Knowledge catalogue
arXiv:2605.05112v1 Announce Type: new Abstract: SWE-bench-style agentic reinforcement learning relies on expensive stateful trajectories, yet substantial compute is wasted on sampled rollout groups wi
arXiv:2504.05407v2 Announce Type: replace-cross Abstract: Autonomous surveillance missions in Internet of Things (IoT) networks often involve solving NP-hard combinatorial optimization problems to ens
arXiv:2511.19513v2 Announce Type: replace Abstract: Decentralized learning often involves a weighted global loss with heterogeneous node weights lambda. We revisit two natural strategies for incorpora
arXiv:2601.00264v2 Announce Type: replace Abstract: Multimodal learning has revolutionized general domain tasks, yet its application in scientific discovery is hindered by the profound semantic gap be
arXiv:2601.08623v2 Announce Type: replace Abstract: Image generation models (IGMs), while capable of producing impressive and creative content, often memorize a wide range of undesirable concepts from
arXiv:2605.04222v1 Announce Type: cross Abstract: Real-world control systems must achieve long-horizon objectives (liveness) while respecting continuous-time safety constraints, a combination that mot
arXiv:2502.04512v3 Announce Type: replace Abstract: AI advancements have been significantly driven by a combination of foundation models and curiosity-driven learning aimed at increasing capability an
日経デジタルガバナンスにて、Sakana AIの「事後学習」技術と Sakana Chat / Namazuモデルに関する記事が掲載されました。 Namazuモデル開発をリードしたリサーチサイエンティストの菅沼雅徳とチーフサイエンティストの秋葉拓哉に取材いただきました。 記事: https://www.nikkei.com/prime/digital-governance/article/DGXZ
arXiv:2605.02897v1 Announce Type: cross Abstract: LLM assistant personalities play a critical role in user experience and perceived response quality. We present a large-scale experiment of frontier LL
arXiv:2605.04560v1 Announce Type: new Abstract: Perceptual image compression focuses on preserving high visual quality under low-bitrate constraints. Most existing approaches to perceptual compression
Saw this and thought 'yes! ChatGPT voice mode is going to stop acting like a two-year-model' but that upgrade hasn't shipped just yet Introducing GPT-Realtime-2 in the API: our most intelligent voice
arXiv:2605.05008v1 Announce Type: cross Abstract: Regionalization aims to partition a spatial domain into contiguous regions that share similar characteristics, enabling more effective spatial analysi
arXiv:2509.17244v2 Announce Type: replace Abstract: We propose MADP, a novel diffusion-model-based approach for collaboration in decentralized robot swarms. MADP leverages diffusion models to generate
arXiv:2508.19651v2 Announce Type: replace Abstract: AI tasks in the car interior like identifying and localizing externally introduced objects is crucial for response quality of personal assistants. H
arXiv:2505.18118v2 Announce Type: replace-cross Abstract: Many interventions, such as vaccines in clinical trials or coupons in online marketplaces, must be assigned sequentially without full knowledg
This document likely describes OpenAI's implementation of trusted access controls and security features in GPT-5.5 and a specialized GPT-5.5-Cyber variant designed for cybersecurity applications. It p
arXiv:2605.04496v1 Announce Type: new Abstract: Long-Text Understanding (LTU) at million-token scale requires balancing reasoning fidelity with computational efficiency. Frontier long-context LLMs can
arXiv:2605.03804v1 Announce Type: new Abstract: Long-term personalized memory for LLM agents is challenging on resource-limited edge devices due to high storage costs and multimodal complexity. To add
arXiv:2605.05057v1 Announce Type: new Abstract: Open-vocabulary human-object interaction (HOI) detection requires recognizing interaction phrases that may not appear as annotated categories during tra
Searching for the right context in a sea of information is such a timeless problem in our field. I'm excited to talk about some of the approaches we've learned and benefited from at Thrive next week a
In this post, you will learn how to secure reserved GPU capacity for short-term workloads using Amazon Elastic Compute Cloud (Amazon EC2) Capacity Blocks for ML and Amazon SageMaker training plans. Th
Cursor's changelog from May 7, 2026 details new features and updates released in their AI-powered code editor. The update likely includes improvements to code completion, editor functionality, or inte
Seems like a massively underinvested area in the “pivot to enterprise.” The fact that the Labs are building their own deployment consultancies (which will take a long time) suggests a failure of imagi
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:2508.00049v2 Announce Type: cross Abstract: The formation of dark-matter halos from small cosmological perturbations generated in the early universe is a highly non-linear process typically mode
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:2605.03625v1 Announce Type: new Abstract: Generative models trained on synthetic plan data are a promising approach to generalized planning. Recent work has focused on finding any valid plan, ra
arXiv:2605.04984v1 Announce Type: cross Abstract: Long-horizon LLM agents depend on intermediate information-gathering turns, yet training feedback is usually observed only at the final answer, becaus
arXiv:2605.04221v1 Announce Type: new Abstract: Clinical named entity recognition from dental progress notes is challenging because documentation is highly unstructured, domain-specific, and often pri
arXiv:2605.04067v1 Announce Type: cross Abstract: The past few years have witnessed vibrant efforts in discovering new two-dimensional (2D) semiconductor materials from both academia and the industry,
arXiv:2605.04887v1 Announce Type: new Abstract: The exponential expansion of digital commerce in Indonesia has significantly shifted consumer interactions toward video-centric social networks, particu
arXiv:2605.04202v1 Announce Type: new Abstract: Strategic classification studies the problem where self-interested individuals or agents manipulate their response to obtain favorable decision outcomes
arXiv:2506.20616v3 Announce Type: replace Abstract: Humans possess a unique ability to perceive meaningful patterns in ambiguous stimuli, a cognitive phenomenon known as pareidolia. This paper introdu
arXiv:2605.05189v1 Announce Type: cross Abstract: How many key-value associations can a dimes d linear memory store? We show that the answer depends not only on the d^2 degrees of freedom in the memor
“She said the theme of this party is the industrial age. And you came in dressed like a train wreck.” Asking AIs to think of the equivalent to this Hold Steady lyric, but for AI. Claude was the clear
Simplex is an OpenAI initiative that reimagines software development processes by integrating Codex, OpenAI's AI code generation model, to enhance developer productivity and streamline coding workflow
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:2605.04061v1 Announce Type: cross Abstract: Understanding how large language models encode task identity from few-shot demonstrations is a central open problem in mechanistic interpretability. P
arXiv:2605.03353v1 Announce Type: cross Abstract: LLM-Agents have evolved into autonomous systems for complex task execution, with the SKILL.md specification emerging as a de facto standard for encaps
arXiv:2605.04970v1 Announce Type: new Abstract: Modern LLMs show mastery over an ever-growing range of skills, as well as the ability to compose them flexibly. However, extending model capabilities to
arXiv:2511.06754v3 Announce Type: replace-cross Abstract: Inspired by how humans reason over discrete objects and their relationships, we explore whether compact object-centric and object-relation rep
arXiv:2605.03412v1 Announce Type: cross Abstract: Passive Acoustic Monitoring (PAM) is an efficient and non-invasive method for surveying ecosystems at a reduced cost. Typically, autonomous recorders
So Mythos was, indeed, not marketing hype. Remember this is a general purpose model that just happens to be good at finding exploits because good models are good at lots of things. Expect similar from
arXiv:2505.19629v3 Announce Type: replace-cross Abstract: Self-adaptive robotic systems operate autonomously in dynamic and uncertain environments, requiring robust real-time monitoring and adaptive b
At this year’s IBM Think, Chief Executive Arvind Krishna’s keynote focused on artificial intelligence’s impact on the modern enterprise. Instead of the usual tour through features and roadmaps, his ta
Simon Willison notes on X that a ChatGPT upgrade appears to be coming soon, though specific details about the upgrade's features or timeline are not provided in this post. The post likely references r
Mark Gurman / Bloomberg: Sources: AirPods with cameras reached an advanced testing stage; the cameras will feed data to Siri to help answer questions, rather than take photos or video — Apple Inc. has
Anissa Gardizy / The Information: Sources: OpenAI and Broadcom discuss terms for Broadcom to finance initial custom chip production for ~$18B, conditioned on Microsoft buying ~40% of the chips — When
Kate Clark / Wall Street Journal: Sources: Ramp told investors it is raising 750M co-led by Iconiq Capital and GIC at a valuation of 40B+ before the investment, up from $32B in November 2025 — The fin
Elon Musk's plans to get into the AI chip manufacturing business are going to be costly. As the New York Times and CNBC report, SpaceX is planning to invest at least $55 billion into its 'Terafab' chi
arXiv:2605.04072v1 Announce Type: cross Abstract: Sparse autoencoders (SAEs) have been applied to large language models and protein language models, but not systematically to electronic health record
arXiv:2605.04700v1 Announce Type: cross Abstract: Jailbreak attacks on audio language models (ALMs) optimize audio perturbations to elicit unsafe generations, and they typically update the entire wave
arXiv:2602.03204v2 Announce Type: replace Abstract: While Mixture-of-Experts (MoE) architectures define the state-of-the-art, their theoretical success is often attributed to heuristic efficiency rath
arXiv:2605.04504v1 Announce Type: cross Abstract: Existing prompt learning for VLMs exhibits a modality asymmetry, predominantly optimizing text tokens while still relying on frozen visual encoder as
arXiv:2605.04712v1 Announce Type: new Abstract: In deep reinforcement learning (DRL), an agent is trained from a stream of experience. In a continual learning setting, such agents can suffer from plas
Terrence O'Brien / The Verge: Spotify launches Save to Spotify, a command-line tool that allows AI agents to upload AI-generated audio summaries and personal podcasts to a user's account — A new comma
arXiv:2605.04468v1 Announce Type: cross Abstract: Post-training large language models (LLMs) often suffers from catastrophic forgetting, where improvements on a target objective degrade previously acq
arXiv:2605.03034v1 Announce Type: new Abstract: Agentic systems involved in high-stake decision-making under adversarial pressure need formal guarantees not offered by existing approaches. Motivated b
arXiv:2605.04453v1 Announce Type: new Abstract: In most real-world image-to-image (I2I) scenarios, existing evaluations primarily focus on instruction following and the perceptual quality or aesthetic
arXiv:2605.03660v1 Announce Type: cross Abstract: Music-inspired Automatic Stage Lighting Control (ASLC) has gained increasing attention in recent years due to the substantial time and financial costs