Knowledge catalogue
arXiv:2605.17373v1 Announce Type: cross Abstract: AI research agents accelerate ML research by automating hypothesis generation, experimentation, and empirical refinement. Existing agent strategies ra
arXiv:2605.18346v1 Announce Type: cross Abstract: Recent advances in autoregressive video diffusion have enabled sequential and streaming video generation. However, long-horizon generation requires in
For those saying 'the tomato sauce blood from the sword wound that flying Shakespeare inflicted on the pizza robot while the otters discussed Spirit Airlines wasn't thick enough' or whatever... this w
arXiv:2605.17590v1 Announce Type: new Abstract: We formulate machine unlearning for online L-BFGS as a counterfactual state-alignment problem. Given an actual event stream and a deletion-edited counte
arXiv:2601.02071v3 Announce Type: replace Abstract: Pharmaceutical three-dimensional (3D) printing is an advanced fabrication technology with the potential to enable truly personalised dosage forms. R
arXiv:2508.06038v3 Announce Type: replace-cross Abstract: Vision-Language Models (VLMs) incur substantial computational overhead and inference latency due to the large number of vision tokens introduc
arXiv:2605.17162v1 Announce Type: new Abstract: This paper investigates whether shallow neural network agents can master the card game Schnapsen and challenge a strong search-based baseline, RdeepBot,
arXiv:2508.01608v2 Announce Type: replace Abstract: Image geolocalization, the task of identifying the geographic location depicted in an image, is important for applications in crisis response, digit
arXiv:2605.16927v1 Announce Type: new Abstract: Clinical decision-making is a feedback system where risk estimates influence treatment, which in turn changes disease trajectories, and both shape clini
arXiv:2605.18475v1 Announce Type: cross Abstract: Mixed-precision quantization improves the budget--accuracy trade-off for large language models (LLMs) by allocating more bits to sensitive modules. Ho
arXiv:2511.21016v3 Announce Type: replace-cross Abstract: Linear State-Space Models (SSMs) offer an efficient alternative to softmax Attention with constant memory and linear compute, but their lossy,
Gemini Gemini 3.5 Flash ARC-AGI (Verified) ARC-AGI-2: - High: 72.1%, 0.85 - Minimal: 8.9%, 0.11 ARC-AGI-1: - High: 92.5%, 0.42 - Minimal: 48.8%, 0.06 Gemini 3.5 Flash is on par with GPT-5.5 (Medium) o
Cognition AI announced the availability of Gemini 3.5 Flash within Windsurf, their AI development environment. This integration brings Google's faster Gemini 3.5 Flash model to Windsurf users, likely
Gemini 3.5 Flash runs 4x faster than other frontier models in output tokens per second while delivering frontier-level intelligence, proving that speed and quality no longer require trade-offs. The mo
Today at Google I/O, Google released Gemini 3.5 Flash. This one skipped the -preview modifier and went straight to general availability, and Google appear to be using it for a whole lot of their key p
Vercel announced the integration of Google's Gemini 3.5 Flash model into its AI Gateway, enabling developers to access this fast and efficient language model through Vercel's unified API infrastructur
Gemini 3.5 is Google's latest family of AI models combining frontier intelligence with action, representing a major leap forward in building more capable, intelligent agents. The first model in the se
Gemini has a creep problem. A few years ago, that little sparkle icon started showing up in all of our Google apps. Gemini in your inbox! Gemini in your Google Drive! It was slow at first, and easy en
Gemini Omni: 'a dramatic reading of Death by Water from the Wasteland by a man eating garlic bread while balanced on a unicycle on a small platform over a churning sea of tomato sauce in which, at the
I cannot provide a reliable summary for this entry. The title contains apparent fictional or unclear references (Google 'Gemini Spark,' 'Open Claw') and the truncated source text is incomplete, making
Gemini is gaining the power of sight and mobility. Today at the I/O conference, Google and Volvo announced that the AI-powered assistant will be able to access external cameras in the upcoming EX60 SU
arXiv:2605.18721v1 Announce Type: cross Abstract: Post-training has split large language model (LLM) alignment into two largely disconnected tracks. Online reinforcement learning (RL) with verifiable
arXiv:2605.17565v1 Announce Type: new Abstract: Recent work has fine-tuned language models on chess data and reported high benchmark scores as evidence that the resulting models can understand the rul
arXiv:2605.16475v1 Announce Type: cross Abstract: Generative artificial intelligence (GenAI), based on large-language models (LLMs), such as ChatGPT, has taken organizations, academia, and the public
arXiv:2507.21035v3 Announce Type: replace Abstract: Gene expression analysis holds the key to many biomedical discoveries, yet extracting insights from raw transcriptomic data remains formidable due t
arXiv:2605.17804v1 Announce Type: new Abstract: Generative models have demonstrated remarkable potential in time series analysis tasks, like synthesis, forecasting, imputation, etc. However, offering
arXiv:2605.16349v1 Announce Type: new Abstract: Mixture-of-Experts (MoE) architectures achieve scalable capacity through sparse routing, yet the geometric structure of expert specialization remains po
arXiv:2512.23752v5 Announce Type: replace-cross Abstract: Recent work has shown that small transformers trained in controlled 'wind-tunnel'' settings can implement exact Bayesian inference, and that t
arXiv:2603.02531v2 Announce Type: replace-cross Abstract: Classifier-Free Guidance (CFG) improves sample quality in diffusion models, but its dual-pass inference and reliance on null-condition trainin
arXiv:2605.18419v1 Announce Type: cross Abstract: Vision-language models (VLMs) can couple visual perception with open-ended clinical reasoning, making them attractive for computational histopathology
arXiv:2605.18663v1 Announce Type: new Abstract: As LLM benchmarks saturate, the evaluation community has pursued two strategies to increase difficulty: escalating knowledge demands (GPQA, HLE) or remo
arXiv:2602.18584v2 Announce Type: replace-cross Abstract: Targeted data selection has emerged as a crucial paradigm for efficient instruction tuning, aiming to identify a small yet influential subset
arXiv:2605.16769v1 Announce Type: new Abstract: Parameter-efficient fine-tuning (PEFT) has emerged as a promising paradigm for adapting pretrained models under limited data conditions. However, most e
Google is launching a big new feature for Gmail called Gmail Live, a new AI-powered voice mode that's basically the Gemini Live experience but built specifically for your inbox. To use Gmail Live, tap
arXiv:2511.08154v2 Announce Type: replace-cross Abstract: We revisit the fermion mass problem of the SU(5) grand unified theory using machine learning techniques. The original SU(5) model proposed by
Sanuj Bhatia / Android Central: Google adds a conversational search feature to YouTube and rolls out the new Gemini Omni model in YouTube Shorts Remix and the Create app — Seriously, who is asking for
Google is announcing the availability of Gemini Omni Flash to subscribers of its Google AI Plus, Pro, and Ultra tiers across multiple applications including the Gemini app, Google Flow, and Google Flo
Macy Meyer / CNET: Google announces updates to Flow and Flow Music: Gemini Omni support, mobile apps, the ability to create custom tools like a video resizer or shaders, and more — Google Flow's famil
Jackson Chen / Engadget: Google debuts Gemini for Science, a set of experimental tools that help researchers generate hypotheses, conduct testing, and understand scientific literature — Three new feat
Google has hidden thinking traces on the Gemini site. You have to use the 3 dot menu to pull up summaries, which are so minimal as to be unusable. Did it do web searches? Did it check results? You can
Google just announced agentic coding in search. Based on your search, Gemini processes your ask, decides whether it should build a new interface, reasons through the steps, and creates a personalized
For a quarter century, the Google search box has been one of the most recognizable interfaces in computing: a thin white rectangle, a blinking cursor, a few typed words, and a list of blue links. On T
Google launches new Omni model. Google says that today Omni can create and edit (yes, edit!!) video but eventually it is to go from “any input to any output”. Even more of a reason to believe that Sor
Google Search is entering the next phase of its AI evolution. During Google I/O 2026, the company showed off a reimagined search box that makes it easier to flow between AI Overviews, the AI-generated
Google LLC today introduced two new generative artificial intelligence models that push its Gemini family further into AI agents and multimodal creation: Gemini 3.5 Flash, a fast reasoning model desig
Google has big promises for its AI-powered future - and a lot of it depends on your trust. At I/O 2026, Google described a bunch of new tools that it claims will make your life easier. Gemini Spark, G
Google’s new Gemini 3.5 Flash is the clear leader on the Intelligence vs Speed Pareto frontier and makes large gains on GDPval-AA (real-world agentic tasks), but is 5x the cost of Gemini 3 Flash @Goog
Entering into the artificial intelligence agent era, Google LLC today introduced Gemini Spark, a 24/7 personal AI assistant that can help people navigate their digital lives and do real work on their
arXiv:2506.14009v2 Announce Type: replace Abstract: Autonomous drones capable of interpreting and executing high-level language instructions in unstructured environments remain a long-standing goal. Y
arXiv:2508.02383v2 Announce Type: replace Abstract: Spectral graph embedding plays a critical role in graph representation learning by generating low-dimensional vector representations from graph spec
arXiv:2605.18387v1 Announce Type: cross Abstract: Graph Neural Networks (GNNs) and Graph Transformers (GTs) are now a fundamental paradigm for graph learning, combining the representation-learning cap
arXiv:2508.08501v3 Announce Type: replace Abstract: We introduce GVGAI-LLM, a video game benchmark for evaluating the reasoning and problem-solving capabilities of large language models (LLMs). Built
arXiv:2605.17007v1 Announce Type: new Abstract: Large language models (LLMs) have achieved remarkable progress in natural language generation, but remain susceptible to hallucination. In response to g
arXiv:2605.17093v1 Announce Type: cross Abstract: Distilling vision-language models into faster hybrid architectures, such as 3:1 Mamba-2/attention mixes, is now standard practice for making inference
This post likely announces or provides updates from 'Code with Claude London,' an event or meetup in London related to Claude AI and coding. The post is from Boris Cherny, a software engineer and Type
arXiv:2504.03035v2 Announce Type: replace-cross Abstract: Random feature ridge regression is often analyzed in the high-dimensional regime under the homogeneous sampling model x_i=Sigma^{1/2}x_i', whe
arXiv:2605.16385v1 Announce Type: cross Abstract: Geometric problem solving, as a typical multimodal reasoning problem, has attracted much attention and made great progress recently, however most of w
arXiv:2605.16286v1 Announce Type: cross Abstract: Different AI tools such as ChatGPT, Gemini, and Claude are becoming very popular. Although they are helpful for many day-to-day tasks, they can be use
Google's AI Mode has surpassed a billion monthly active users globally one year after launch, with queries more than doubling every quarter . AI Mode bridges traditional search and conversational AI,
arXiv:2605.17276v1 Announce Type: cross Abstract: While scaling laws have established a fundamental framework for foundation models in natural language processing, their applicability to electrocardio