605.24354v2 Announce Type: replace Abstract: Recently, world models have made significant progress in enhancing end-to-end driving systems through both future situation forecasting and improved
arXiv:2510.04180v2 Announce Type: replace Abstract: Deep neural networks can achieve high accuracy while relying on evidence that is hard to inspect or misaligned with the intended task. Concept Bottl
arXiv:2606.20693v1 Announce Type: new Abstract: Background: Wildfires in Canada present increasing threats to ecosystems, communities, and infrastructure, demanding accurate forecasting tools to aid m
arXiv:2606.20629v1 Announce Type: cross Abstract: LLM agents are increasingly deployed as multi-role teams, where tasks are divided across specialized roles such as planner, executor, and verifier. In
arXiv:2606.22308v1 Announce Type: cross Abstract: Lesion segmentation in breast ultrasound involves two related challenges. In images with lesions, speckle noise, low tissue contrast, and posterior ac
arXiv:2606.23129v1 Announce Type: new Abstract: Implicit Neural Representations (INRs) have been proven successful in encoding continuous signals through coordinate-based networks, yet facing a spectr
arXiv:2606.21258v1 Announce Type: cross Abstract: Recent 3DGS-SLAM systems enable real-time operation by leveraging conventional feature matching or ICP-based tracking, thereby avoiding the heavy dens
arXiv:2606.21828v1 Announce Type: cross Abstract: Neural operators are increasingly used to warm-start Newton solvers for nonlinear PDEs, on the premise that a low test error places the initial guess
arXiv:2606.22443v1 Announce Type: new Abstract: Compliant mechanisms are important in robotics because they can improve adaptability, safety, and energy efficiency while reducing hardware complexity.
arXiv:2606.20244v2 Announce Type: replace Abstract: Vision-language models (VLMs) often underperform on evidence intensive tasks because decisive visual evidence are small, localized, and easy to over
arXiv:2606.22874v1 Announce Type: new Abstract: Long contexts have become standard in pretrained LLMs, yet they remain expensive to run: prefill compute grows quadratically with sequence length, and e
arXiv:2606.21973v1 Announce Type: new Abstract: Physiological signals such as EEG, ECG, and PPG are widely used in clinical monitoring. Recent self-supervised learning (SSL) methods offer an attractiv
arXiv:2606.23537v1 Announce Type: cross Abstract: Text-to-SQL enables users to access relational databases via natural language, but real-world settings remain challenging due to coordinated reasoning
arXiv:2601.22679v2 Announce Type: replace-cross Abstract: Consistency models have been proposed for fast generative modeling, achieving results competitive with diffusion and flow models. However, the
arXiv:2606.20197v2 Announce Type: replace Abstract: Actor-Critic Model Predictive Control (MPC) effectively addresses complex, non-convex control problems, but guaranteeing the closed-loop stability o
arXiv:2606.23188v1 Announce Type: new Abstract: Black-box optimization (BBO) deals with problems where objective functions lack explicit analytical forms and are expensive to evaluate. Factorization m
Right now, MIT alumni and friends are voicing their support for: America’s scientific and technological leadership Merit-based admissions and affordable education Advances that increase US health, sec
Financial Times: Stark, which has a deal to supply “kamikaze” drones to the German military, raised €500M from Founders Fund, Sequoia, others; it faced criticism over Thiel ties — US billionaire's fun
Elon Musk announced via X that Starlink satellite internet service will be available on American Airlines flights beginning in the following year. This integration would provide passengers with high-s