Knowledge catalogue
arXiv:2606.09006v1 Announce Type: cross Abstract: Both digital economy and digital technology researchers increasingly recognize the need to better address the role that artificial intelligence (AI) p
arXiv:2606.07916v1 Announce Type: new Abstract: The growing ability of generative models to produce realistic documents poses a direct challenge to evidentiary workflows in the justice system and the
arXiv:2606.07587v1 Announce Type: new Abstract: LLM routing has become a popular approach to improve the cost-quality trade-off of LLM services by dynamically selecting a model for each query. Recent
Jeremy Howard argues that calls to pause AI research are selectively applied, with restrictions primarily targeting independent researchers while well-resourced labs continue development, creating an
arXiv:2603.25184v2 Announce Type: replace-cross Abstract: Reinforcement learning (RL) has become essential for post-training large language models (LLMs) in reasoning tasks. While scaling rollouts can
arXiv:2606.08152v1 Announce Type: new Abstract: The growing volume of retired lithium-ion battery packs from electric vehicles and portable electronics calls for automated disassembly that is safe, fl
arXiv:2606.09167v1 Announce Type: new Abstract: Hyperspectral object tracking (HOT) leverages the rich spectral information provided by hyperspectral videos (HSVs), offering substantial potential for
arXiv:2606.09132v1 Announce Type: new Abstract: Visual Language Models (VLMs) have gained significant popularity due to their remarkable ability. While various methods exist to enhance privacy in text
arXiv:2602.08222v2 Announce Type: replace Abstract: As post-training optimization becomes central to improving large language models, we observe a persistent saturation bottleneck: once models grow hi
arXiv:2502.09194v1 Announce Type: cross Abstract: Generative Artificial Intelligence (AI) techniques have become integral part in advancing next generation wireless communication systems by enabling s
arXiv:2509.04991v2 Announce Type: replace-cross Abstract: Land surface temperature (LST) is a fundamental physical variable in land-atmosphere interactions, surface energy budgets, and climate process
arXiv:2606.07365v1 Announce Type: cross Abstract: Photoplethysmography (PPG), a non-invasive measure of changes in blood volume, is widely used in both wearable devices and clinical settings. Recent P
Also, those who focus on using AI to help improve the skills of themselves and their teams will be diamonds in great demand, since they will be the rare A++ players in a sea of mediocrity. There will
arXiv:2606.06887v1 Announce Type: new Abstract: This paper introduces ARAPDiffusion, a latent diffusion model to learn the underlying continuous shape space of a deformation shape collection. The key
As many of you were interested in the technical details of the model, here is a followup thread to go more into technical details about VLA-JEPA. 1. Architecture 2. Training 3. Recipe for the demo 4.
arXiv:2606.07079v1 Announce Type: new Abstract: Standard diffusion models corrupt an entire sample with a single shared noise level, forcing all spatial regions to follow the same denoising trajectory
arXiv:2606.07374v1 Announce Type: cross Abstract: In this work, we propose a deep learning framework for coherence regression directly from detected SAR images, without the need for accurate coregistr
arXiv:2606.07120v1 Announce Type: new Abstract: Autoencoders (AEs) learn low-dimensional representations by mapping data into a latent space while minimizing reconstruction error. Despite their empiri
arXiv:2606.07304v1 Announce Type: new Abstract: Embodied agents need to predict the future consequences of candidate actions in order to plan effectively before execution. Existing visual dynamics mod
arXiv:2606.07058v1 Announce Type: cross Abstract: Variational autoencoders (VAEs) learn low-dimensional latent representations of high-dimensional data. When the data lies on a manifold with non-Eucli
arXiv:2508.17693v2 Announce Type: replace-cross Abstract: Database normalization is crucial to preserving data integrity. However, it is time-consuming and error-prone, as it is typically performed ma
arXiv:2606.07503v1 Announce Type: new Abstract: We propose Differences in Detection (DnD), an intuitive method to compare two object detection models. Based on the same matching algorithm, it compleme
arXiv:2606.07089v1 Announce Type: new Abstract: World Action Models (WAMs) offer a promising approach to embodied intelligence, yet existing methods rely heavily on video prediction as action priors a
arXiv:2606.06872v1 Announce Type: cross Abstract: Estimating hand-surface contact pressure from an egocentric view is crucial for AR/VR devices, robotic imitation, and ergonomic analysis. Existing met
This blog has previously discussed FHE for ML inference in the post Enable fully homomorphic encryption with Amazon SageMaker endpoints for secure, real-time inferencing, but this post goes a little f
arXiv:2606.07288v1 Announce Type: new Abstract: Reconstructing surface meshes from multi-view images has remained a core challenge in recent years. Most existing methods, whether implicit or explicit,
As AI capabilities mature, sports organizations are using AI-powered fan personalization to move beyond broad audience targeting and deliver experiences shaped by real-time data and deeper audience un
arXiv:2606.07183v1 Announce Type: new Abstract: This work examines the semantic geometry underlying NLP models. We compare supervised vector embeddings, such as CamemBERT, with lexical co-occurrence g
arXiv:2603.20967v2 Announce Type: replace-cross Abstract: One of the most common machine learning setups is logistic regression. In many classification models, including neural networks, the final pre
arXiv:2606.06899v1 Announce Type: new Abstract: Variations in illumination remain a major challenge for visual representation learning, as they induce substantial appearance changes both across and wi
arXiv:2602.11201v2 Announce Type: replace Abstract: Chain-of-Thought (CoT) explanations are widely used to interpret how language models solve complex problems, yet it remains unclear whether these st
arXiv:2606.07153v1 Announce Type: cross Abstract: Physics-informed learning is increasingly used for partial differential equation (PDE)-governed inverse problems, but its reliability remains difficul
arXiv:2510.26714v5 Announce Type: replace-cross Abstract: Machine unlearning aims to remove the influence of certain data points from a trained model without costly retraining. Most practical unlearni
People demanding 'proof' of election fraud are not understanding how crime works. I worked at Manhattan DA for over 2 years, one in Homicide. We never had video proof of the crime. We almost never had
arXiv:2606.06765v1 Announce Type: cross Abstract: Establishing quantitative relationships among mix design, raw material properties, curing conditions, and performance remains a long-standing challeng
arXiv:2606.06943v1 Announce Type: cross Abstract: Vision-language models (VLMs) such as CLIP achieve strong zero-shot recognition but remain highly fragile under adversarial perturbations. Recent test
arXiv:2606.07196v1 Announce Type: new Abstract: Classical sparse Type-II Bayesian methods for M/EEG brain imaging support joint estimation of source and noise hyperparameters, but rely on fixed iterat
arXiv:2606.07015v1 Announce Type: cross Abstract: While song generation and singing voice conversion (SVC) have evolved significantly, they have long been developed isolated: the former lacks zero-sho
arXiv:2606.07291v1 Announce Type: new Abstract: Multivariate time-series forecasting requires models to reason over temporal dynamics, cross-variable dependencies, and historical input-output correspo
arXiv:2606.07491v1 Announce Type: cross Abstract: High-performance computing (HPC) clusters remain the backbone of large-scale scientific computation, traditionally executing deterministic, linear pip
With access to the latest generative AI models and high-performance accelerated compute in high global demand, AWS customers need tools to take advantage of model availability and capacity across mult
Apple's biggest event of the year is nearly here. The company's Worldwide Developers Conference will spotlight updates to iOS, macOS, and all of Apple's other operating systems, and this year's event
zoomers will not remember this, but we used to hold elections in this country and learn the results of those elections in the evening — on election day. the overwhelming majority of people simply assu
'Malinformation' refers to information that is factually accurate but strategically shared to cause political or reputational damage. The term describes a category of misleading communication that dif
Bad take, you absolutely need to look at the data, manually Just learned: Software engineers used to do manual data labeling at Scale AI while Alex Wang was CEO. After he left, new leadership joined,
not sure i see the issue here Just learned: Software engineers used to do manual data labeling at Scale AI while Alex Wang was CEO. After he left, new leadership joined, and were HORRIFIED to learn th
of course he wants to marginalize any objections to AI.* *exact dollar figures of course depend on dilution and the size of the angel investment etc. David Sacks invested in SpaceX at a 27 million val
Super-powerful AI models will launch in the coming weeks. We are looking at a potential step change in model capabilities. The biggest mistake right now is to lock into one vendor. I say this not only
American AI startups have increasingly shifted toward adopting Chinese AI models since the beginning of the year, representing a notable change in technology sourcing preferences. This trend likely re
anyone who wants to put money into OpenAI’s IPO should think again. the talent is voting with its feet, and has been for several years. Personal update: I’ve decided to leave OpenAI. I’m proud to have
// Continual Learning Bench // One of the research areas with lots of investments is continual learning. While there are many efforts, there is very little progress in measuring it. So the big questio
arXiv:2606.05855v1 Announce Type: cross Abstract: Continuous electroencephalography (EEG) emotion prediction aims to model the temporal evolution of human emotional states from EEG signals. Unlike con
arXiv:2606.05441v1 Announce Type: cross Abstract: We investigate how to make small tabular foundation models effective for High-Dimensional, Low-Sample Size (HDLSS) tabular prediction without retraini
https://x.com/CAIS/status/2049145768460882142?s=20 Should we care about AI happiness? In our new research, we find evidence of functional AI wellbeing across several independent measures. We find whic
https://x.com/CAIS/status/2057681579242348801?s=20 In our latest research, we find that AIs are subtly and pervasively politically manipulative. When we ask the same question about politically opposed
I organized an intervention to stop Elon from starting SpaceX. Here is the story... Twenty five years ago, Elon and I sat in a car on a dark stretch of Long Island highway, two neurodiverse geeks star
arXiv:2508.06249v3 Announce Type: replace-cross Abstract: Fine-tuning lets practitioners repurpose aligned large language models (LLMs) for new domains, yet recent work reveals emergent misalignment (
arXiv:2603.13761v2 Announce Type: replace-cross Abstract: Curriculum learning--ordering training examples in a sequence to aid machine learning--takes inspiration from human learning, but has not gain
neuro paper finds that the hippocampus is basically an immutable event log that projects a state in graph form…. just like activegraph 🤔 if you’re into neuro and think we live in a simulation, read on
arXiv:2606.06479v1 Announce Type: cross Abstract: Training recurrent neural networks (RNNs) requires assigning credit across long sequences of computations. Standard backpropagation through time (BPTT