Knowledge catalogue
Elon's team just did something nobody's talking about. They replaced Starlink's call center with an AI. 🤯 And the results are insane. 1 in 5 people who called Starlink bought Starlink on the call. 70%
arXiv:2603.22823v3 Announce Type: replace Abstract: Context. The problem of comparative evaluation of communication protocols for task orchestration by large language model (LLM) agents is considered.
arXiv:2604.21733v1 Announce Type: new Abstract: The increasing integration of artificial intelligence (AI) in higher education has raised important questions regarding students' transparency in report
arXiv:2604.21668v1 Announce Type: new Abstract: The world knowledge and reasoning capabilities of text-based large language models (LLMs) are advancing rapidly, yet current approaches to human motion
arXiv:2604.21554v1 Announce Type: new Abstract: Under the EU AI Act, translating AI governance requirements into software development practice remains challenging. While AI governance frameworks exist
arXiv:2604.21229v1 Announce Type: cross Abstract: Large language model assistants are increasingly expected to retain and reason over information accumulated across many sessions. We introduce Engrama
arXiv:2604.21264v1 Announce Type: new Abstract: Person-Job Fit (PJF) is a critical component for online recruitment. Existing approaches face several challenges, particularly in handling low-quality j
arXiv:2604.21137v1 Announce Type: cross Abstract: Analyzing the reasoning patterns of students in science classrooms is critical for understanding knowledge construction mechanism and improving instru
arXiv:2512.05591v2 Announce Type: replace-cross Abstract: Large language model post-training relies on reinforcement learning to improve model capability and alignment quality. However, the off-policy
arXiv:2604.21907v1 Announce Type: cross Abstract: Equity Bias is a philosophical and practical framework for building smarter, more equitable AI systems. Grounded in hermeneutic philosophy and epistem
arXiv:2604.20854v1 Announce Type: cross Abstract: Retrieval-Augmented Generation (RAG) grounds language models in factual evidence but introduces critical challenges regarding knowledge conflicts betw
arXiv:2604.20972v1 Announce Type: new Abstract: Content moderation systems are typically evaluated by measuring agreement with human labels. In rule-governed environments this assumption fails: multip
Europe authorized Moderna's combination mRNA flu-COVID vaccine before the United States did. This dual-purpose vaccine addresses two respiratory viruses in a single shot. The European Commission grant
The Economist: Europe's dependence on US companies in tech and finance is in no small part its own fault after overregulation left European businesses too weak to compete — It wasn't long after blue j
arXiv:2604.21345v1 Announce Type: new Abstract: We present a reusable evaluation pipeline for generative AI applications, instantiated for AI meeting summaries and released with a public artifact pack
arXiv:2604.21690v1 Announce Type: new Abstract: Explaining deep neural network predictions on genome sequences enables biological insight and hypothesis generation-often of greater interest than predi
arXiv:2604.21928v1 Announce Type: new Abstract: Automatic Speech Recognition (ASR) is traditionally evaluated using Word Error Rate (WER), a metric that is insensitive to meaning. Embedding-based sema
arXiv:2604.21407v1 Announce Type: new Abstract: When approximating an intractable density via variational inference (VI) the variational family is typically chosen as a simple parametric family that v
arXiv:2604.21890v1 Announce Type: new Abstract: Event extraction identifies the central aspects of events from text. It supports event understanding and analysis, which is crucial for tasks such as in
everyones gonna be here! I’ll be in San Francisco from May 9-16 for @LangChain Interrupt 🦜 If you’re around, DM me, I’d love to chat about applied AI, agents, and running agentic systems in production
arXiv:2604.21068v1 Announce Type: cross Abstract: The most technologically consequential materials are often the rarest: they occupy narrow regions of chemical space, obey competing physical constrain
arXiv:2604.21300v1 Announce Type: new Abstract: Learning robust representations of authorial style is crucial for authorship attribution and AI-generated text detection. However, existing methods ofte
arXiv:2410.16006v3 Announce Type: replace Abstract: A common challenge towards the adaptability of Large Language Models (LLMs) is their ability to learn new languages over time without hampering the
arXiv:2604.21291v1 Announce Type: cross Abstract: Controllable human video generation aims to produce realistic videos of humans with explicitly guided motions and appearances,serving as a foundation
Emma Dunkley / Financial Times: EY survey of 18,000 people across 23 countries: ~49% of consumers have used AI over the past six months to support their savings and investment decisions — Gen Z and mi
arXiv:2510.18914v4 Announce Type: replace-cross Abstract: Large language models often display undesirable behaviors embedded in their internal representations, undermining fairness, inconsistency drif
arXiv:2604.21711v1 Announce Type: cross Abstract: Fair machine learning (ML) methods help identify and mitigate the risk that algorithms encode or automate social injustices. Algorithmic approaches al
arXiv:2604.21420v1 Announce Type: new Abstract: Quality Estimation (QE) aims to assess machine translation quality without reference translations, but recent studies have shown that existing QE models
arXiv:2604.20913v1 Announce Type: new Abstract: Large language models are increasingly deployed on CPU-only platforms where memory bandwidth is the primary bottleneck for autoregressive generation. We
arXiv:2506.19579v3 Announce Type: replace-cross Abstract: Robotic scene understanding increasingly relies on Vision-Language Models (VLMs) to generate natural language descriptions of the environment.
Falcon Heavy is SpaceX's heavy-lift launch vehicle, the most powerful operational rocket in the world, capable of carrying large payloads to orbit and beyond. The rocket uses three Falcon 9 first stag
The FCC has expanded its foreign-made router ban to also cover consumer Wi-Fi hotspots and LTE/5G home-internet devices, though existing products and phones with hotspot features are not affected. Cel
Simon Willison requested that Hugging Face add a repository size sorting option to help users find and filter models by storage requirements, specifically mentioning interest in locating DeepSeek quan
arXiv:2411.11707v3 Announce Type: replace-cross Abstract: By adapting Large Language Models (LLMs) to domain-specific tasks or enriching them with domain-specific knowledge, we can fully harness the c
arXiv:2510.04772v2 Announce Type: replace-cross Abstract: Developing generalizable surgical AI requires multi-institutional data, yet patient privacy constraints preclude direct data sharing, making F
Feel like very few serious people make the argument Britain should develop its own LLM? Certainly not an argument you see made in Westminster often during the sovereignty debate. Also some other eyebr
arXiv:2604.21555v1 Announce Type: new Abstract: Sentence embedding techniques aim to encode key concepts of a sentence's meaning in a vector space. However, the majority of evaluation approaches for s
arXiv:2604.21667v1 Announce Type: cross Abstract: Beyond exploring disaggregated labels for modeling perspectives, annotator rationales provide fine-grained signals of individual perspectives. In this
arXiv:2604.21927v1 Announce Type: new Abstract: Continual learning (CL) studies how models acquire tasks sequentially while retaining previously learned knowledge. Despite substantial progress in benc
arXiv:2604.21331v1 Announce Type: new Abstract: The current practice of dexterous manipulation generally relies on a single wrist-mounted view, which is often occluded and limits performance on tasks
arXiv:2604.21698v1 Announce Type: new Abstract: Persistent homology, a method from topological data analysis, extracts robust, multi-scale features from data. It produces stable representations of tim
arXiv:2506.09998v2 Announce Type: replace-cross Abstract: Large language models (LLMs) can often accurately describe probability distributions using natural language, yet they still struggle to genera
arXiv:2510.04823v2 Announce Type: replace Abstract: Generating synthetic CT (sCT) from MRI or CBCT plays a crucial role in enabling MRI-only and CBCT-based adaptive radiotherapy, improving treatment p
This entry discusses conditioning enhancement and reference latent control for FLUX.2 Klein 9B in ComfyUI, built from empirical analysis of the model's dual-stream architecture. The Identity Feature T
arXiv:2601.02438v3 Announce Type: replace-cross Abstract: Software vulnerability detection can be formulated as a binary classification problem that determines whether a given code snippet contains se
For the last 72 hours since ml-intern launched we have had over 500+ autonomous AI research projects running on the Space at all times. Some insane ones I saw: 1. A new AI paradigm from scratch — tryi
for the record, i put 'undecided' as the last choice, not the second choice, @nikitabier sorry i know this is minor but it should be a 2 second fix in cursor https://x.com/kr0der/status/20477027526678
arXiv:2604.20920v1 Announce Type: new Abstract: Scaling large language models to long contexts is challenging due to the quadratic computational cost of full attention. Mitigation approaches include K
arXiv:2604.21079v1 Announce Type: new Abstract: Vision-language models benefit from high-resolution images, but the increase in visual-token count incurs high compute overhead. Humans resolve this ten
Joe Wertz / Bloomberg: France's forecasting office refers suspected weather sensor tampering at Paris airport to police, after detecting unusual readings alongside Polymarket betting — France's foreca
arXiv:2604.20902v1 Announce Type: cross Abstract: While standard flow-matching models transport noise to data uniformly, incorporating an explicit generation order - specifically, establishing coarse,
arXiv:2604.21786v1 Announce Type: new Abstract: Social media platforms have become primary arenas for climate communication, generating millions of images and posts that - if systematically analysed -
arXiv:2604.21716v1 Announce Type: new Abstract: Prior work evaluates code generation bias primarily through simple conditional statements, which represent only a narrow slice of real-world programming
arXiv:2604.21391v1 Announce Type: cross Abstract: Bridging high-level semantic understanding with low-level physical control remains a persistent challenge in embodied intelligence, stemming from the
arXiv:2509.23649v2 Announce Type: replace-cross Abstract: Generative recommendation, which directly generates item identifiers, has emerged as a promising paradigm for recommendation systems. However,
arXiv:2604.21910v1 Announce Type: new Abstract: Scientific workflow systems automate execution -- scheduling, fault tolerance, resource management -- but not the semantic translation that precedes it.
arXiv:2604.21511v1 Announce Type: cross Abstract: Learned Sparse IR models, such as SPLADE, offer an excellent efficiency-effectiveness tradeoff. However, they rely on the underlying backbone vocabula
arXiv:2604.21479v1 Announce Type: new Abstract: Large language models (LLMs) have recently demonstrated strong reasoning capabilities and attracted increasing research attention in the field of autono
arXiv:2604.21321v1 Announce Type: new Abstract: Monitoring frying oil degradation is critical for food safety, yet current practice relies on destructive wet-chemistry assays that provide no spatial i
arXiv:2604.21189v1 Announce Type: new Abstract: Collision avoidance for robotic manipulators requires enforcing full-body safety constraints in high-dimensional configuration spaces. Control Barrier F