Knowledge catalogue
arXiv:2508.06614v2 Announce Type: replace Abstract: As a class of generative artificial intelligence frameworks inspired by statistical physics, diffusion models have shown extraordinary performance i
arXiv:2604.20236v1 Announce Type: new Abstract: High-performance TSP solvers like LKH search within a sparsified candidate graph rather than over all possible edges. Graph sparsification is non-trivia
arXiv:2604.20317v1 Announce Type: new Abstract: GAN-based facial attribute editing is widely used in virtual avatars and social media but often suffers from attribute entanglement, where modifying one
arXiv:2604.20783v1 Announce Type: new Abstract: Internal ice layers imaged by radar provide key evidence of snow accumulation and ice dynamics, but radar-derived layer boundary observations are often
Plugins and skills are extensions that enhance the capabilities of OpenAI's Codex, allowing developers to integrate custom functionality and extend the model's functionality beyond its base capabiliti
[...] if you ever needed another reason to learn in public by digital gardening or podcasting or streaming or whathaveyou, add on that people will assume you’re more competent than you are. This will
arXiv:2604.20730v1 Announce Type: new Abstract: Multimodal Large Language Models (MLLMs) have shown promising capabilities in generating Scalable Vector Graphics (SVG) via direct code synthesis. Howev
arXiv:2604.20147v1 Announce Type: cross Abstract: Data-driven decision-making under uncertainty typically presumes the collection of historical data from an unknown target probability distribution. Ho
arXiv:2604.20336v1 Announce Type: new Abstract: Co-manipulation requires multiple humans to synchronize their motions with a shared object while ensuring reasonable interactions, maintaining natural p
Enterprise IT is shifting from AI experimentation to enterprise AI enablement, pushing companies to modernize systems and unlock data value. At the same time, cloud-first strategies and evolving gover
arXiv:2407.17395v5 Announce Type: replace Abstract: Machine Learning research, including work promoting fair or equitable algorithms, often relies on the concept of a data-generating probability distr
arXiv:2604.20123v1 Announce Type: new Abstract: In natural images, object skeletons are used to represent geometric shapes. However, even slight variations in pose or movement can cause noticeable cha
arXiv:2509.22343v2 Announce Type: replace-cross Abstract: Reasoning capability is essential to ensure the factual correctness of the responses of transformer-based Large Language Models (LLMs), and ro
Codex is OpenAI's AI model specialized in understanding and generating code across multiple programming languages. Based on OpenAI's documentation, it likely explains Codex's capabilities for code com
This OpenAI Academy course covers how to effectively use Codex, OpenAI's AI model designed for code generation and understanding. It likely includes practical guidance on prompting techniques, best pr
arXiv:2604.18881v1 Announce Type: cross Abstract: Supervised learning with Earth observation inputs is often limited by the sparsity of high-quality labeled or in-situ measured data to use as training
arXiv:2604.19518v1 Announce Type: new Abstract: Decentralized optimization enables multiple devices to learn a global machine learning model while each individual device only has access to its local d
AFAIK this is the first time it's been made official from an OpenAI staffer - the `/backend-api/codex/responses` endpoint that Pi and Opencode (IIUC) uses is officially supported! :D This is really gr
This guide covers the fundamentals and best practices for developing AI-powered applications, likely including key stages from ideation through deployment, technology stack considerations, and integra
Jeremy Howard shares positive impressions of working with Kimi Moonshot's K2.6 model for two hours, noting it performed well despite being used somewhat unexpectedly. The post suggests K2.6 demonstrat
This post appears to reference regulatory or policy 'clampdowns' on AI, with the author expressing anticipation that OpenAI will face similar restrictions. Without access to the full context or surrou
Company-wise memory in Amazon Bedrock, powered by Amazon Neptune and Mem0, provides AI agents with persistent, company-specific context—enabling them to learn, adapt, and respond intelligently across
arXiv:2512.16059v2 Announce Type: replace-cross Abstract: In-Context Learning (ICL) has become a standard technique for adapting Large Language Models (LLMs) to specialized tasks by supplying task-spe
In this post, we walk through building a scalable, event-driven transcription pipeline that automatically processes audio files uploaded to Amazon Simple Storage Service (Amazon S3), and show you how
arXiv:2604.19658v1 Announce Type: new Abstract: Damage identification is a core task in structural health monitoring. In practice, however, its reliability is often compromised by confounding non-dama
arXiv:2507.01918v3 Announce Type: replace-cross Abstract: We develop a rotation-invariant neural network that provides the global minimum-variance portfolio by jointly learning how to lag-transform hi
arXiv:2604.19171v1 Announce Type: new Abstract: Heterogeneous graphs have attracted increasing attention for modeling multi-typed entities and relations in complex real-world systems. Multi-label node
arXiv:2502.09741v2 Announce Type: replace Abstract: Large Language Models (LLMs) typically represent numbers using multiple tokens, which requires the model to aggregate these tokens to interpret nume
arXiv:2604.18907v1 Announce Type: cross Abstract: A central challenge in program induction has long been the trade-off between symbolic and neural approaches. Symbolic methods offer compositional gene
arXiv:2604.19149v1 Announce Type: cross Abstract: Thinking LLMs produce reasoning traces before answering. Prior activation steering work mainly targets on shaping these traces. It remains less unders
arXiv:2604.19680v1 Announce Type: new Abstract: In image restoration, single-step discriminative mappings often lack fine details via expectation learning, whereas generative paradigms suffer from ine
Judging AGI by how well it can mimic us is a category error, because mimicry isn't intelligence and isn't general. We should judge AGI by how well it learns to do things we didn't teach it (including
arXiv:2407.11107v3 Announce Type: replace-cross Abstract: Model predictive control (MPC) has played a more crucial role in various robotic control tasks, but its high computational requirements are co
ComfyUI announced the availability of GPT Image 2 through a partner integration. The post links to a blog entry providing details about the new image generation capabilities and how to access them wit
arXiv:2604.19043v1 Announce Type: new Abstract: Efficient construction of models capturing the preconditions and effects of actions is essential for applying AI planning in real-world domains. Extensi
arXiv:2601.21092v2 Announce Type: replace Abstract: Planning effective interventions in biological systems requires treatment-effect models that adapt to unseen biological contexts by identifying thei
arXiv:1902.07683v1 Announce Type: cross Abstract: Over the past 15 years, the volume, richness and quality of data collected from the combined social networking platforms has increased beyond all expe
arXiv:2604.19670v1 Announce Type: cross Abstract: Effective human-robot teaming is crucial for the practical deployment of robots in human workspaces. However, optimizing joint human-robot plans remai
arXiv:2604.19383v1 Announce Type: cross Abstract: Metal-organic frameworks (MOFs) are a major target of machine-learning-based property prediction, yet most models assume that a single framework repre
Oh you came so close there. You almost saw it. The part about 'advising law enforcement on how to arrest those extremists'. You're almost there. You're almost ready for the next step: That the people
arXiv:2604.18800v1 Announce Type: cross Abstract: We study online learning for new products on a platform that makes capacity-constrained assortment decisions on which products to offer. For a newly l
arXiv:2512.12448v2 Announce Type: replace Abstract: Efforts to improve Kolmogorov--Arnold networks (KANs) with architectural enhancements have been stymied by the complexity those enhancements bring,
arXiv:2512.00993v2 Announce Type: replace Abstract: Composition matters during the photo-taking process, yet many casual users struggle to frame well-composed images. To provide composition guidance,
arXiv:2511.08418v2 Announce Type: replace Abstract: Accurately simulating systems governed by PDEs, such as voltage fields in cardiac electrophysiology (EP) modelling, remains a significant modelling
arXiv:2602.20323v5 Announce Type: replace-cross Abstract: Reliable object manipulation requires understanding physical properties that vary across objects and environments. Vision-language model (VLM)
Principal Platform Engineer at Sakana AI https://sakana.ai/careers/#principal-platform-engineer At Sakana AI, we are building a sovereign, unified data platform for Japan's defense sector and largest
arXiv:2604.19099v1 Announce Type: cross Abstract: Education is not merely the transmission of information or the optimisation of individual performance; it is a fundamentally social, constructive, and
arXiv:2604.18939v1 Announce Type: new Abstract: Table annotation is crucial for making web and enterprise tables usable in downstream NLP applications. Unlike textual data where learning semantically
arXiv:2604.19372v1 Announce Type: cross Abstract: Graph representation learning has achieved notable success in encoding graph-structured data into latent vector spaces, enabling a wide range of downs
arXiv:2604.18857v1 Announce Type: cross Abstract: In continual learning, the primary challenge is to learn new information without forgetting old knowledge. A common solution addresses this trade-off
The 'Very Fine People' Hoax just got a major plot twist. It turns out the Unite the Right group that was involved in Charlottesville was a LEFT-WING FUNDED FRONT GROUP. So, this was a HOAX upon a HOAX
There seems to be some excitement around “ChatGPT’s powerful new image engine”, but as ever, its functional understanding of the world seems limited. I first learned about the new system when some som
arXiv:2604.19218v1 Announce Type: new Abstract: Learning identity-discriminative representations with multi-scene generality has become a critical objective in person re-identification (ReID). However
arXiv:2604.19571v1 Announce Type: new Abstract: Language-driven 3D Gaussian Splatting (3DGS) editing provides a more convenient approach for modifying complex scenes in VR/AR. Standard pipelines typic
What are the odds that the unnamed senator who called the effort to pass the SAVE America Act a “charade” professes unqualified support for the bill when talking to constituents and donors? Statistica
arXiv:2409.18660v2 Announce Type: replace-cross Abstract: Feedback from artificial intelligence (AI) is increasingly easy to access and research has already established that people learn from it. But
Workspace agents are AI systems designed to automate tasks and workflows within collaborative work environments, likely covering how these agents can handle scheduling, communication, document managem
This guide from Databricks covers practical techniques and best practices for fine-tuning large language models, including methodologies for adapting pre-trained LLMs to specific tasks and domains. It
arXiv:2604.17312v1 Announce Type: new Abstract: Reinforcement learning (RL) has emerged as a powerful post-training paradigm for enhancing the reasoning capabilities of large language models (LLMs). H
arXiv:2604.16936v1 Announce Type: new Abstract: Feature reconstruction techniques are widely applied for few-shot fine-grained image classification (FSFGIC). Our research indicates that one of the mai