Search: “papers”

arXiv:2608.14626v1 Announce Type: cross Abstract: Large Language Models (LLMs) have achieved substantial progress in safety alignment, yet their safety guarantees remain significantly weaker in low-re

arXiv:2608.14568v1 Announce Type: new Abstract: As Artificial Intelligence (AI) systems become deeply integrated into critical global infrastructure, the urgency for robust governance frameworks has i

arXiv:2608.14571v1 Announce Type: new Abstract: With soaring submission counts, stricter reciprocal review policies, widespread adoption of platforms like OpenReview, and without the offsetting pressu

arXiv:2608.15560v1 Announce Type: new Abstract: Human demonstrations offer a scalable data source for dexterous manipulation, but transferring them to robot actions remains challenging due to the embo

arXiv:2608.15193v1 Announce Type: cross Abstract: As large language model (LLM) agents are increasingly adopted in scientific research, external knowledge bases, knowledge graphs, and long-term memory

arXiv:2603.24575v2 Announce Type: replace-cross Abstract: Scalable Vector Graphics (SVG) are essential for technical illustration and digital design, offering resolution independence and semantic edit

arXiv:2608.14573v1 Announce Type: cross Abstract: Large language model (LLM) agents are increasingly capable of tool use, code execution, artifact inspection, and iterative revision, creating new oppo

arXiv:2608.14075v1 Announce Type: new Abstract: Scientific figures and tables encode essential experimental evidence, yet remain difficult for digital libraries and multimodal AI systems to retrieve a

arXiv:2608.14287v1 Announce Type: cross Abstract: Passive acoustic sensing offers a critical, cost-efficient, and, crucially, passive alternative for detecting small unmanned aerial vehicles. However,

Here are 22 more gems according to the AI among my bookmarks 1. Researchers compressed 4.1 million recipes into a two-megabyte model of human cooking. The model spans seven languages and represents 1,

How many agent skills are actually out there? There are ~3.8M SKILL.md files across 282,200 public GitHub repositories, nine months after Anthropic published the format as an open spec. This research

arXiv:2608.14369v1 Announce Type: cross Abstract: We consider the notion of shattering introduced by Ben Arous and Jagannath for spherical pure p-spin glasses with overlap q. For every pgeq 3 and 0sqr

arXiv:2507.13505v2 Announce Type: replace-cross Abstract: Cybersecurity simulation environments, such as cyber ranges, honeypots, and sandboxes, require realistic human behavior to be effective, yet n

arXiv:2511.19009v2 Announce Type: replace-cross Abstract: Large language models (LLMs) demonstrate powerful capabilities across various natural language processing tasks,yet their inherent safety vuln

Very interesting new work from Microsoft Research. (bookmark it) They show that a 4B model can be tuned to out-negotiate the GPT-5 family of models. The dispositions that make an assistant pleasant ma

arXiv:2608.13472v1 Announce Type: cross Abstract: Analog circuit design is a time-consuming, iterative process in a nonlinear and high-dimensional design space that relies heavily on expert intuition.

arXiv:2608.12351v1 Announce Type: cross Abstract: Generative artificial intelligence (GenAI) has challenged the validity of unsupervised online assessment, especially in technical subjects where plaus

arXiv:2608.12358v1 Announce Type: cross Abstract: Product and engineering teams building role-bearing AI agents face an evaluation gap: an agent can produce accurate, safe, and fluent content while st

arXiv:2608.12361v1 Announce Type: new Abstract: Neologisms, emerging terms in meaning or form, can serve as new vehicles for toxic expression, like 'country girl' as a stigmatizing label targeting fem

// Skill Misevolution in Self-Improving LLM Agents // Self-improving agents write their successes down as reusable skills. An unsafe success becomes reusable policy long after the input that triggered

Something has happened with post-training as shown by DeepSeek flash & GLM-5.3 updates. Same base, big improvement in perf to frontier levels. Can't explain this by even logit distillation etc These a

arXiv:2608.13337v1 Announce Type: new Abstract: Sparse autoencoders are meant to name the things a language model computes, and the usual way to check that a latent matters is to switch it off and see

arXiv:2608.12299v1 Announce Type: cross Abstract: Class activation mapping (CAM) is one of the most widely used visual explanation families in explainable artificial intelligence. Its purpose is intui

If you write rules in an AGENTS.md, this one is worth your time. When a coding agent follows your rule, it may have been going to do that anyway. Harness-IF separates the two by scoring 256 rules one

arXiv:2608.12036v1 Announce Type: new Abstract: AI models have achieved remarkable success across diverse domains, yet the mechanisms underlying their capabilities and the risks they may pose remain p

To the extent that AI use boosts firm performance, some early signs here that early AI adopting firms that were already doing well may start to outpace others. Data from OpenAI shows some firms are us

arXiv:2512.15211v4 Announce Type: replace Abstract: Infrared and visible image fusion is a pivotal technology in low-altitude Unmanned Aerial Vehicle (UAV) reconnaissance missions, enabling robust tar

I've been building an open-source tool for diagnosing world models, the kind that predict future frames from a starting context and a sequence of actions. It compares a rollout against ground truth an

// Actions Speak Louder Than Words // Multilingual agent evaluation compares final answers and throws the trajectory away. The trajectory fixes cost, latency, failure mode, and auditability. New resea

arXiv:2608.10715v1 Announce Type: cross Abstract: Over the past several years, LLM-powered chatbots and agents have become widely used as a tool for academic writing. LLM-assisted writing can be valua

Most semantic search queries leave something unstated. The user knows what they mean. The system doesn't. Pinecone's text match filters scope a vector search to a lexical condition (a machine number,

arXiv:2608.10530v1 Announce Type: cross Abstract: Large Language Models (LLMs) have undergone a shift from stateless conversational interfaces to autonomous agents capable of multi-step planning, tool

arXiv:2608.11075v1 Announce Type: new Abstract: Event cameras capture intensity changes asynchronously with high temporal resolution, requiring novel preprocessing methods for downstream tasks. Unlike

arXiv:2608.00961v2 Announce Type: replace-cross Abstract: AI anthropomorphism is typically treated as a problem of user misperception requiring institutional correction. Users who engage in sustained

arXiv:2608.10740v1 Announce Type: new Abstract: Effective research ideation requires moving beyond a static understanding of prior work to trace how research problems and solutions evolve across the l

Very interesting new work from Anthropic. (bookmark it) They evolve mind viruses, ideas that spread through a multi-agent system by getting each host to pass them on, then measure what governs the spr

We wrote a 36-page ArXiv whitepaper on ExtractBench 🧑‍🔬 , our effort to create the most comprehensive, schema-guided, real-world document extraction benchmark. It’s extremely detailed and covers every

Why does CLAUDE.MD keep growing? If you maintain a CLAUDE.md or an AGENTS.md, this one is worth your time. (bookmark it) This work traces why these files grow without bound. Appending an instruction i

arXiv:2608.08059v1 Announce Type: new Abstract: Post-Editing (PE) of Machine Translation (MT) output often involves repeating the same lexical and terminological corrections across many segments, espe

arXiv:2604.03159v2 Announce Type: replace-cross Abstract: Large language models with web search are increasingly used in scientific publishing agents, yet they produce BibTeX entries with pervasive fi

Link: https://arxiv.org/pdf/2604.27883 Hi, Most of use are familiar with the headache of training a neural network using gradient descent where the training error may go to zero but the test error may

arXiv:2608.08143v1 Announce Type: cross Abstract: We extend the DS@GT ARC working-note submission to the Touche 2025 Retrieval-Augmented Debate task. The task has two subtasks: generating the next utt

arXiv:2608.07552v1 Announce Type: cross Abstract: Semigroups of holomorphic self-maps of the unit disc with an interior fixed point are, by the classical Berkson--Porta representation, entirely determ

arXiv:2608.09280v1 Announce Type: new Abstract: Responsible NLP practice includes a) transparency, b) ethics, and c) societal impacts. The Responsible NLP Checklist aims to push these goals, and promo

arXiv:2608.07577v1 Announce Type: cross Abstract: A closed-set detector for autonomous driving must assign every object one of a fixed set of labels. On an object outside that set (a horse-drawn carri

arXiv:2608.08443v1 Announce Type: cross Abstract: Previous studies have shown that people can develop shared symbols, partner-specific expressions, personal idioms, inside jokes, and other parts of a