Knowledge catalogue
Advances in models, chips, or devices will continually improve local-first capabilities. We will open our benchmarks soon. Read the full post: https://www.perplexity.ai/hub/blog/a-local-first-agent-fo
arXiv:2608.22606v1 Announce Type: new Abstract: Topology optimization, using both physic-based approaches and deep learning surrogates, serves as a cornerstone for generative design agents in cyber-ma
arXiv:2608.23375v1 Announce Type: cross Abstract: Gumbel-based inference verification bounds LLM weight exfiltration by only forgiving token choices that plausibly arise from honest GPU nondeterminism
arXiv:2607.18429v2 Announce Type: replace-cross Abstract: Phishing emails remain one of the most persistent cybersecurity threats, and machine-learning classifiers are widely used to detect them. Most
arXiv:2507.13727v2 Announce Type: replace Abstract: Adversarial training is a promising strategy for enhancing robustness against adversarial attacks, but its impact on generalization under substantia
arXiv:2608.23318v1 Announce Type: new Abstract: Hint-based reinforcement learning addresses reward sparsity in long-horizon agentic tasks by retaining a prefix of an expert trajectory before each roll
For two years, the field has gotten very good at training models, and it still hand-wires the agents around them. Whether an agent plans, searches, calls a tool, or checks its own work before answerin
arXiv:2608.21444v1 Announce Type: new Abstract: Multi-drone systems are increasingly positioned for safety-critical missions such as search and rescue (SAR) and critical infrastructure monitoring. Yet
arXiv:2603.12031v3 Announce Type: replace-cross Abstract: Cloud-native container orchestration requires resource schedulers capable of balancing infrastructure expenditure, fault resilience, and node
Amazon OpenSearch Service now supports MCP Apps, which return interactive visualizations alongside your AI agent's text responses. Learn how a single, locally run MCP server lets your agent move from
arXiv:2608.21377v1 Announce Type: cross Abstract: Sycophancy in large language models, the tendency to prioritize user agreement over truthful responses, has been documented extensively but studied pr
arXiv:2608.21423v1 Announce Type: cross Abstract: Agentic security uses large-language-model (LLM) agents to plan, dispatch, and interpret security tools. As these systems move from demonstrations to
Artificial intelligence startup Keenable.ai Inc. said today it’s launching with 26 million in funding to try to revamp a web search infrastructure that was built for humans, not the billions of autono
arXiv:2608.23078v1 Announce Type: new Abstract: Large language models increasingly operate over large collections of tools, functions, APIs, and specialized agents. As the candidate action space grows
arXiv:2608.22161v1 Announce Type: new Abstract: Online users often release multiple texts under the same identity, giving attackers an author profile that can reveal more than any single text. Existin
arXiv:2608.22617v1 Announce Type: cross Abstract: Assembly and disassembly processes rely on expert knowledge that is difficult to document, reuse, and transfer. This paper presents a data-centric app
arXiv:2608.23196v1 Announce Type: new Abstract: People increasingly face a novel decision when seeking emotional support: human or AI. In existing studies, AI's empathic messages are rated as well as
The artificial intelligence infrastructure market is crossing an important threshold. The conversation is shifting from acquiring graphics processing units to building complete AI factories that can g
AI storage infrastructure is becoming a more consequential planning issue as organizations move from model training toward agentic AI. As agents reason, act and reassess, they build longer contexts an
arXiv:2608.21372v1 Announce Type: new Abstract: This report summarizes the work conducted on the Game of Hidden Rules (GOHR), focusing on reinforcement learning agents trained to infer hidden rules fr
arXiv:2608.23217v1 Announce Type: cross Abstract: Fast and reliable plasma equilibrium prediction is essential for real-time tokamak operation and control, but conventional Grad-Shafranov (GS) solvers
arXiv:2504.08846v2 Announce Type: replace-cross Abstract: We introduce AI University (AI-U), a flexible framework for AI-driven course content delivery that adapts to a course's instructional style. A
arXiv:2608.21426v1 Announce Type: new Abstract: The garment manufacturing industry is under increasing pressure to improve product quality, reduce costs, and accelerate digital transformation toward I
arXiv:2608.21841v1 Announce Type: new Abstract: Conversational AI increasingly shapes consequential decisions, yet users have limited support for recognizing and resisting manipulation. We present AI
arXiv:2608.21926v1 Announce Type: new Abstract: Unmanned aerial vehicle (UAV) navigation in modern low-altitude environments requires more accurate pose alignment in the final approach stage for targe
arXiv:2608.21363v1 Announce Type: new Abstract: A protocol is presented for recording the governance decisions of automated AI runtimes. When a runtime releases, blocks, defers, redacts, or escalates
arXiv:2608.22034v1 Announce Type: new Abstract: Mechanistic interpretability has identified transformer circuits, but lacks a shared vocabulary for describing how their functions compose across tasks
arXiv:2608.22444v1 Announce Type: new Abstract: The unit of AI safety evaluation is still the individual model, yet language-model agents are increasingly deployed in interacting populations that read
arXiv:2608.23214v1 Announce Type: new Abstract: Biomedical knowledge exists in two complementary but distinct forms: unstructured scientific literature and structured knowledge graphs (KGs). Aligning
arXiv:2608.21425v1 Announce Type: cross Abstract: Video generation is central to AI-powered content creation. Aligning generated videos with human preferences is a key criterion for evaluating generat
arXiv:2608.22425v1 Announce Type: cross Abstract: Large language models are increasingly consulted at moments of distress, yet single-turn benchmarks neither test sustained exchanges nor distinguish b
arXiv:2601.05882v2 Announce Type: replace-cross Abstract: Preference tuning aligns base language models to human judgments of quality, helpfulness, or safety by optimizing over explicit preference sig
arXiv:2608.23143v1 Announce Type: new Abstract: Prostate cancer is among the most frequently diagnosed malignancies worldwide, and structured reporting of each biopsy core burdens pathologists. Existi
arXiv:2509.01479v3 Announce Type: replace-cross Abstract: Explainable systems expose information about why certain observed effects are happening to the agents interacting with them. We argue that thi
arXiv:2608.21894v1 Announce Type: new Abstract: Human tactile perception relies on complex multisensory cues. Yet the relationship between tactile signals and perceptual representations remains poorly
arXiv:2607.14393v2 Announce Type: replace-cross Abstract: Human-in-the-loop Reinforcement Learning has become a popular approach for training, finetuning, and aligning robot behavior with user prefere
arXiv:2608.23014v1 Announce Type: new Abstract: 3D brain MRI generation has made significant advances in medical imaging, simulation, and controllable anatomical analysis. However, existing generative
arXiv:2608.22363v1 Announce Type: new Abstract: Medical visual question answering (VQA) is a crucial task in clinical AI, yet its evaluation has so far centered almost exclusively on English, limiting
arXiv:2608.21577v1 Announce Type: cross Abstract: Multimodal Large Language Models (MLLMs) are increasingly deployed in high-stakes domains where fairness is a critical safety requirement. In practice
David Gewirtz / ZDNET: Anthropic merges the memory systems for Claude chat and Claude Cowork, making Claude chat history available to Cowork unless users opt out — ZDNET's key takeaways — Claude chat
Artificial intelligence startup Anthropic PBC announced today it’s changing how Claude, its flagship AI product, uses memory by allowing users to see everything it remembers “topic by topic,” and edit
arXiv:2608.23283v1 Announce Type: new Abstract: General-purpose language models can reason and synthesize knowledge, but complex work also requires sustained interaction with files, information source
Nicole Nguyen / Wall Street Journal: Apple raises Mac mini and Studio prices: the M6 and M5 Pro Mac mini are 899+ and 1,699+, 100 above M4 models, and the M5 Ultra Mac Studio is 5,499+, up $200 — Betw
'A 12-core GPU, also with two more cores than before, now includes Neural Accelerators in each core for the first time on Mac mini, resulting in up to 4x faster AI performance and 2x faster graphics t
arXiv:2608.22906v1 Announce Type: new Abstract: Recent monocular 3D Gaussian Splatting (3DGS) streaming reconstruction methods have achieved impressive performance by balancing reconstruction quality
arXiv:2608.22894v1 Announce Type: cross Abstract: Arabic harmful-language detection has received considerable attention, yet Arabic text detoxification remains underexplored. We introduce AraDetox, a
arXiv:2608.22478v1 Announce Type: cross Abstract: Implied volatility surfaces summarise the option market and are central to many financial applications. Forecasting their future evolution requires mo
arXiv:2107.11800v2 Announce Type: replace Abstract: Scene text detection has become an important research area in computer vision. However, dynamic changes in scenes and the complex diversity of text
arXiv:2608.22029v1 Announce Type: new Abstract: Single-particle cryo-electron microscopy (cryo-EM) pose estimation is traditionally solved anew for each dataset, where iterative refinement is done fro
arXiv:2608.21747v1 Announce Type: cross Abstract: LLM-based coding agents generate complete software systems from high-level descriptions, yet little is known about how the format of architecture spec
arXiv:2608.23030v1 Announce Type: new Abstract: We study how an AI system can identify and model other agents in its environment from observation alone, which is a capability necessary for cooperative
arXiv:2608.15933v1 Announce Type: cross Abstract: Implicit surface representations have regained popularity because of their use in machine learning. A common component in optimization is regularizati
arXiv:2608.21721v1 Announce Type: new Abstract: Correcting health misinformation in dialogue requires more than producing a factual rebuttal: users differ in what they know, what they believe, and wha
arXiv:2608.21712v1 Announce Type: new Abstract: Transformer-based models are widely used for clinical prediction from electronic health records (EHRs), yet their architectures still require substantia
arXiv:2603.29902v2 Announce Type: replace Abstract: Interleaved text-and-image generation represents a significant frontier for Multimodal Large Language Models (MLLMs), offering a more intuitive way
arXiv:2505.21430v3 Announce Type: replace Abstract: Attribute-efficient PAC learning of sparse halfspaces has been a fundamental problem in machine learning theory. In recent years, machine learning a
arXiv:2608.22186v1 Announce Type: cross Abstract: We present AudioNoisePrints, a training-free watermarking pipeline for flow matching and diffusion TTS models, which requires minimal extra computatio
arXiv:2608.22160v1 Announce Type: new Abstract: Physical automation is scaling toward fleets of embodied machines commanded by an AI brain. Early deployments already run factories and warehouses at pr
arXiv:2608.23263v1 Announce Type: new Abstract: The FAIR Digital Object (FDO) framework mandates that metadata attribute values be expressed as persistent identifiers (PIDs) wherever possible, to prod
arXiv:2608.21558v1 Announce Type: cross Abstract: Recent advances in LLMs and the adoption of RAG systems in industry have created a need for domain-specific question-answer datasets that can assess R