Knowledge catalogue
// Adapt the Interface, Not the Model // I am fascinated by the results across my cheap-model-plus-good-harness builds. This new paper also shows good signs of the code-as-agent-harness thesis. The id
arXiv:2605.22275v1 Announce Type: new Abstract: Kernel methods are typically formulated under the assumption of exact, noise-free access to the Gram matrix. However, in emerging settings such as quant
arXiv:2605.21534v1 Announce Type: cross Abstract: Kolmogorov-Arnold Networks (KANs) approximate multivariate functions using learnable univariate edge functions, typically parameterized by B-spline ba
Added a DeepSeek Sparse Attention (DSA) from-scratch implementation to my LLMs-from-scratch repo thanks to an awesome new reader contrib. With motivation, overview, and GPT-style model reference imple
arXiv:2605.22111v1 Announce Type: new Abstract: Accurate modeling of aerodynamic loads is essential for understanding and predicting the responses of complex structural systems. However, these models
Agents shouldn’t have direct visibility into env vars or credentials that can expose sensitive systems and data. Keeping secrets outside the agent’s context helps secure the env while still allowing a
arXiv:2605.21610v1 Announce Type: new Abstract: Antibody design methods condition on antigen structure to generate complementarity-determining regions (CDR), yet a systematic evaluation of baseline me
Latent Space reports on a rebranding or reorganization where Model Labs have been renamed or converted into Agent Labs, reflecting a shift in focus toward AI agent development and capabilities. This c
arXiv:2605.22155v1 Announce Type: new Abstract: Symbolic methods are generally not considered competitive with strong modern learners on realistic supervised tasks. We evaluate Algebraic Machine Learn
arXiv:2511.10619v2 Announce Type: replace Abstract: The improving multi-armed bandits problem is a formal model for allocating effort under uncertainty, motivated by scenarios such as investing resear
arXiv:2605.21646v1 Announce Type: new Abstract: Prototype-based explanations offer an intuitive, example-based approach to support the interpretability of machine learning black box classifiers but of
Also applies to selling b2b saas Spoke with a late-30s girlfriend in Dallas who went on a date last night with a late-50s bachelor from NYC. They were introduced via another matchmaker. She said the v
Gary Marcus humorously describes riding an airport monorail as an example of a geofenced autonomous vehicle, highlighting how existing transportation systems already operate with limited autonomy with
arXiv:2605.22432v1 Announce Type: new Abstract: Modern deep learning commonly relies on AdamW with prescribed learning rate schedules, but recent works challenge both components: Schedule-Free optimiz
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:2509.09088v3 Announce Type: replace Abstract: We study the Riemannian geometry of the Deep Linear Network (DLN) as a foundation for a thermodynamic description of the learning process. The main
arXiv:2605.21968v1 Announce Type: new Abstract: Optimization is essential in deep learning. The foundational method upon which most optimizers are built is momentum-based stochastic gradient descent.
And just like that, it’s completely VANISHED from the media. A sitting congressman, Ted Lieu, said on the record the Epstein files are being blocked because they show Trump raped and threatened to kil
another of the dudes going after me (Theo) is perhaps paid by OpenAI 🙄 He doesn’t work for them, but he likely has or has had some paid partnership with them, because they’ve invited him onto their ca
arXiv:2605.22222v1 Announce Type: new Abstract: Partial differential equation (PDE) foundation models are pretrained networks that forecast how physical fields like velocity and pressure evolve from a
Natalie Lung / Bloomberg: As the US House probes Airbnb's use of Chinese AI models, CEO Brian Chesky says the company is not sharing data with Chinese firms and uses open-source models — Airbnb Inc. C
arXiv:2605.22372v1 Announce Type: new Abstract: Vision Transformers (ViTs) face severe computational bottlenecks due to the quadratic complexity of self-attention at high resolutions. Existing token r
arXiv:2605.21615v1 Announce Type: cross Abstract: Existing binary corpora typically capture only one or two axes of binary variation: they either provide cross-compiler builds without a temporal axis,
AsymFLUX.2-klein-9B is a pixel-space text-to-image model finetuned from FLUX.2-klein-base-9B using the AsymFlow method. The model is noted for producing sharp textures with strong adherence and compos
arXiv:2605.22416v1 Announce Type: new Abstract: Hybrid language models like Jamba mix attention layers with State Space Models (SSMs), creating two memory cache types with opposite profiles: Key-Value
arXiv:2510.16590v2 Announce Type: replace Abstract: Applications of machine learning in chemistry are often limited by the scarcity and expense of labeled data, restricting traditional supervised meth
arXiv:2512.21132v2 Announce Type: replace-cross Abstract: As large language models (LLMs) see wide adoption in software engineering, the reliable assessment of the correctness and security of LLM-gene
arXiv:2605.22262v1 Announce Type: cross Abstract: Audio context determines which sound components and sources are relevant and which can be perceived as irrelevant (noise) by listeners. For example, t
arXiv:2605.21560v1 Announce Type: new Abstract: Deploying neural networks on microcontroller units (MCUs) is critical for edge intelligence but remains challenging due to tight memory, storage, and co
b9294 is a llama.cpp release that includes improvements to OpenCL kernels for AMD Adreno GPUs, specifically generalizing MoE (Mixture of Experts) kernel implementations. The release provides pre-built
b9296 is a build release of llama.cpp , the C/C++ implementation for efficient large language model inference. As an intermediate build in the llama.cpp release cycle, it likely includes recent bug fi
The search results show information about llama.cpp releases but don't contain specific details about build b9297. Based on the context and numbering (b9297 is a recent build after b9294), b9297 is li
arXiv:2605.22191v1 Announce Type: new Abstract: Bandit convex optimization (BCO) is a fundamental online learning framework with partial feedback, where the learner observes only the loss incurred at
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:2603.02938v2 Announce Type: replace Abstract: Graph-based tasks in the zero-shot setting remain a significant challenge due to data scarcity and the inability of traditional Graph Neural Network
arXiv:2605.21820v1 Announce Type: new Abstract: Self-driving laboratories or autonomous experimentation are emerging as transformative platforms for accelerating scientific discovery. Bayesian optimiz
arXiv:2605.21556v1 Announce Type: new Abstract: Guaranteed display advertising is crucial for platform monetization, yet existing methods often operate under a single-slot assumption, limiting their a
arXiv:2602.04768v2 Announce Type: replace Abstract: Graph-structured data underpins many critical applications. While foundation models have transformed language and vision via large-scale pretraining
arXiv:2605.22468v1 Announce Type: new Abstract: Cross-subject generalization in biomedical time-series refers to training on data from some subjects and testing on unseen subjects.The key challenge is
Boring Company’s goal is to solve traffic in cities and one day build Hyperloop high-speed transit between city centers See how Prufrock continuously mines - pushing and building at the same time. The
This appears to be a satirical or false claim, as 'Chief Gyatt Officer' is not a legitimate corporate position and such a significant personnel announcement would not use slang terminology. The post l
arXiv:2511.18159v2 Announce Type: replace Abstract: Masked diffusion models (MDMs) are a promising alternative to autoregressive models (ARMs), but they suffer from inherently much higher training var
British police are hiding Henry Nowak’s final Snapchat and police bodycam footage. 18-year-old Henry Nowak was stabbed to death in Southampton. His Snapchat videos captured the attacker carrying a 21c
arXiv:2510.10129v2 Announce Type: replace Abstract: Retrieval-Augmented Generation (RAG) systems suffer from severe time-to-first-token (TTFT) bottlenecks due to long input sequences. Existing KV cach
arXiv:2605.21566v1 Announce Type: new Abstract: Machine learning models for chronic kidney disease (CKD) risk prediction often post strong discrimination scores on internal test sets. Calibration and
arXiv:2605.22075v1 Announce Type: new Abstract: Diabetes is a global health burden, and early detection is critical for timely intervention. This study explores a non-invasive, data-driven framework t
Can frontier models forecast scientific progress? Mostly no, but here is why. This work looks at 4,760 scientific events across disciplines. Frontier models can identify plausible research directions
arXiv:2605.22221v1 Announce Type: new Abstract: Backtracking search underlies classical constraint solvers, planners, and theorem provers. Recent transformer-based reasoning systems explore search tre
arXiv:2605.22043v1 Announce Type: new Abstract: Multivariate time series (MTS) classification is foundational to pervasive computing and financial analysis, yet existing multi-scale paradigms are ofte
arXiv:2605.21846v1 Announce Type: cross Abstract: Causal discovery from multivariate time series is challenging when causal effects may occur both across time and within the same sampling interval. Th
arXiv:2605.21928v1 Announce Type: new Abstract: Estimating treatment effects from observational data requires choosing an adjustment set, but valid adjustment depends on an unknown causal graph. Graph
arXiv:2605.21915v1 Announce Type: cross Abstract: Congestion controllers (CCs) are critical to network performance, and yet their robustness under adverse conditions remains insufficiently understood.
arXiv:2603.21743v4 Announce Type: replace Abstract: Building virtual cells with generative models to simulate cellular behavior in silico is emerging as a promising paradigm for accelerating drug disc
arXiv:2605.22437v1 Announce Type: cross Abstract: Vision processing units and other commercial neural-network inference accelerators are increasingly deployed in safety-relevant edge applications, but
arXiv:2605.22305v1 Announce Type: new Abstract: We analytically solve the Mountain Car problem, a canonical benchmark in RL, and derive an optimal control solution, closing a gap after 36 years. This
arXiv:2605.21963v1 Announce Type: new Abstract: Long-horizon clinical simulation -- predicting how a patient's physiology evolves over years under specified interventions -- is central to chronic-dise
arXiv:2605.22684v1 Announce Type: new Abstract: Time Series Foundation Models (TSFMs) have become a new component of the state-of-the-art in general time series forecasting. However, adapting them to
arXiv:2605.22703v1 Announce Type: new Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) has emerged as a central paradigm for scaling LLM reasoning, yet its optimization often suffers fr
Matthew Prince / Wall Street Journal: Cloudflare CEO Matthew Prince says AI won't replace builders or sellers, but it will affect middle managers, operations jobs, and other “measuring” positions — Th
arXiv:2603.25958v2 Announce Type: replace Abstract: The Minkowski weighted k-means (mwk-means) algorithm extends classical k-means by incorporating feature weights and a Minkowski distance. We first s