Knowledge catalogue
arXiv:2511.12710v2 Announce Type: replace Abstract: Automated red teaming frameworks for Large Language Models (LLMs) have become increasingly sophisticated, yet many still formulate attack optimizati
arXiv:2605.18421v1 Announce Type: cross Abstract: Recent benchmarks for Large Language Model (LLM) agents mainly evaluate reasoning, planning, and execution. However, memory is also essential for agen
arXiv:2601.05653v2 Announce Type: replace Abstract: Existing traffic simulation frameworks for autonomous vehicles typically rely on imitation learning or game-theoretic approaches that solve for Nash
arXiv:2605.16967v1 Announce Type: new Abstract: In open-world settings, thermal infrared (TIR) image degradations continuously emerge and evolve, while most existing all-in-one restoration methods are
arXiv:2501.12709v2 Announce Type: replace-cross Abstract: Federated learning enables decentralized, privacy-preserving training but remains vulnerable to privacy leakage in the quantum era. Quantum fe
arXiv:2605.16975v1 Announce Type: cross Abstract: Electrocardiogram (ECG) foundation models pretrained on typical diagnostic 10-second ECG segments, have demonstrated strong transferability across a r
arXiv:2605.17531v1 Announce Type: new Abstract: Referring segmentation aims to segment the target objects in images or videos based on the textual query. Despite remarkable progress over the past year
arXiv:2605.16630v1 Announce Type: cross Abstract: Hybrid local--cloud agents enrich user requests with context from persistent working state before delegating capability-intensive subtasks to a cloud
arXiv:2406.15797v2 Announce Type: replace-cross Abstract: Employing graph neural networks (GNNs) for graph clustering has shown promising results in deep graph clustering. However, existing methods di
arXiv:2503.16492v3 Announce Type: replace-cross Abstract: ffective Human-Robot Interaction (HRI) is crucial for enhancing accessibility and usability in real-world robotics applications. However, exis
Fascinatingly Antigravity is actually the best tool so far at providing this sort of transparency, doing something by default that Codex and Code do not: offering a summary of exactly what it did at t
arXiv:2505.18991v3 Announce Type: replace Abstract: Pansharpening seeks to fuse high-resolution panchromatic (PAN) and low-resolution multispectral (LRMS) images into a single image with both fine spa
arXiv:2605.18554v1 Announce Type: new Abstract: Federated Bayesian neural networks require fixing a prior on the model parameters together with a likelihood. Eliciting meaningful priors on the weight
arXiv:2509.06984v3 Announce Type: replace-cross Abstract: Federated Learning with LoRA fine-tuning offers an efficient and privacy-aware solution for institutions to collaboratively leverage their lar
arXiv:2605.17246v1 Announce Type: cross Abstract: We introduce fidelity probes: natural-language questions generated from a reference artifact with code-derived ground-truth answers, answered from a c
arXiv:2605.16800v1 Announce Type: cross Abstract: Low-rank adaptation (LoRA) assigns a uniform rank to every adapted weight matrix - a practical convenience that ignores a fundamental reality: differe
arXiv:2510.08886v3 Announce Type: replace Abstract: Going beyond simple text processing, financial auditing requires detecting semantic, structural, and numerical inconsistencies across large-scale di
arXiv:2505.20218v2 Announce Type: replace Abstract: Accurate and safe medication recommendations are critical for effective clinical decision-making, especially in multimorbidity cases. However, exist
arXiv:2605.17693v1 Announce Type: cross Abstract: Structure-based drug design has been accelerated by pocket-aware 3D generative models, yet most methods primarily fit the training distribution and ma
arXiv:2602.05172v2 Announce Type: replace-cross Abstract: We derive finite-particle rates for the regularized Stein variational gradient descent (R-SVGD) algorithm introduced by He et al. (2024) that
arXiv:2505.20650v5 Announce Type: replace-cross Abstract: Accurate interpretation of numerical data in financial reports is critical for markets and regulators. Although XBRL (eXtensible Business Repo
arXiv:2605.17558v1 Announce Type: cross Abstract: Training tool-calling agents requires large-scale trajectory data with verifiable labels, yet existing approaches either synthesize environments that
arXiv:2602.03784v2 Announce Type: replace Abstract: Long-context LLM agents often struggle with growing token, memory, and latency costs, making efficient context compression essential for practical d
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