Knowledge catalogue
arXiv:2512.09874v2 Announce Type: replace Abstract: Correctly parsing mathematical formulas from PDFs is critical for training large language models and building scientific knowledge bases from academ
arXiv:2605.03742v1 Announce Type: new Abstract: This paper is devoted to the adaptation of generative large language models for the Tajik language, a low-resource language with Cyrillic script. To ove
arXiv:2605.03509v1 Announce Type: new Abstract: Low-light image enhancement is a fundamental challenge in computer vision and multimedia applications, as images captured under insufficient illuminatio
arXiv:2605.03637v1 Announce Type: new Abstract: Learning robotic manipulation from human videos is a promising solution to the data bottleneck in robotics, but the distribution shift between humans an
arXiv:2605.02959v1 Announce Type: new Abstract: Calibrating the urban underlying surface parameters is crucial for urban flood simulation. We formulate the parameter calibration problem into an optimi
arXiv:2512.13913v3 Announce Type: replace Abstract: Out-of-equilibrium quantum many-body systems exhibit rapid correlation buildup that underlies many emerging phenomena. Exact wave-function methods t
arXiv:2605.02454v1 Announce Type: cross Abstract: Software engineering increasingly involves making high-stakes decisions under uncertainty, using signals from code, field data, and socio-technical pr
arXiv:2605.03903v1 Announce Type: new Abstract: Large Multimodal Models (LMMs) have recently shown strong performance on Optical Character Recognition (OCR) tasks, demonstrating their promising capabi
Claude Desktop has a third-party inference feature that lets you replace Anthropic's API with any model provider, including a local AI model running entirely on your machine. This feature can be activ
Code with Claude is happening now! ▪︎ 9:00AM - Keynote ▪︎ 10:30AM - What's new in Claude Code ▪︎ 11:15AM - Building on Claude at GitHub scale ▪︎ 12:00PM - Get to production faster with Managed Agents
arXiv:2605.02829v1 Announce Type: new Abstract: Adapting large pretrained models to diverse tasks is now routine, yet the two dominant strategies of parameter-efficient fine-tuning (PEFT) and low-rank
arXiv:2506.19714v2 Announce Type: replace-cross Abstract: Offline model-based optimization (MBO) refers to the task of optimizing a black-box objective function using only a fixed set of prior input-o
arXiv:2603.00822v2 Announce Type: replace-cross Abstract: As Large Language Model (LLM) agents increasingly execute complex, autonomous software engineering tasks, developers rely on natural language
Continuous-video agents (computer use, robotics, static scenes) burn compute re-ingesting pixels that didn't move. VLMaxxing teaches a frozen video VLM to skip the reruns. 54 fps perception on Gemma 4
arXiv:2605.03297v1 Announce Type: cross Abstract: ASR systems based on self-supervised acoustic pretraining and CTC fine-tuning achieve strong performance on native speech but remain sensitive to acce
arXiv:2605.02033v1 Announce Type: cross Abstract: Conventional commits provide a structured format for writing commit messages, which improves readability, software maintenance, and enables automation
arXiv:2605.03310v1 Announce Type: cross Abstract: Multi-agent LLM systems fail in production at rates between 41% and 87%, mostly due to coordination defects rather than base-model capability. Existin
arXiv:2605.02910v1 Announce Type: cross Abstract: Recent advances in large language models have led to strong performance on reasoning and environment-interaction tasks, yet their ability for creative
arXiv:2605.03259v1 Announce Type: new Abstract: High-throughput plant phenotyping, the quantitative measurement of observable plant traits, is critical for modern breeding but remains constrained by a
arXiv:2605.03476v1 Announce Type: new Abstract: Discharge summaries require extracting critical information from lengthy electronic health records (EHRs), a process that is labor-intensive when perfor
arXiv:2605.03544v1 Announce Type: new Abstract: Foundation models with visual question answering capabilities for digital pathology are emerging. Such unprecedented technology requires independent ben
arXiv:2605.02503v1 Announce Type: new Abstract: Evaluating autonomous data analysis agents requires testing their ability to perform exploratory analysis in underexplored data environments. However, m
arXiv:2605.01789v1 Announce Type: new Abstract: Constructing controllable visual data is a major bottleneck for image editing and multimodal understanding. Useful supervision is rarely produced by a s
arXiv:2605.03472v1 Announce Type: new Abstract: As conversational AI therapists are increasingly used in psychological support settings, reliable offline evaluation of therapeutic response quality rem
arXiv:2605.01338v1 Announce Type: new Abstract: System-level diagrams encode the architectural blueprint of chip design, specifying module functions, dataflows, and interface protocols. However, non-s
arXiv:2605.03175v1 Announce Type: new Abstract: The remote sensing (RS) domain suffers from a lack of densely labeled datasets, which are costly to obtain. Thus, models that can segment RS imagery wel
arXiv:2605.03570v1 Announce Type: new Abstract: Real-world clinical data is inherently multimodal, providing complementary evidence that mirrors the practical necessity of jointly assessing multiple r
arXiv:2605.03069v1 Announce Type: cross Abstract: Federated learning (FL) lets distributed nodes train a shared model without exchanging their raw data, but in privacy-sensitive deployments medical se
arXiv:2605.02163v1 Announce Type: cross Abstract: Software documentation frequently drifts from executable logic as codebases evolve, creating technical debt that degrades maintainability and causes d
arXiv:2605.03281v1 Announce Type: cross Abstract: Donor-level disease classification from single-cell RNA sequencing (scRNA-seq) requires strict donor-aware cross-validation: naive pipelines that spli
arXiv:2605.03061v1 Announce Type: cross Abstract: Time varying dependence is often modeled through dynamic correlations or Gaussian graphical models, yet many multivariate systems change through tail
arXiv:2605.03147v1 Announce Type: new Abstract: Earnings calls are a key source of financial information about public companies. However, extracting information from these calls is difficult. Unlike t
arXiv:2505.19841v2 Announce Type: replace-cross Abstract: This work is focussed on the inversion task of inferring the distribution over parameters of interest leading to multiple sets of observations
arXiv:2605.03667v1 Announce Type: new Abstract: Large Language Models (LLMs) have achieved remarkable capabilities, but their immense computational demands during training remain a critical bottleneck
Elon has been the longest and by far the biggest voice actively warning about the dangers of AI for a very long time The entire reason he started OpenAI was this one thing.....to make sure AI is built
arXiv:2509.17677v2 Announce Type: replace Abstract: Large language models (LLMs) have shown strong performance on mathematical reasoning under well-defined conditions. However, real-world engineering
arXiv:2605.01250v1 Announce Type: new Abstract: Earth Observation (EO) analysis is inherently interactive: resolving uncertainty often requires expanding the region of interest, retrieving historical
arXiv:2605.02905v1 Announce Type: new Abstract: We show that the key-value (KV) cache in transformer attention heads admits a natural decomposition into a low-rank shared context component and a full-
arXiv:2605.03998v1 Announce Type: new Abstract: Emergency department triage assigns patients an acuity score that determines treatment priority, and clinical evidence documents persistent gender dispa
arXiv:2605.03547v1 Announce Type: new Abstract: Large Vision-Language Models (LVLMs), trained on web-scale data, risk memorizing and regenerating copyrighted visual content such as characters and logo
arXiv:2605.01604v1 Announce Type: new Abstract: Existing evaluation frameworks for large language models -- including HELM, MT-Bench, AgentBench, and BIG-bench -- are designed for controlled, single-s
arXiv:2605.03578v1 Announce Type: cross Abstract: Boltzmann Machines trained on evolutionary sequence data have emerged as a powerful paradigm for the data-driven design of artificial proteins. Howeve
Swyx live-tweeted an Anthropic Code with Claude event, featuring speakers Katelyn Lesse and Ang Jiang discussing the Claude platform. The event appears to have been a real-time social media coverage o
arXiv:2605.03441v1 Announce Type: cross Abstract: Large language models (LLMs) employ safety mechanisms to prevent harmful outputs, yet these defenses primarily rely on semantic pattern matching. We s
arXiv:2605.03294v1 Announce Type: new Abstract: Open-vocabulary object detection often fails under distribution shifts, as it can be misled by spurious correlations between non-causal visual attribute
arXiv:2605.03969v1 Announce Type: new Abstract: AI-generated text is nowadays produced at scale across domains and heterogeneous generation pipelines, making robustness to distribution shift a central
arXiv:2605.01726v1 Announce Type: cross Abstract: Sequential recommendation models often struggle to capture latent periodic patterns in user interests, primarily due to the noise inherent in time-dom
arXiv:2605.03460v1 Announce Type: cross Abstract: Time series (TS) reasoning models (TSRMs) have shown promising capabilities in general domains, yet they consistently fail on financial domain, which
arXiv:2605.03749v1 Announce Type: new Abstract: Ground-to-space astronomical super-resolution requires recovering space-quality images from ground-based observations that are simultaneously limited by
Anthropic: Following its SpaceX deal, Anthropic doubles Claude Code's five-hour rate limits for paid plans and removes peak hours limit reduction for Pro and Max plans — We've agreed to a partnership
arXiv:2605.03686v1 Announce Type: cross Abstract: Automated Machine Learning (AutoML) frameworks increasingly leverage Large Language Models (LLMs) for tasks such as hyperparameter optimization and ne
arXiv:2601.03731v3 Announce Type: replace-cross Abstract: As large language models (LLMs) evolve into autonomous agents, evaluating repository-level reasoning, the ability to maintain logical consiste
arXiv:2605.02939v1 Announce Type: new Abstract: Multimodal controversy detection (MCD) identifies controversial content in videos and their associated user comments, to support risk management for soc
True spatial intelligence for multimodal agents transcends low-level geometric perception, evolving from knowing where things are to understanding what they are for. While existing benchmarks, such as
arXiv:2605.03196v1 Announce Type: new Abstract: A reliable language model should be able to signal, prior to generation, when a query falls outside its knowledge. We investigate whether representation
arXiv:2510.12218v2 Announce Type: replace Abstract: Current approaches rely on zero-shot evaluation due to the absence of training data; while proprietary models such as GPT-4 exhibit strong reasoning
Ben Schoon / 9to5Google: Google Chrome silently installs a ~4GB Gemini Nano model on desktop devices; Google says it has been offered since 2024 and users can remove it via settings — The ongoing marc
At Google, we see firsthand how cyber threats can outpace traditional defense mechanisms — and how agentic threat intelligence can help bridge the gap. We have a vision for agentic defense where auton
Ryan Whitwam / Ars Technica: Google releases Multi-Token Prediction drafters for its Gemma 4 models, which use a form of speculative decoding to guess future tokens for faster inference — Google launc
arXiv:2605.03901v1 Announce Type: cross Abstract: Local gauge structures play a central role in a wide range of condensed matter systems and synthetic quantum platforms, where they emerge as effective