Knowledge catalogue
arXiv:2510.17139v3 Announce Type: replace Abstract: Recent advances in large language models (LLMs) have led to a surge of interest in query augmentation for information retrieval (IR). Two main appro
arXiv:2606.30788v1 Announce Type: cross Abstract: Language models are often adapted in stages: a public skill phase, a private memory phase, and a later safety phase that learns to refuse outputs tied
arXiv:2606.22678v2 Announce Type: replace-cross Abstract: Agentic coding harnesses - such as Agent-Skills, Superpowers, and Agent-Rigor - are increasingly deployed to augment underlying LLMs for real-
arXiv:2507.11061v3 Announce Type: replace-cross Abstract: Recent advances in 3D neural representations and instance-level editing models have enabled the efficient creation of high-quality 3D content.
arXiv:2606.14027v3 Announce Type: replace-cross Abstract: Agentic browsers integrate autonomous AI agents into web browsers, enabling users to accomplish web tasks through natural-language instruction
arXiv:2606.31875v1 Announce Type: new Abstract: Autonomous vehicles (AVs) must navigate not only motion-based hazards but also socially complex situations whose danger is constituted by inter-agent re
Editor’s note: SOCRadar is a leading cybersecurity company that provides threat intelligence to businesses worldwide. As the volume of cyber threats continued to grow, SOCRadar needed to modernize its
arXiv:2606.31741v1 Announce Type: cross Abstract: While semantic embeddings are rigorously evaluated on the Massive Text Embedding Benchmark, the evaluation of style embeddings remains fragmented, wit
arXiv:2606.31259v1 Announce Type: cross Abstract: Diffusion-based text-to-audio (TTA) models achieve impressive synthesis quality but suffer from high inference latency due to iterative multi-step den
arXiv:2606.31464v1 Announce Type: cross Abstract: Recent advances in Large Language Models (LLMs) have motivated their adoption across a wide range of domains, including Artificial Intelligence (AI) f
arXiv:2606.31272v1 Announce Type: cross Abstract: AI agents increasingly acquire and execute skills at runtime: bundles of prompt instructions, executable code, and tool declarations fetched from mark
This is today’s edition of The Download, our weekday newsletter that provides a daily dose of what’s going on in the world of technology. Claude Science is Anthropic’s newest flagship product At an ev
The Great Algae Conspiracy Theory, sure to go down in history along with Hugo Chavez stole the 2020 election, the windmills are killing us, and other Trump classics Trump on the Reflecting Pool: 'They
This is pretty concerning. You could still do this at the API level to some degree, but they seemingly just blatantly put it right into the code? This is why open harnesses and agents are a much bette
🚨 TRUMP’S FINANCIAL DISCLOSURE JUST DROPPED…AND IT’S WORSE THAN YOU THOUGHT. The U.S. Office of Government Ethics released Donald Trump’s 927-page financial disclosure today. Here’s what a sitting U.S
We are at a turning point: many of the decisions we make about AI today will permanently shape our future. Governments and the public need to clearly understand the impacts, risks, and opportunities o
arXiv:2606.31612v1 Announce Type: new Abstract: Mobile GUI agents increasingly face long-horizon tasks that require reading, updating, and reusing task-relevant data across pages and applications. Exi
When boomer companies get high Anthropic bill, they set spend limits When I see a nearly million dollar Anthropic monthly bill, my first reaction is to complain about use of shitty Haiku models Imagin
arXiv:2507.14661v2 Announce Type: replace-cross Abstract: Semi-supervised domain adaptation (SSDA) seeks to achieve accurate predictions in a target domain with limited labeled target data by exploiti
arXiv:2606.31575v1 Announce Type: new Abstract: Reinforcement learning (RL) has become a powerful tool for propelling Large Language Models (LLMs) beyond imitation-based training towards more robust r
This post compares the outputs of three AI models—GLM-5.2, Fugu Ultra, and Fable 5—using an identical one-shot prompt to evaluate their performance, with the author expressing a preference for Fable 5
Wiki!!! One unexpected outcome of this is that I'm now using the wiki as the ONLY place I run Claude Code I use it as a master controller for all of my repos, kicking off cross-repo tasks and using To
This entry documents a Wordle puzzle solution (puzzle #1,837) shared by Anthropic on X/Twitter, showing the complete sequence of guesses and letter feedback that led to solving the word on the sixth a
This appears to be a Wordle game result shared by Anthropic on X (formerly Twitter), showing the solution was found in 4 attempts with a specific pattern of correct (green), present but misplaced (yel
arXiv:2606.29719v1 Announce Type: cross Abstract: Measurements of proprietary LLM evaluators can become invalid within weeks -- we document one case and provide the diagnostic framework to detect it.
arXiv:2606.29193v1 Announce Type: cross Abstract: LLM-based agents are reshaping microservice operations into AgentOps, where benchmarks are key to evaluating failure diagnosis over multimodal observa
arXiv:2606.29806v1 Announce Type: cross Abstract: Action-values are foundational to many control algorithms such as Q-learning. Therefore learning action-values efficiently is central to reinforcement
arXiv:2502.18864v2 Announce Type: replace Abstract: Scientific discovery is driven by scientists generating novel hypotheses for complex problems that undergo rigorous experimental validation. To augm
arXiv:2606.28326v1 Announce Type: cross Abstract: This research aims to solve the challenge of video retrieval from massive datasets, caused by ambiguous user queries. Prevailing single-round retrieva
arXiv:2606.28644v1 Announce Type: cross Abstract: Parameter settings in evolutionary algorithms and metaheuristics are important because such parameter values can influence the performance of algorith
Anthropic has integrated Claude with Modal's serverless compute platform, enabling scalable cloud infrastructure for scientific computing workflows. This integration allows Claude to leverage Modal's
@anthropicai: Anthropic says the Department of Commerce has lifted export controls on Claude Fable 5 and Mythos 5 and that it will begin restoring access Wednesday — We've received notice that the Dep
After weeks of negotiating with the Trump administration, Anthropic is finally going to be able to bring Claude Fable 5 back online. In a post on X, Anthropic said it plans to begin restoring access W
arXiv:2606.29519v1 Announce Type: new Abstract: Long-range learning is hard for recurrent networks trained with stochastic gradient descent, because the influence of a past input fades with the lag el
arXiv:2606.30047v1 Announce Type: new Abstract: Metric feed-forward 3D reconstruction for panoramic data remains under-explored due to the lack of large-scale panoramic RGB-D training data. We present
arXiv:2606.29869v1 Announce Type: cross Abstract: Knowledge distillation (KD) is a key technique for compressing Large Language Models (LLMs), yet methods relying on a single KL objective often fail t
arXiv:2606.29706v1 Announce Type: cross Abstract: Telecom question answering (QA) is a challenging setting for retrieval-augmented generation (RAG): evidence is fragmented across standards, papers, en
Russell Brandom / TechCrunch: AWS launches an internal organization for AI-focused forward-deployed engineers, backed by $1B in resources, following OpenAI and others in launching FDE teams — As compa
Amazon Web Services Inc. said today it’s rolling out a new dedicated organization to bring agentic artificial intelligence systems, built on the same technology, to customers by embedding engineers in
arXiv:2606.28367v1 Announce Type: cross Abstract: Retrieval-augmented generation (RAG) is routinely extended with methods meant to improve retrieval: query expansion, hierarchical and cross-document s
arXiv:2409.05980v2 Announce Type: replace-cross Abstract: Rested and Restless Bandits are two well-known bandit settings that are useful to model real-world sequential decision-making problems in whic
arXiv:2606.30049v1 Announce Type: new Abstract: Visibility distance is critical to maritime navigational safety because it determines the effective observation range of shipborne and shore-based monit
arXiv:2606.30609v1 Announce Type: cross Abstract: Sparse Autoencoders (SAEs) are widely used to interpret large language models by decomposing activations into sparse, human-understandable features, b
arXiv:2606.29463v1 Announce Type: new Abstract: Recent advances in pathology foundation models have substantially improved patch and slide level representation learning from whole-slide images (WSIs).
arXiv:2606.30318v1 Announce Type: new Abstract: General-purpose robot policies should be modeled as dynamical systems, yet many VLA and generative imitation policies still rely on present observations
Claude Desktop is now available on Linux (Ubuntu and Debian) in beta. Alongside the browser and terminal, you now get a first-class desktop experience with Claude Code, Claude Cowork, and chat on all
At an event for pharmaceutical executives, biotech founders, and researchers on Tuesday, Anthropic announced Claude Science, a major new product intended to support scientific research in the same way
arXiv:2506.13932v3 Announce Type: replace-cross Abstract: The rise of large language models (LLMs) has led to dramatic improvements across a wide range of natural language tasks. Their performance on
arXiv:2606.30237v1 Announce Type: new Abstract: In our goal to develop personalised dysarthric speech recognition (DSR) models, this study compared the recognition performances of human listeners and
arXiv:2606.28984v1 Announce Type: cross Abstract: We give a single compositional setting in which gradient-based learning and Hamiltonian-style mechanics appear as functorial semantics. The syntax is
arXiv:2606.29801v1 Announce Type: new Abstract: Text-to-image diffusion models remain vulnerable to adversarial prompts that elicit disallowed content, motivating reliable inference-time controls. A p
Cool new paper from NVIDIA. Looks like agentic coding is moving into hardware design. HORIZON treats hardware design as repository-level code evolution. A Markdown harness becomes a project pack with
This article describes OpenAI's investigation and resolution of a longstanding bug in their data infrastructure that had persisted for 18 years, likely related to how core dumps (system memory snapsho
arXiv:2606.29563v1 Announce Type: cross Abstract: Large language models (LLMs) excel at complex tasks like question answering and summarization, thanks to their ability to handle long-context inputs.
arXiv:2606.30027v1 Announce Type: new Abstract: Color Fundus Photography (CFP) offers a low-cost and non-invasive route for ischemic heart disease (IHD) screening, but current studies are limited by s
arXiv:2606.28863v1 Announce Type: cross Abstract: AI systems increasingly exhibit behavior that differs systematically between evaluation and deployment contexts. Alignment faking, sandbagging, benchm
arXiv:2603.17863v2 Announce Type: replace-cross Abstract: Automating the development of machine learning algorithms has the potential to unlock new breakthroughs. However, our ability to improve and e
arXiv:2606.29379v1 Announce Type: cross Abstract: Gaussian splatting (GS) has garnered significant attention in VR/AR and digital content creation due to its explicit parameterization and efficient re
arXiv:2603.28049v3 Announce Type: replace Abstract: Autoregressive (AR)-Diffusion hybrid paradigms combine AR's structured semantic modeling with diffusion's high-fidelity synthesis, yet suffer from a
Earlier this month, the City of Starbase was excited to support residents, local fishermen, @SpaceX volunteers, and @SeaTurtleInc in rescuing 266-lb loggerhead Arlen from Boca Chica Beach jetties. She