Knowledge catalogue
arXiv:2605.25866v1 Announce Type: new Abstract: Accurately predicting crystal properties is critical for accelerating materials discovery, but it is often limited by scarce labeled data and costly the
arXiv:2605.25566v1 Announce Type: new Abstract: Clinical decision-making requires reasoning over incomplete, imprecise, and linguistically expressed patient narratives. While large language models (LL
we just revamped the create_agent docs! the new agents page shows how to build a custom harness for your use case w/ create_agent as an easy entrypoint start w/ your prompt and tools, then add middlew
arXiv:2605.25385v1 Announce Type: cross Abstract: Camouflaged object detection (COD) from a single image is a challenging task due to the high similarity between objects and their surroundings. Existi
arXiv:2605.22972v1 Announce Type: cross Abstract: Humans, animals, and modern machine learning models exhibit impressive abilities to learn complex behaviors and generalize these behaviors to unseen s
arXiv:2605.23247v1 Announce Type: new Abstract: In this paper, we introduce the first machine learning framework for predicting optimal processing times in Single-Level Tree Network (SLTN) architectur
📢 Accepted to TMLR, with reproducibility certification 🏅 v2 of our JEPA-WM study (arXiv:2512.24497) is out, with new data-scaling experiments, a Lipschitz analysis of multistep rollout training, and e
arXiv:2605.23417v1 Announce Type: new Abstract: Most black-box optimization methods require extensive hyperparameter tuning, often limiting their ability to generalize across different optimization do
arXiv:2605.23231v1 Announce Type: new Abstract: This paper considers a practical few-shot anomaly detection (FSAD) setting, termed discriminative FSAD, where a limited number of both normal and anomal
arXiv:2512.15767v2 Announce Type: replace-cross Abstract: Simulating complex unsteady physical phenomena relies on detailed mathematical models, simulated for instance by using the Finite Element Meth
arXiv:2605.23139v1 Announce Type: cross Abstract: Multivariate time series anomaly detection has become increasingly important in real-world applications, where labeled data are often scarce. Many exi
Finally, a big name has the courage to tell it: we are nowhere near AGI. Demis Hassabis, CEO of Google DeepMind and Nobel laureate for AlphaFold, put it neat and clear: 'Today's systems are nowhere ne
arXiv:2506.14135v5 Announce Type: replace-cross Abstract: Accurate scene perception is critical for vision-based robotic manipulation. Existing approaches typically follow either a Vision-to-Action (V
arXiv:2504.09846v2 Announce Type: replace-cross Abstract: Frequent and long-term exposure to hyperglycemia increases the risk of chronic complications, including neuropathy, nephropathy, and cardiovas
arXiv:2605.23183v1 Announce Type: cross Abstract: Contemporary glioma diagnosis integrates molecular features with histopathology to guide clinical decision-making. However, in clinical settings, dive
arXiv:2605.23892v1 Announce Type: cross Abstract: Visual geometry transformers have become powerful architectures for multi-view 3D reconstruction, enabling joint prediction of multiple 3D attributes
Groove Jones is a customer or partner of ComfyUI, as featured on the ComfyUI customers page. The post likely highlights Groove Jones's use of ComfyUI, a node-based UI for Stable Diffusion and other ge
arXiv:2602.05202v2 Announce Type: replace Abstract: Aligning video generative models with human preferences remains challenging: current approaches rely on Vision-Language Models (VLMs) for reward mod
Ha. @demishassabis and @DarioAmodei, who are running the two best AI labs in the world both have PhDs. Jim Simons, who founded one of the biggest hedge funds in the world had a PhD. Eric Schmidt, Goog
arXiv:2605.22942v1 Announce Type: new Abstract: This report presents a lightweight modification to the DETR-based fusion transformer baseline for the MaCVi 2026 Vision-to-Chart data association challe
Its very limiting that a big set of very hard problems that we have just lying around are Erdos problems. Don’t get me wrong, they are quite cool, but we really need hard problems repositories for man
arXiv:2605.22939v1 Announce Type: new Abstract: We aim to improve the reasoning capabilities of diffusion language models (DLMs). While SFT is a popular post-training recipe for autoregressive models,
arXiv:2605.22967v1 Announce Type: new Abstract: When Masked Diffusion Models (MDMs) generate sequences through iterative refinement, the rich internal computation over masked positions is discarded, f
arXiv:2605.23845v1 Announce Type: new Abstract: Data-driven learning approaches for physics simulation, sometimes referred to as world models, have emerged as promising alternatives to traditional phy
arXiv:2603.18551v2 Announce Type: replace-cross Abstract: We study how to construct compressed datasets that suffice to recover optimal decisions in linear programs with an unknown cost vector c lying
arXiv:2605.23510v1 Announce Type: new Abstract: When learning dynamical systems from data, embedding physical structure can constrain the solution space and improve generalization, but many physics-in
arXiv:2605.23643v1 Announce Type: cross Abstract: Tools like Tamarin and ProVerif have achieved notable success in analyzing and verifying complex real-world protocols such as EMV, 5G, and WPA2, even
Listen to my conversation with @jerryjliu0 of @llama_index on Spotify: https://bit.ly/3v1R0Tu Apple: https://bit.ly/4bTCwpD Youtube: https://bit.ly/3uXthnv LinkedIn: http://bit.ly/3Xs8GQP Website: htt
Andrew Ng posted a Memorial Day tribute emphasizing that democracy requires sacrifice and cannot be taken for granted, describing it as a 'precious inheritance' that demands defense. The post honors t
arXiv:2406.02883v2 Announce Type: replace Abstract: Automated scraping stands out as a common method for collecting data in deep learning models without the authorization of data owners. Recent studie
arXiv:2510.16335v4 Announce Type: replace Abstract: This paper investigates the recently emerged problem of Language-assisted Image Clustering (LaIC), where textual semantics are leveraged to improve
arXiv:2605.23434v1 Announce Type: new Abstract: Approximate inference over inducing variables is the central computational bottleneck of Deep Gaussian Processes (DGPs). Existing methods either fit an
arXiv:2605.23478v1 Announce Type: cross Abstract: Accurate crop yield prediction is crucial for sustainable agriculture and global food security. While existing methods are predominantly developed for
arXiv:2605.23672v1 Announce Type: new Abstract: Reconstructing dynamic 3D scenes from monocular videos is a fundamental yet highly challenging task, as real-world motions often involve both long-term
arXiv:2605.23040v1 Announce Type: new Abstract: Latent steering exploits internal representations of Large Language Models (LLMs) to guide generation, yet interventions on dense states can entangle di
// The Efficiency Frontier in LLMs // (bookmark this one) How much are you overpaying for context you do not need? It turns out that context costs dominate production LLM bills, and the right strategy
arXiv:2605.23045v1 Announce Type: cross Abstract: Video representation learning has seen tremendous progress in recent years. This has been driven by many factors, including the scale of training and
arXiv:2605.23033v1 Announce Type: cross Abstract: Foundational Models pretrained on huge amount of data learn representations that evolve across depth, forming a hierarchy of embeddings with distinct
arXiv:2605.22851v1 Announce Type: cross Abstract: Photoplethysmography (PPG) has become a ubiquitous physiological signal; however, current generative models still struggle to preserve realistic wavef
Grok, an AI assistant, can provide information about geological features, local history, and points of interest in unfamiliar locations when activated with the 'Hey Grok' voice command. The feature is
Nicole Nguyen / Wall Street Journal: Hands-on with a pre-release build of Google Docs Live, an AI-powered voice tool for drafting documents, rolling out this summer to AI Pro and Ultra subscribers — A
this is bad SHOCKING: Two researchers at Northeastern sat down with six of the chatbots that hundreds of millions of people use every day. They typed a sentence anyone in distress might type at 3 in t
This post emphasizes the growing demand for engineers and researchers in advancing technology fields, advising people to focus on mastering fundamental concepts rather than being distracted by hype or
an elaboration of the Paul Graham reference: Literally one of the most important essays could read, if you want to have a *productive* disagreements about anything, on X or anywhere else, is @paulg’s
arXiv:2605.22611v1 Announce Type: new Abstract: Antimicrobial stewardship (AMS) is critical in pediatric intensive care units (PICUs), where diagnostic uncertainty often drives broad-spectrum antibiot
arXiv:2605.21514v1 Announce Type: cross Abstract: Many complex systems can be modeled by temporal networks, whose organization often evolves through distinct structural phases. Detecting the change po
arXiv:2605.21600v1 Announce Type: new Abstract: Computational antibody CDR design methods condition on antigen structure to generate binding loops, yet existing architectures conflate two fundamentall
arXiv:2605.21614v1 Announce Type: cross Abstract: Worked examples are step-by-step solutions to problems in a specific domain, offered to students to acquire domain-specific problem-solving skills. Th
@GaryMarcus I don't understand why the people running the AI companies are held to a much lower standard. In early 2025 Sam Altman wrote 'we are now confident we know how to build AGI.' As predictions
“I have no idea why you tagged Paul Graham” means “I was too lazy to try to learn something”. Paul Graham’s piece on argumentation is brilliant, something everyone should learn from it. In the meantim
This statement from AI researcher François Chollet suggests that the ability to learn something genuinely novel demonstrates a fundamental learning capacity that generalizes across all domains. The cl
arXiv:2605.22335v1 Announce Type: new Abstract: In-context learning for tabular data sets strong predictive standards in observational settings; it however primarily relies on correlational structure,
Literally one of the most important essays could read, if you want to have a *productive* disagreements about anything, on X or anywhere else, is @paulg’s “How to Disagree”. It describes a pyramid. Ev
arXiv:2605.21770v1 Announce Type: new Abstract: Large language models frequently produce errors in reasoning tasks despite possessing the underlying knowledge required for correct reasoning. One possi
arXiv:2603.16077v3 Announce Type: replace Abstract: Masked diffusion models (MDM) exhibit superior generalization when learned using a Partial masking scheme (Prime). This approach converts tokens int
Most agents die after a few seconds. @AnthropicAI's workshop shows how to build agents that run for hours. full 75-min session with Ash Prabaker & Andrew Wilson. https://www.youtube.com/watch?v=mR-WAv
Nothing disappoints me more than people saying we should stop progress because peoples meaning depends on that monotonous labor, as if humanitys highest purpose is filling Excel sheets or stocking she
WordDetectorNet predicts an axis-aligned bounding box for each inner-word pixel using a ResNet18-based neural network, then applies DBSCAN clustering to refine the predictions . The system demonstrate
This Databricks resource discusses how pharmaceutical companies can use analytics to optimize their product launch strategy, focusing on accelerating critical decision-making during the crucial first
arXiv:2605.21859v1 Announce Type: cross Abstract: Phylogenetic trees are hybrid objects: branch lengths vary continuously, while topologies change discretely through edge contractions and expansions.