Knowledge catalogue
arXiv:2509.15121v2 Announce Type: replace-cross Abstract: We investigate a WIMP dark matter (DM) candidate in the form of a singlino-dominated lightest supersymmetric particle (LSP) within the Z_3-sym
arXiv:2605.26900v1 Announce Type: new Abstract: A fundamental open question in self-supervised learning (SSL) is the explicit characterization of the optimal geometry of the learned representations. R
arXiv:2605.26898v1 Announce Type: cross Abstract: Large Language Models (LLMs) can generate functional source code from natural-language prompts, but often fail to consistently follow higher-level arc
arXiv:2504.02775v2 Announce Type: replace Abstract: We aim to solve unsupervised anomaly detection in a practical challenging environment where the normal dataset is both contaminated with defective r
the future of Continual Learning will rely on building to systems to ingest, understand, & apply knowledge from Agent Traces at scale had a blast presenting LangSmith Engine with @bentannyhill to show
arXiv:2605.24823v1 Announce Type: new Abstract: Manufacturing has passed through four widely recognized paradigms - mechanization, electrification, programmable automation, and Smart Manufacturing - e
arXiv:2512.10961v2 Announce Type: replace-cross Abstract: A growing body of empirical research suggests that generative AI narrows performance gaps between novice and expert workers on routine tasks--
arXiv:2605.25619v1 Announce Type: new Abstract: In the paper we show that there is an analogy between the operations occurring in a layer of a transformer (projections and layer normalizations, disreg
Software-as-a-service security company AppOmni Inc. today launched Marlin AI, a new autonomous artificial intelligence capability built into its platform that handles correlation, investigation and gu
arXiv:2601.03624v3 Announce Type: replace Abstract: The rapid evolution of Large Language Models (LLM) and subsequent Agentic AI technologies requires systematic architectural guidance for building so
In this post you'll learn how to build a multi-agent campaign review system that demonstrates parallel reasoning, context persistence, and traceable execution paths using an integrated architecture th
arXiv:2605.24696v1 Announce Type: cross Abstract: Streaming network intrusion detection systems must process flows continuously while keeping memory bounded, but most current methods leave alerting th
arXiv:2605.24144v1 Announce Type: cross Abstract: Large Language Models (LLMs) have achieved impressive performance across diverse domains but remain inefficient during the autoregressive decoding pha
arXiv:2605.25645v1 Announce Type: cross Abstract: We present the first end-to-end demonstration of fine-tuning and serving Google's Gemma 4 31B model on TPU hardware, providing an empirical comparison
arXiv:2602.21479v2 Announce Type: replace-cross Abstract: Across many risk-sensitive areas, it is critical to continuously audit machine learning systems as we receive more data to quickly determine i
arXiv:2406.09079v5 Announce Type: replace Abstract: Deep reinforcement learning agents progressively lose representational capacity during training: neurons become dormant, removing active capacity fr
Huge one for developers building with AI. Excited to announce @ClementDelangue (CEO @huggingface) is joining DASH 2026 for a fireside chat with @oliveur. Open source changed software, open models are
Huge thanks to @ComfyUI for publishing a deep-dive case study on how we’re building enterprise-grade, scalable AI pipelines. Arron Award Winning work for AI workflow. Read the full breakdown: https://
arXiv:2605.24659v1 Announce Type: new Abstract: LLM-based agents are increasingly deployed for complex tasks requiring planning, tool use, and interaction with external services. Their reliance on unt
Microsoft Copilot Cowork Exfiltrates Files The biggest challenge in designing agentic systems continues to be preventing them from enabling attackers to exfiltrate data. In this case Microsoft Copilot
Mistral-7B v0.3 model achieves significant memory optimization when running at 128K context length in llama.cpp, reducing live VRAM usage from 22,657 MiB to 13,235 MiB while maintaining minimal perfor
A comparative test of three AI image generation models—SenseNova U1, GPT Image 2, and Nano Banana 2—evaluating their performance on infographic generation tasks. GPT Image 2 proved more reliable for e
arXiv:2306.14853v5 Announce Type: replace-cross Abstract: In this work, we consider bilevel optimization when the lower-level problem is strongly convex. Recent works show that with a Hessian-vector p
The way we work has fundamentally changed. From automated agents to sophisticated AI services, Generative AI (GenAI) has become a daily tool for a vast majority of employees. But with this rapid adopt
Artificial intelligence penetration testing startup Novee Cyber Security Ltd. today launched Agentic Fix, a new capability that pushes validated exploit findings directly into the AI coding agents dev
arXiv:2601.10457v3 Announce Type: replace Abstract: Although the Gradient Boosted Decision Trees (GBDTs) dominate industrial tabular applications, upgrading legacy models in high-concurrency productio
arXiv:2311.11342v5 Announce Type: replace Abstract: Stochastic bilevel optimization finds widespread applications in machine learning, including meta-learning, hyperparameter optimization, and neural
arXiv:2506.09084v2 Announce Type: replace-cross Abstract: Whole-page optimization (WPO) decides how search and recommendation results are surfaced to users, and large language models (LLMs) open a new
arXiv:2605.24920v1 Announce Type: cross Abstract: Quaternion neural networks are parameter-efficient and model multidimensional dependencies by representing four related features as a single entity. H
arXiv:2605.24945v1 Announce Type: cross Abstract: Accurate evaluation of weather forecasting models is critical for their reliable deployment in real-world applications. However, existing benchmarks p
arXiv:2605.24428v1 Announce Type: new Abstract: Stochastic process-based molecular graph generators have become the state of the art for template-free single-step retrosynthesis. However, these models
Vercel has announced that Sandbox persistence is now generally available (GA), a feature that allows developers to maintain state and data across sandbox environments. This capability enables more per
arXiv:2605.25674v1 Announce Type: new Abstract: The loss and the norm of its gradient separate the healthy and the pathological regimes of neural-network training only weakly, whilst the curvature of
arXiv:2605.24416v1 Announce Type: new Abstract: Human cognitive performance is constrained by limited mental resources, yet continuous computational estimation of cognitive capacity dynamics remains a
arXiv:2409.08379v4 Announce Type: replace-cross Abstract: Large Language Models (LLMs) are reshaping knowledge work, yet their impact on voluntary, self-guided open innovation forums (contributors cho
arXiv:2605.23918v1 Announce Type: cross Abstract: The AI inference industry keeps models loaded in GPU memory around the clock to avoid cold-start latency, implicitly treating idle power as a fixed co
Today's Training Data episode takes us BTS on the infrastructure challenges required to do large RL runs at scale, featuring @ellev3n11 (Composer Lead at @cursor_ai) and @dzhulgakov (Co-Founder at @Fi
arXiv:2507.10593v3 Announce Type: replace-cross Abstract: Every LLM tool call is structurally an RPC -- a function name, JSON arguments, and a serialized result -- yet each protocol (native Python, MC
arXiv:2605.25612v1 Announce Type: cross Abstract: The observation that activation sparsity emerges in MLP blocks of standardly trained Transformers offers an opportunity to drastically reduce computat
Trace data is literally worth its weight in gold these days, if you know what to do with it! As has been established, creating effective agents requires shipping early, observing behavior, and iterati
arXiv:2507.21556v3 Announce Type: replace Abstract: The cognitive reality of irregular morphological patterns has been debated for decades: do speakers extend them to novel forms, or are they lexical
Apple's 599 MacBook Neo launched in March 2026 at approximately half the price of the MacBook Air, directly competing with lower-cost Windows PCs and triggering significant industry reaction. PC maker
arXiv:2605.23243v1 Announce Type: cross Abstract: We evaluate whether frontier LLMs are ready for cybersecurity through a dual-mode benchmark: white-box function-level vulnerability detection (VulnLLM
arXiv:2605.23416v1 Announce Type: new Abstract: Acoustic vowel dynamics have some speaker-identifying characteristics, which have been ascribed to individual properties of articulatory strategies: for
arXiv:2605.22866v1 Announce Type: new Abstract: Compound AI systems route tasks through hierarchies of specialised components. Attribution is dominated by Shapley-based methods (SHAP), which decompose
arXiv:2605.22924v1 Announce Type: new Abstract: Serving personalized content on mobile devices has traditionally required pooling sensitive user data on centralized servers, a practice increasingly at
Simon Willison discusses whether coding agents should automatically generate tests alongside the code they produce, addressing a key quality assurance consideration in AI-assisted development. This li
arXiv:2511.13904v2 Announce Type: replace Abstract: Cameras are a core sensing modality in modern intelligent transportation systems (ITS), providing rich visual information on road-user activities. M
arXiv:2605.22848v1 Announce Type: cross Abstract: Global food security depends on predicting crop responses to climate variability, yet process based crop models remain too computationally expensive f
Grok foundation model V9-Medium (1.5T) has finished training. Evals look good. A lot of Cursor data was added in supplementary training and there is more to come. Fine-tuning is underway and reinforce
arXiv:2605.23651v1 Announce Type: new Abstract: While factual correctness and task-performance have been in focus of Large Language Model (LLM) research for a long time, the fundamental question of ho
arXiv:2505.13893v2 Announce Type: replace Abstract: Recent advances in large language models (LLMs) have intensified efforts to fuse heterogeneous open-source models into a unified system that inherit
I've yet to see, or hear of a company that is winning against its competition, because said company is spending more on AI tools, or using it better than the competition. Ways I see companies win: - b
arXiv:2605.23871v1 Announce Type: cross Abstract: We develop a gradient flow on the space of probability measures defined on matrix-valued parameters induced by regularized Muon, an analytically smoot
Dropped this morning by the Vatican: Magnifica Humanitas of His Holiness Pope Leo XIV on Safeguarding the Human Person in the Time of Artificial Intelligence. This is a very interesting document. It's
arXiv:2605.23673v1 Announce Type: new Abstract: Graph Neural Networks (GNNs) have become important machine learning tools for graph analysis, and its explainability is crucial for safety, fairness, an
arXiv:2605.23597v1 Announce Type: new Abstract: Matching person names across heterogeneous records is a core challenge in entity resolution, especially within linguistically and culturally complex env
arXiv:2605.22984v1 Announce Type: cross Abstract: Test-Time Training (TTT) is an emerging paradigm that enables models to adapt their parameters during inference, improving performance on tasks such a
arXiv:2605.23348v1 Announce Type: cross Abstract: AI power demand is growing at an unprecedented rate while power grids are often ailing and struggle to keep up. Grid expansion comes with high capital
Q: How are job postings for software engineers rising rapidly despite AI agents automating coding? A: Because there’s far more code to manage than ever before. We’re already seeing a 14x YoY increase