Knowledge catalogue
arXiv:2604.02022v2 Announce Type: replace Abstract: Evaluating the safety of LLM-based agents is increasingly important because risks in realistic deployments often emerge over multi-step interactions
arXiv:2604.08070v1 Announce Type: new Abstract: Darija, the Moroccan Arabic dialect, is rich in visual content yet lacks specialized Optical Character Recognition (OCR) tools. This paper introduces At
arXiv:2604.06231v1 Announce Type: cross Abstract: Database systems incorporate an ever-growing number of functions in their kernels (a.k.a., database native functions) for scenarios like new applicati
arXiv:2505.20662v3 Announce Type: replace Abstract: Efficient reproduction of research papers is pivotal to accelerating scientific progress. However, the increasing complexity of proposed methods oft
arXiv:2604.07041v1 Announce Type: cross Abstract: Text-to-SQL is the task of translating natural language queries into executable SQL for a given database, enabling non-expert users to access structur
arXiv:2604.08540v1 Announce Type: cross Abstract: Text-to-Audio-Video (T2AV) generation is rapidly becoming a core interface for media creation, yet its evaluation remains fragmented. Existing benchma
arXiv:2510.03046v2 Announce Type: replace Abstract: Machine learning potentials (MLPs) have become essential for large-scale atomistic simulations, enabling ab initio-level accuracy with computational
arXiv:2601.05529v5 Announce Type: replace Abstract: High success rates on navigation-related tasks do not necessarily translate into reliable decision making by foundation models. To examine this gap,
arXiv:2603.18019v2 Announce Type: replace Abstract: Do language model benchmarks actually measure what practitioners intend them to ? High-level metadata is too coarse to convey the granular reality o
arXiv:2604.06185v1 Announce Type: cross Abstract: Fulfilling user needs through Large Language Model multi-turn, multi-step tool-use is rarely a straightforward process. Real user interactions are inh
arXiv:2604.06173v1 Announce Type: cross Abstract: Legal QA benchmarks have predominantly focused on case law, overlooking the unique challenges of statute-centric regulatory reasoning. In statutory do
arXiv:2604.06201v1 Announce Type: cross Abstract: While most reading comprehension benchmarks for LLMs focus on factual information that can be answered by localizing specific textual evidence, many r
arXiv:2604.08038v1 Announce Type: new Abstract: In a real-world traffic scenario, varying-scale objects are usually distributed in a cluttered background, which poses great challenges to accurate dete
arXiv:2604.07749v1 Announce Type: new Abstract: Large language models (LLMs) can shift their answers under pressure in ways that reflect accommodation rather than reasoning. Prior work on sycophancy h
arXiv:2604.07763v1 Announce Type: new Abstract: As generative artificial intelligence evolves, deepfake attacks have escalated from single-modality manipulations to complex, multimodal threats. Existi
arXiv:2604.06336v1 Announce Type: cross Abstract: Graph Transformers have recently attracted attention for molecular property prediction by combining the inductive biases of graph neural networks (GNN
arXiv:2604.06216v1 Announce Type: cross Abstract: As LLM-powered chatbots are increasingly deployed in mental health services, detecting hallucinations and omissions has become critical for user safet
arXiv:2604.06233v1 Announce Type: new Abstract: Safety-trained language models routinely refuse requests for help circumventing rules. But not all rules deserve compliance. When users ask for help eva
arXiv:2604.07606v1 Announce Type: new Abstract: AI-driven sign language interpretation is limited by a lack of high-quality annotated data. New datasets including ASL STEM Wiki and FLEURS-ASL contain
arXiv:2601.02670v2 Announce Type: replace Abstract: We introduce self-jailbreaking, a threat model in which an aligned LLM guides its own compromise. Unlike most jailbreak techniques, which oft
BREAKING: GLM 5.1 by @Zai_org overwhelmingly dominates design-centric coding tasks amongst open-weight models In the categories featured below, it is most comparable to Opus 4.6 by @AnthropicAI at ~1/
arXiv:2604.06395v1 Announce Type: new Abstract: Spiking reservoir computing provides an energy-efficient approach to temporal processing, but reliably tuning reservoirs to operate at the edge-of-chaos
arXiv:2604.05292v2 Announce Type: replace-cross Abstract: AI coding assistants are now used to generate production code in security-sensitive domains, yet the exploitability of their outputs remains u
arXiv:2506.12040v2 Announce Type: replace-cross Abstract: Binary quantization represents the most extreme form of compression, reducing weights to +/-1 for maximal memory and computational efficiency.
arXiv:2604.07286v1 Announce Type: cross Abstract: Autonomous vehicles deployed in remote environments typically rely on embedded processors, compact batteries, and lightweight sensors. These hardware
arXiv:2604.06398v1 Announce Type: cross Abstract: Global ocean models exhibit biases in the mean state and variability, particularly at coarse resolution, where mesoscale eddies are unresolved. To add
arXiv:2604.07583v1 Announce Type: new Abstract: Real-world categorization is severely hampered by class imbalance because traditional ensembles favor majority classes, which lowers minority performanc
arXiv:2604.08287v1 Announce Type: new Abstract: Discovering camouflaged objects is a challenging task in computer vision due to the high similarity between camouflaged objects and their surroundings.
arXiv:2604.08294v1 Announce Type: cross Abstract: Action Quality Assessment (AQA) has broad applications in physical therapy, sports coaching, and competitive judging. Although Vision Language Models
arXiv:2604.06718v2 Announce Type: cross Abstract: Repurchase behavior is a primary signal in large-scale retail recommendation, particularly in categories with frequent replenishment: many items in a
arXiv:2508.13993v2 Announce Type: replace Abstract: Long-context modeling is critical for a wide range of real-world tasks, including long-context question answering, summarization, and complex reason
Claude for Word is now in beta. Draft, edit, and revise documents directly from the sidebar. Claude preserves your formatting, and edits appear as tracked changes. Available on Team and Enterprise pla
Claude now supports dynamic looping. If you run /loop without passing an interval, Claude will dynamically schedule the next tick based on your task. It also may directly use the Monitor tool to bypas
arXiv:2604.08523v1 Announce Type: new Abstract: AI agents may be able to automate your inbox, but can they automate other routine aspects of your life? Everyday online tasks offer a realistic yet unso
arXiv:2604.05172v2 Announce Type: replace Abstract: Large language model (LLM) agents are increasingly deployed to automate productivity tasks (e.g., email, scheduling, document management), but evalu
arXiv:2603.18472v2 Announce Type: replace-cross Abstract: Multimodal large language models (MLLMs) perform strongly on natural images, yet their ability to understand discrete visual symbols remains u
arXiv:2506.19420v2 Announce Type: replace Abstract: Multimodal sarcasm understanding is a high-order cognitive task. Although large language models (LLMs) have shown impressive performance on many dow
arXiv:2604.06196v1 Announce Type: cross Abstract: Three-way logical question answering (QA) assigns True/False/Unknown to a hypothesis H given a premise set S. While modern large language models
arXiv:2604.07484v1 Announce Type: cross Abstract: Generative reward models (GRMs) have emerged as a promising approach for aligning Large Language Models (LLMs) with human preferences by offering grea
arXiv:2604.07354v1 Announce Type: new Abstract: The accuracy frontier of speech-to-text systems has plateaued on academic benchmarks.1 In contrast, industrial benchmarks and adoption in high-stakes do
arXiv:2604.06435v1 Announce Type: cross Abstract: Visual Anomaly Detection (VAD) is a critical task for many applications including industrial inspection and healthcare. While VAD has been extensively
arXiv:2601.08950v3 Announce Type: replace Abstract: Despite their growing adoption in education, LLMs remain misaligned with the core principle of effective tutoring: the dialogic construction of know
CoreWeave Inc. today announced that it has won a multiyear contract to supply Anthropic PBC with cloud infrastructure. The company’s shares closed 11% higher on the news. The data center capacity comm
arXiv:2604.08457v1 Announce Type: new Abstract: Cooperative autonomous driving requires traffic scene understanding from both vehicle and infrastructure perspectives. While vision-language models (VLM
In support of our mission to accelerate the developer journey on Google Cloud, we built Dev Signal: a multi-agent system designed to transform raw community signals into reliable technical guidance by
Cron Jobs — AI That Works on a Schedule Tell Qwen Code 'check if tests pass every 30 minutes' and it sets up a cron job in your session. No crontab editing, no scripts to write. Use /loop commend. Wor
arXiv:2604.06202v1 Announce Type: cross Abstract: Large language models (LLMs) have transformed natural language processing, yet their capabilities remain uneven across languages. Most multilingual mo
arXiv:2508.04929v4 Announce Type: replace-cross Abstract: As a critical modality for structural biology, cryogenic electron microscopy (cryo-EM) facilitates the determination of macromolecular structu
arXiv:2512.19173v2 Announce Type: replace Abstract: Current chart-related tasks, such as chart generation (NL2Chart), chart schema parsing, chart data parsing, and chart question answering (ChartQA),
arXiv:2604.07125v1 Announce Type: cross Abstract: This article presents DDP-SA, a scalable privacy-preserving federated learning framework that jointly leverages client-side local differential privacy
Dear MAGA, Just out of curiosity: If president Biden had banged porn stars, cheated on multiple wives, lied 30,000 times, singlehandedly and unilaterally started a war, released 5,000 Talibanis, bombe
arXiv:2604.07717v1 Announce Type: new Abstract: Human immunodeficiency virus (HIV)-related stigma is a critical psychosocial determinant of health for people living with HIV (PLWH), influencing mental
arXiv:2601.08258v3 Announce Type: replace Abstract: Large language models increasingly fail in a way that scalar accuracy cannot diagnose: they produce a sound reasoning trace and then abandon it unde
arXiv:2604.06863v1 Announce Type: cross Abstract: Skin-toned emojis are crucial for fostering personal identity and social inclusion in online communication. As AI models, particularly Large Language
arXiv:2604.07723v1 Announce Type: new Abstract: Open-vocabulary semantic segmentation (OVSS) aims to segment arbitrary category regions in images using open-vocabulary prompts, necessitating that exis
arXiv:2604.06250v1 Announce Type: cross Abstract: When asked to describe a molecular diagram, a Vision-Language Model correctly identifies ``a benzene ring with an -OH group.'' When asked to reason ab
arXiv:2604.06483v1 Announce Type: cross Abstract: Large language models that require multiple GPU cards to host are usually the most capable models. It is necessary to understand and steer these model
arXiv:2604.08284v1 Announce Type: new Abstract: Large language models store not only isolated facts but also rules that support reasoning across symbolic expressions, natural language explanations, an
arXiv:2602.11635v2 Announce Type: replace Abstract: Multimodal large language models (MLLMs) have achieved strong performance on perception-oriented tasks, yet their ability to perform mathematical sp
arXiv:2604.04344v2 Announce Type: replace Abstract: We establish a computation-substrate-agnostic inference architecture in which domain is an explicit first-class computational parameter. This produc