Knowledge catalogue
arXiv:2601.22400v2 Announce Type: replace-cross Abstract: We study the problem of learning complex-valued linear dynamical systems (CLDS) with sector-bounded spectrum. This class captures oscillatory
arXiv:2605.07116v1 Announce Type: cross Abstract: Physics-informed neural solvers offer a promising route to model-based reinforcement learning in continuous time, where optimal feedback synthesis is
arXiv:2605.07105v1 Announce Type: cross Abstract: Language model (LM) alignment improves model outputs to reflect human preferences while preserving the capabilities of the base model. The most common
arXiv:2603.05539v2 Announce Type: replace-cross Abstract: We introduce VDCook: a self-evolving video data operating system, a configurable video data construction platform for researchers and vertical
arXiv:2605.07896v1 Announce Type: cross Abstract: The rapid convergence of artificial intelligence (AI) toward conversational chatbot interfaces marks a critical moment for the industry. This paper ar
Take Mythos seriously, but don’t panic. Here are the facts: • Mythos is a real threat. And it can really help with finding bugs (as @mozilla’s new report documents well). • It’s not unique; similar vu
We are less safe as a society by keeping Mythos (or any other smart model) tightly gated so only a few companies get it. Protecting 100 companies is not enough. There are 96 million open source projec
arXiv:2505.13246v2 Announce Type: replace Abstract: Purpose: This paper introduces the concept of 'Agentic Publication,' a novel LLM-driven framework designed to complement traditional scientific publ
arXiv:2605.03042v1 Announce Type: cross Abstract: This report describes ARIS (Auto-Research-in-sleep), an open-source research harness for autonomous research, including its architecture, assurance me
arXiv:2605.04083v1 Announce Type: new Abstract: Much of the focus in RL today is on evaluation design: building meaningful evals that serve simultaneously as benchmarks and as well-defined reward sign
arXiv:2605.04077v1 Announce Type: cross Abstract: Reinforcement learning with verifiable rewards (RLVR) has become a central paradigm for improving reasoning and code generation in large language mode
arXiv:2605.04130v1 Announce Type: new Abstract: High-fidelity simulations, such as computational fluid dynamics and finite element analysis, are essential for modeling complex engineering systems but
arXiv:2605.03900v1 Announce Type: new Abstract: Frontier AI systems perform best in settings with clear, stable, and verifiable objectives, such as code generation, mathematical reasoning, games, and
arXiv:2605.04246v1 Announce Type: cross Abstract: In this article, we study unbalanced optimal transport (UOT) and establish a control-theoretic dynamical extension, which we call the unbalanced densi
arXiv:2605.04279v1 Announce Type: new Abstract: Transformer self-attention can be interpreted as a gradient flow on the unit sphere, in which tokens evolve under softmax interaction potentials and ten
arXiv:2605.04282v1 Announce Type: new Abstract: Visual SLAM is a core component of spatial computing systems, yet deploying learned local feature extractors on microcontroller-class hardware remains c
arXiv:2605.05113v1 Announce Type: new Abstract: We study signal propagation in linear recurrent models at finite width. While existing signal propagation theory relies predominantly on the infinite-wi
arXiv:2605.04932v1 Announce Type: cross Abstract: We study long-horizon deployment of a frozen predictor under dynamic covariate shift. A time-domain Poincare inequality reduces temporal risk volatili
arXiv:2605.04115v1 Announce Type: new Abstract: Learning in neural systems arises from synaptic changes that reshape the representations underlying behavior. While low-rank recurrent neural networks (
arXiv:2605.03847v1 Announce Type: new Abstract: Distributed collaborative intelligence (DCI), encompassing edge-to-edge architectures, federated learning, transfer learning, and swarm systems, creates
arXiv:2605.03216v1 Announce Type: cross Abstract: Strategy-proofness is a fundamental desideratum in mechanism design, ensuring truthful reporting and robust participation. Stability is another centra
arXiv:2601.07389v2 Announce Type: replace Abstract: Post-training of large language models routinely interleaves supervised fine-tuning (SFT) with reinforcement learning (RL). These two methods have d
arXiv:2605.05017v1 Announce Type: cross Abstract: Embodied AI (EAI) systems are rapidly transitioning from simulations into real-world domestic and other sensitive environments. However, recent EAI so
arXiv:2605.04542v1 Announce Type: new Abstract: Recent analyses question whether reinforcement learning (RL) is responsible for strong reasoning in large language models (LLMs). At the same time, dist
arXiv:2504.10808v3 Announce Type: replace Abstract: Detecting empathy from video interactions has emerging applications, yet raw videos that could be used for training AI models are rarely available d
Seems plausible people will eventually periodize AI history into: - pre/post AlphaGo (waking up China re: AI + researchers re: deep learning) - pre/post ChatGPT (waking up capital + accelerating comme
arXiv:2605.04893v1 Announce Type: cross Abstract: Large language models hallucinate in predictable ways: attention routing fails by over-concentrating on a narrow set of positions, or by spreading so
arXiv:2605.04126v1 Announce Type: new Abstract: This paper develops convolutional neural network (CNN) methods for simultaneous approximation and elliptic boundary value problems on compact Riemannian
arXiv:2602.14872v2 Announce Type: replace Abstract: Reinforcement learning with verifiable rewards (RLVR) has been a main driver of recent breakthroughs in large reasoning models. Yet it remains a mys
arXiv:2605.05080v1 Announce Type: new Abstract: We administer 45 validated psychometric questionnaires to 50 large language models (LLMs) to identify the dimensions along which LLMs differ psychometri
arXiv:2603.01097v2 Announce Type: replace Abstract: Continuous knowledge updating for pre-trained large language models (LLMs) is increasingly necessary yet remains challenging. Although inference-tim
arXiv:2605.04078v1 Announce Type: new Abstract: Reasoning distillation aims to transfer multi-step reasoning capabilities from large language models to smaller, more efficient ones. While recent metho
arXiv:2605.05148v1 Announce Type: new Abstract: One of the major differentiators unlocked by learned codecs relative to their hard-coded traditional counterparts is their ability to be optimized direc
One of the major differentiators unlocked by learned codecs relative to their hard-coded traditional counterparts is their ability to be optimized directly to appeal to the human visual system. Despit
Jan Leike, OpenAI's safety and alignment lead, resigned in May 2024, citing concerns about the company's commitment to safety practices and the deprioritization of safety work relative to product deve
arXiv:2605.01546v1 Announce Type: cross Abstract: Sixth-generation (6G) networks are increasingly envisioned as AI-native infrastructures integrating communication, sensing, and computing into a unifi
arXiv:2512.12109v3 Announce Type: replace-cross Abstract: Automated eligibility systems increasingly determine access to essential public benefits, but the explanations they generate often fail to ref
arXiv:2605.03590v1 Announce Type: new Abstract: Recent large language models (LLMs) show strong speech recognition and translation capabilities for high-resource languages. However, African languages
arXiv:2605.01415v1 Announce Type: new Abstract: Recent AI systems compress the distance between capability growth and capability deployment. Earlier high-risk technologies were slowed by capital inten
arXiv:2509.20789v4 Announce Type: replace Abstract: The remarkable success of modern AI has been closely tied to scaling laws, yet the finite supply of high-quality data makes data efficiency--learnin
arXiv:2605.03710v1 Announce Type: cross Abstract: Bayesian predictive inference propagates parameter uncertainty to quantities of interest through the posterior-predictive distribution. In practice, t
arXiv:2605.02346v1 Announce Type: cross Abstract: Bare-metal operational technology (OT) devices -- especially the microcontrollers running Modbus/TCP and CoAP at the base of industrial control system
Big data management startup Collibra BV is trying to position itself as the nerve center for artificial intelligence agents with the launch of its new AI Command Center offering. It’s designed to give
arXiv:2605.04013v1 Announce Type: cross Abstract: Sampling from unnormalized multimodal distributions with limited density evaluations remains a fundamental challenge in machine learning and natural s
arXiv:2605.02949v1 Announce Type: new Abstract: We propose a novel method of understanding disease transformation from a healthy baseline with biomarker-level explainability. By modeling the biomarker
arXiv:2605.03065v1 Announce Type: new Abstract: Generative control policies (GCPs), such as diffusion- and flow-based control policies, have emerged as effective parameterizations for robot learning.
arXiv:2605.03283v1 Announce Type: cross Abstract: We provide a unified theoretical analysis of Linear Discriminant Analysis with simultaneous multilabel scatter matrix formulations and Stiefel orthogo
arXiv:2601.20303v2 Announce Type: replace Abstract: Estimating object mass from visual input is challenging because mass depends jointly on geometric volume and material-dependent density, neither of
arXiv:2605.02937v1 Announce Type: new Abstract: Deep learning in de novo protein design has achieved atomic-level fidelity. However, existing models remain largely non-deliberative: they directly synt
🇺🇸 Rogan and Chamath just nailed why Elon doesn't care what you think about him. He's not playing defense. He's not managing his image. He posted '10T or bust' and logged off. He's just himself, alway
arXiv:2605.03301v1 Announce Type: new Abstract: De-identification of clinical text remains essential for secondary use of electronic health records (EHRs), yet public benchmarks such as i2b2 2006/2014
arXiv:2605.03780v1 Announce Type: cross Abstract: Transformers are effective at inferring the latent task from context via two inference modes: recognizing a task seen during training, and adapting to
arXiv:2408.12622v3 Announce Type: replace-cross Abstract: Artificial intelligence (AI) is reshaping society, from video generation to medical diagnosis, coding agents to autonomous vehicles. Yet resea
arXiv:2510.09511v2 Announce Type: replace-cross Abstract: Variable stiffness is a key capability in biological and robotic systems, enabling adaptive interaction across tasks and environments. Mechani
arXiv:2605.03838v1 Announce Type: new Abstract: We introduce TRACE, a cross-domain engineering framework for trustworthy agentic AI in operationally critical domains. TRACE combines a four-layer refer
arXiv:2605.00881v1 Announce Type: cross Abstract: Speckle noise severely limits the quality of images acquired from coherent imaging systems such as Synthetic Aperture Radar (SAR) and medical ultrasou
arXiv:2605.01288v1 Announce Type: new Abstract: In deep networks with small initialization, training exhibits long plateaus separated by sharp feature-acquisition transitions. Whereas shallow nonlinea
arXiv:2602.00074v2 Announce Type: replace-cross Abstract: While large language models (LLMs) can support clinical documentation needs, standalone tools struggle with 'workflow friction' from manual da
arXiv:2605.00425v1 Announce Type: new Abstract: Reinforcement learning (RL) has significantly advanced the ability of large language model (LLM) agents to interact with environments and solve multi-tu
Data quality is a foundational prerequisite for successful AI applications, often more important than model complexity or sophistication. The article emphasizes that clean, well-organized data directl