Knowledge catalogue
arXiv:2607.06621v1 Announce Type: new Abstract: The pre-softmax score of an attention head is a bilinear form score(i,j) = x_i^T M x_j in a learned operator M = W_q^T W_k. Because M is generally non-s
arXiv:2607.06652v1 Announce Type: new Abstract: Rough path signatures are a universal feature map for continuous paths and, via the expected signature, characterise path distributions. These guarantee
arXiv:2607.07626v1 Announce Type: cross Abstract: Reliable confidence estimation is essential for deploying large language models (LLMs) in confidence-aware systems, where downstream decisions such as
Got this setup in Claude Code to trace models routed through @merge_api! Being able to trace what your agents are doing is so valuable, I love open source 🙌 We built a plugin that traces every Claude
arXiv:2602.18164v3 Announce Type: replace Abstract: Accurate state estimation and multi-modal perception are prerequisites for autonomous legged robots in complex, large-scale environments. To date, n
This post compares Grok's code generation capabilities favorably against Claude Code and OpenAI's Codex, claiming superior performance particularly in Grok 4.5's speed and functionality. The author as
Here is my other heavily used pattern. Evaluator/Judge: Fable 5 Executor: GPT-5.5 I no longer wait for frontier models or am loyal to any. I now spend more time on better orchestration, harness, skill
Ollama announced support for running multiple open-source language models locally, emphasizing accessibility and ease of deployment for users who want to use AI models without relying on cloud service
I appreciate the many xAI and Cursor engineers who dedicated their time to addressing feedback from Tesla. I remember meeting Andrew a few weeks after he was hired and telling him that I needed a bett
arXiv:2607.07316v1 Announce Type: new Abstract: This article offers a comprehensive overview of mechanistic interpretability, an emerging field that seeks to reverse-engineer the internal algorithms o
Kurt Wagner / Bloomberg: Meta launches a Meta Model API, which Mark Zuckerberg says will have “aggressive and attractive” pricing at ~25% of the cost of OpenAI's and Anthropic's models — In a crowded
Julie Bort / TechCrunch: Ollama, which helps developers run open-weight AI models locally, raised a 65M Series B led by Theory Venture, following a 15M Series A led by Benchmark — The popular open sou
Unified identity security platform provider Permiso Security Inc. today launched the Risk Score Engine, a model that assigns continuous, multidimensional risk scores to every human, machine and artifi
arXiv:2607.07425v1 Announce Type: cross Abstract: Many biological processes are governed by complex dynamical mechanisms that remain incompletely understood despite increasing volumes of experimental
SensorFM is a foundation model that analyzes multimodal wearable sensor signals from devices like smartwatches and fitness trackers to generate insights into health and activities. The model was train
arXiv:2607.06748v1 Announce Type: cross Abstract: Smart home automation platforms increasingly rely on user-authored YAML configuration files to define device behaviors, but these files are prone to s
NVIDIA's NeMo framework addresses the challenge of limited, imbalanced financial NLP data by generating synthetic financial news headlines to fill gaps for trading research, risk modeling, and surveil
The upcoming wave of SpaceXAI Grok updates is insane Grok 4.5: The 1.5T foundation model is being refined almost daily, and its context window is expected to jump to 1M tokens, possibly as soon as nex
arXiv:2607.06799v1 Announce Type: cross Abstract: Evaluating uncertainty in AI-generated SQL queries requires estimating whether a query is correct, where correct means it executes to the same result
arXiv:2607.06291v1 Announce Type: new Abstract: Game worlds have traditionally been built through labor-intensive production pipelines, making them costly to develop, difficult to customization, and e
arXiv:2607.05750v1 Announce Type: new Abstract: Computer-aided design (CAD) for industrial components requires long-horizon procedural modeling, robust feature dependencies, editable parametric geomet
arXiv:2607.06484v1 Announce Type: cross Abstract: Poisoning attacks against public datasets lead to major concerns, such as (i) misclassification of perceived objects when the poisoned data is used fo
arXiv:2607.05898v1 Announce Type: new Abstract: Evaluating whether unlearning algorithms truly remove training data influence remains an open challenge. We propose a practical auditor that computes da
Based on the available information, b9905 is a build-tagged release from the llama.cpp project, which is an open-source C/C++ inference engine that powers most of the local-AI ecosystem . The project
llama.cpp is an open-source software library that performs inference on various large language models , and the project ships continuous build-tagged releases rather than traditional semantic versioni
B9932 is a continuous build-tagged release from the llama.cpp project , an open-source C/C++ inference engine for running large language models locally. llama.cpp performs inference on various large l
arXiv:2607.05773v1 Announce Type: new Abstract: As Large Language Models (LLMs) evolve into autonomous agents, traditional static evaluation fails to capture multi-step decision-making. We introduce A
arXiv:2607.06522v1 Announce Type: new Abstract: Vision-language models (VLMs) struggle to generalize in interactive physical reasoning, particularly under unseen tasks and environments. Two key failur
Creator @8bit_e reimagined one of cinema's most iconic scenes in ' the Terminator ' using ComfyUI + Wan 2.2 Animate and some masking. They were most likely limited by both the budget and the technolog
arXiv:2607.05462v1 Announce Type: cross Abstract: As AI agents are incorporated into life science workflows, the capabilities that speed discovery might also enable misuse. We present BioSecBench-Refu
arXiv:2607.05902v1 Announce Type: cross Abstract: Chamber music, as a highly precise multi-part interactive system, contains a logic of 'role assignment and dynamic interaction' that provides an extre
arXiv:2607.05869v1 Announce Type: cross Abstract: Robust robotic grasping of novel objects requires datasets that simultaneously provide photorealistic RGB-D observations, physically validated grasp q
Great writeup from the University of Oxford. It's a taxonomy of LLM-based agent limitations. Good read for anyone shipping with agents. Benchmark scores keep climbing, yet the same agent failures resu
Grok 4.5 demonstrated capability in website creation by generating a visually appealing website about black holes as an example of its web development functionality. The post was shared on X (formerly
Grok groks engineering. Next month’s release will be another step-change improvement, as we close the loop on solving real-world engineering problems at Tesla, SpaceX, Neuralink and Boring Company. Gr
OpenAI provides resources and guidance to help K-12 educators develop practical skills in teaching and implementing artificial intelligence concepts in their classrooms. The initiative aims to equip t
arXiv:2607.05475v1 Announce Type: cross Abstract: Deploying Large Language Models (LLMs) on mobile devices enhances privacy and reduces latency, but is severely bottlenecked by hardware inefficiency.
arXiv:2607.06157v1 Announce Type: cross Abstract: Deliberation plays a crucial role in collaboration; when humans work together, they naturally engage in communication to align information and reach a
This post discusses Baseten's partnership efforts to democratize access to open-weight models for use in AI agents, making advanced model capabilities available to a broader audience. The initiative a
arXiv:2503.13212v3 Announce Type: replace Abstract: Alignment between human brain networks and artificial models has become an active research area in vision science and machine learning. A widely ado
arXiv:2607.05690v1 Announce Type: new Abstract: Language agents run a loop - observe, reason, act - but the memory they reason over sits outside it: a store queried at most once per turn. We study the
If you’re reading this, you’ve likely already done the hard work to prove your qualifications with a Google Cloud certification. And good for you — research shows that’ll help you get ahead. Certified
arXiv:2607.05915v1 Announce Type: new Abstract: PCB routing is the task of connecting the nets of a board with copper traces under strict design rules, yet learning-based methods still lag behind rule
arXiv:2506.03218v2 Announce Type: replace-cross Abstract: The EU has become one of the vanguards in regulating the digital age. A particularly important regulation in the Artificial Intelligence (AI)
arXiv:2607.06133v1 Announce Type: cross Abstract: Modern software systems increasingly depend on data for analysis, prediction, testing, and decision-making. Yet many important domains, including medi
arXiv:2505.11602v3 Announce Type: replace Abstract: Selective State-Space Models (SSMs) such as Mamba have become central to long-sequence modeling. Still, their stability is poorly understood: their
ComfyUI discusses innovations and improvements to its node-based production pipeline for generative AI workflows, likely covering updates to how users can construct and optimize image generation proce
This post references a notable GitHub repository that the commenter considers particularly valuable for those with a serious interest in AI development. The tweet appears to be a recommendation or end
Superhuman Inc., the company formerly known as Grammarly, today announced the launch of Docs, a product that enables multiple users to collaborate on writing using artificial intelligence. Docs contai
Elon Musk announced the availability of Grok 4.5, xAI's large language model, integrated into Cursor, a popular AI-assisted code editor. This integration allows developers to leverage Grok's capabilit
IBM Quantum's Q2 2026 updates likely showcase advancements in quantum computing hardware, software, or services, including new processor capabilities, improved error correction, expanded cloud access,
Wispr Flow kept replacing the word 'Anthropic' with the word 'Perplexity'. They sound nothing alike and are direct competitors. After flagging this to them back in April, they only just now emailed me
Software-as-a-service (SaaS) is evolving into Agents-as-a-service (AaaS). Instead of isolated applications, developers are creating AI agents that interoperate using standardized open protocols such a
arXiv:2602.02908v2 Announce Type: replace-cross Abstract: Diffusion models trained on different, non-overlapping subsets of a dataset often produce strikingly similar outputs when given the same noise
arXiv:2507.04136v2 Announce Type: replace Abstract: This survey offers a comprehensive foundation on the integration of RL with language models, highlighting prominent algorithms such as Proximal Poli
arXiv:2607.03860v1 Announce Type: new Abstract: The Strong Lottery Ticket Hypothesis (SLTH) asserts that sufficiently overparameterized, randomly initialized neural networks contain sparse subnetworks
arXiv:2607.04426v1 Announce Type: new Abstract: Embodied AI is moving from isolated perception or action modules toward physical agents that understand, plan under goals, act through robot bodies, mon
arXiv:2607.05120v1 Announce Type: cross Abstract: AI agents act on behalf of user prompts, consuming external data and taking actions based on the agent context. Prior research on AI agent security ha
arXiv:2607.03233v1 Announce Type: cross Abstract: The rapid growth of publicly available digital information has rendered manual open-source intelligence (OSINT) analysis insufficient for modern intel
arXiv:2509.17255v2 Announce Type: replace-cross Abstract: We present the first language-model-driven agentic artificial intelligence (AI) system to autonomously execute multi-stage physics experiments