Knowledge catalogue
You really need your own benchmarks. If you are translating hieroglyphics, use Gemini 3.5 Flash. If you are running a vending machine use Opus 4.8. (This is one reason why I am skeptical of just swapp
Your coding agent bill doubled and nobody can tell you why. Here's the actual reason: Claude Code, Cursor, and Copilot all log activity in different formats. The second your team uses more than one (t
Michael Nuñez / VentureBeat: Z.ai launches ZCode, an “Agentic Development Environment” optimized for its new GLM-5.2 model; Z.ai's GLM Coding Plan costs from 16.20 to 144 per month — The move marks th
arXiv:2607.01125v1 Announce Type: new Abstract: Zeroth-order (ZO) optimization enables fine-tuning large language models when backpropagation is unavailable or memory-prohibitive, but existing methods
arXiv:2606.31483v1 Announce Type: new Abstract: Personalized driving can improve the user acceptance of automated driving systems. However, existing methods still provide limited support for translati
arXiv:2404.10034v3 Announce Type: replace Abstract: Weakly Supervised Object Localization (WSOL) allows training deep learning models for classification and localization (LOC) using only global class-
arXiv:2505.03303v3 Announce Type: replace-cross Abstract: Lightweight convolutional neural networks are often compared using results obtained with different training recipes, input settings, and pretr
arXiv:2606.31763v1 Announce Type: new Abstract: Autonomous wet-lab experimentation requires more than plausible protocol text: biological intent, quantitative procedures, device constraints and experi
arXiv:2606.31041v1 Announce Type: new Abstract: Natural language-to-SQL (NL2SQL) over real-world enterprise databases remains significantly more challenging than on academic benchmarks. Enterprise sch
arXiv:2606.30837v1 Announce Type: cross Abstract: The number of trees is a central computational parameter in Random Forests: increasing it reduces finite-ensemble variability but increases training a
arXiv:2602.10528v2 Announce Type: replace-cross Abstract: We propose a novel swap-adversarial framework that mitigates high inter-subject variability and the high-dimensional low-sample-size problem i
arXiv:2606.30877v1 Announce Type: cross Abstract: Recent literature shows that large language models (LLMs) are useful for general-purpose tasks yet perform poorly on specific domain ones. One reason
arXiv:2606.30997v1 Announce Type: new Abstract: We present a three-phase deep reinforcement learning system for personalized portfolio management that addresses three limitations shared by all prior f
arXiv:2606.31532v1 Announce Type: new Abstract: Staff absenteeism imposes substantial operational costs in high-demand work environments such as healthcare, emergency services, meat processing, constr
arXiv:2606.30842v1 Announce Type: new Abstract: Outbreak transmission reconstruction treats epidemiological timing and transmission labels as deterministic ground truth; neither has been systematicall
arXiv:2606.31824v1 Announce Type: new Abstract: Long-wave infrared (LWIR) hyperspectral observations contain distance-dependent atmospheric absorption signatures, providing a physical basis for long-r
arXiv:2606.30702v1 Announce Type: cross Abstract: Structured tabular data dominates clinical medicine, yet existing benchmarks fail to reflect real-world properties like complex survey sampling, demog
arXiv:2606.31820v1 Announce Type: new Abstract: Large-scale capacitated vehicle routing problems (CVRPs) are commonly addressed using cluster-first route-second (CFRS) approaches that split a routing
Again, 2 weeks missed. No rehab. Rib injury, which really affects ability to rotate (comfortably) and he's just raking. He's on a heater. It is kind of unfathomable that Chase DeLauter missed two week
arXiv:2606.30970v1 Announce Type: new Abstract: Autonomous AI agents increasingly perform consequential actions on behalf of human principals, including financial transactions, external communications
“Agentic kernel optimization is the future of on-device inference” @xenovacom used Fable 5 to write kernels that pushed Gemma 4 to a massive 255 tok/s on WebGPU with M4. He shared the demo, so you can
arXiv:2606.31200v1 Announce Type: new Abstract: Generalizable robotic grasping in cluttered environments is essential for deploying manipulators in unstructured human spaces, yet existing VLM-based me
Agentic retrieval is changing the way retrieval-augmented applications are built, especially in domains like legal and fintech, where agents need to autonomously navigate large, evolving knowledge bas
arXiv:2601.15614v3 Announce Type: replace Abstract: Object-Goal Navigation (ObjectNav) requires an agent to autonomously explore an unknown environment and navigate toward target objects specified by
AlloyDB is an AI-native database—it isn’t just a passive data store, it intelligently understands and processes your data. With AlloyDB, you get industry-leading vector and hybrid search, near 100% ac
arXiv:2606.31159v1 Announce Type: cross Abstract: Large Language Models (LLMs) are rapidly transforming software development, yet their use in security-critical contexts raises a key question: do mode
arXiv:2605.11030v2 Announce Type: replace-cross Abstract: Closed-loop tool-using agents are increasingly evaluated in executable web, code, and micro-task environments, but benchmark reports often con
Anthropic PBC today debuted Claude Sonnet 5, a midrange large language model that outperforms its predecessor in several areas. The LLM will be the default option in the consumer tiers of the company’
Anthropic: Anthropic says Fable 5 will be available via usage credits for Claude users from July 7, and is working with partners to draft an AI jailbreak severity standard — On Friday, June 12, the US
Juro Osawa / The Information: Anthropic says it is rolling back a covert Claude Code tracking feature to identify users based in China or affiliated with Chinese AI labs, after backlash — Anthropic is
@anthropicai: Anthropic says “some routine tasks like coding and debugging” on Fable 5 “will fall back to Opus 4.8” in “the near term” as it works to “reduce false positives” — Claude Fable 5 will be
ARC-AGI-3 is built different, it has dumbfounded almost all regular attempts so far because it's so much harder than anything that came before. It has no rules, it's agentic and has no explicit goals,
arXiv:2606.31711v1 Announce Type: new Abstract: Faithfulness -- how precisely a generated image aligns with its prompt -- is increasingly central to the real-world utility of text-to-image (T2I) model
Security researchers at Armadin Inc. today detailed an attack chain that runs arbitrary commands as root inside the sandbox behind Anthropic PBC’s Claude Cowork, escaping the isolation layer, with a s
arXiv:2503.05785v2 Announce Type: replace-cross Abstract: Generative Artificial Intelligence (AI) tools such as ChatGPT, Copilot, or Gemini have a crucial impact on academic research and teaching. Emp
As generative AI tools continue to evolve, we believe it's more important than ever to know what's AI-generated and what isn't. That’s why @GoogleDeepMind launched SynthID in 2023—a technology that ad
arXiv:2606.31551v1 Announce Type: new Abstract: Training language models (LMs) remains a highly human-intensive process, even as frontier language model agents become increasingly capable at software
arXiv:2606.32007v1 Announce Type: new Abstract: We study agentic code generation in Dafny, where a model must generate both executable code and the proof artifacts for verification. We present AxDafny
arXiv:2606.30850v1 Announce Type: new Abstract: Large language models (LLMs) are typically deployed in multi-turn conversations, where each turn provides new evidence that should reduce epistemic unce
arXiv:2606.31308v1 Announce Type: new Abstract: This paper investigates the capability of Large Language Models (LLMs) to detect and classify floating-point errors statically in software code. We intr
This post humorously describes using Claude AI as a learning tool to understand Microsoft Teams functionality for first-time users, shared during an AI Engineer event discussion. The post suggests Cla
arXiv:2606.31338v1 Announce Type: cross Abstract: Recent music audio-language models achieve high accuracy on instrument question-answering benchmarks, but it remains unclear whether this reflects rob
arXiv:2606.30914v1 Announce Type: new Abstract: Event detection (ED) systems are typically evaluated on clean, curated text, leaving their robustness to real-world noise largely unexplored, particular
arXiv:2606.31002v1 Announce Type: new Abstract: Theorem-proving benchmarks evaluate proof search against fixed formal statements, but natural-language-to-Lean formalization must generate the formal st
arXiv:2606.30863v1 Announce Type: new Abstract: Agents typically assume an expert user -- one with well-formed preferences about what they want -- and default to clarifying questions whenever the task
arXiv:2606.31169v1 Announce Type: new Abstract: Existing AI-assisted oracle bone inscription (OBI) visual recognition and understanding studies mainly focus on character-level, ignoring the long-form
As enterprise generative AI transitions from simple, conversational chatbots to autonomous multi-agent workflows, developers face a critical bottleneck: scale. In a production environment, an enterpri
arXiv:2606.22723v2 Announce Type: replace Abstract: Although Large Language Models (LLMs) excel in many tasks, their assessment in Portuguese has received less attention, particularly for open-ended,
arXiv:2606.30943v1 Announce Type: new Abstract: Russian and Arabic are among the major languages of scientific communication. Language barriers impede the exchange of research results between these co
arXiv:2606.31508v1 Announce Type: new Abstract: Automatic speech recognition for children's reading remains underdeveloped for most African languages, including Bambara, despite its potential value fo
arXiv:2606.31371v1 Announce Type: cross Abstract: When large language model (LLM) agents adapt their behavior through evaluator feedback, systematic evaluator biases propagate into the agent's learned
arXiv:2606.31630v1 Announce Type: new Abstract: Language models increasingly write probabilistic programs (in NumPyro, Stan, or Pyro), but a program that compiles, runs, and passes every unit test can
arXiv:2606.30651v1 Announce Type: cross Abstract: Delirium is common in hospitalized patients and is often missed in routine care. We present a user-centered interactive machine learning (UC-iML) fram
@_catwu @simonw and I will be doing a fireside chat about 'This year in Claude' from 12:30pm-1:30pm at AIE in Expo Stage 2. We'll be covering a really wide range of topics and I think it will be reall
arXiv:2606.31435v1 Announce Type: new Abstract: Data refinement involves executing multi-step recipes over evolving text states, where both composition and execution order of processing operators dete
arXiv:2606.31796v1 Announce Type: cross Abstract: We study three complementary techniques for training compute-efficient language models. (1) Selective supervision and per-token efficiency. Selective
Minxiao Chang / South China Morning Post: Chinese robot maker UBTech launches U1, a line of humanoid robots for personal companionship with lifelike silicone skin and emotional AI, priced from $17,650
arXiv:2606.30689v1 Announce Type: cross Abstract: Spec-Driven Development (SDD) frameworks guide Large Language Model (LLM)-powered code generation through formal specifications, yet they differ funda
Vercel has restored access to Claude Fable 5 on its AI Gateway service, allowing developers to integrate the model into their applications through Vercel's platform. This restoration enables continued
Claude Fable 5 has been re-enabled as an available model option within Cursor, where it achieves the highest performance scores on CursorBench among all supported models. However, it comes with the hi