Knowledge catalogue
arXiv:2605.16610v1 Announce Type: new Abstract: High-dimensional data arise naturally in many areas of science and engineering, including machine learning, signal processing, computational physics, an
arXiv:2605.17087v1 Announce Type: new Abstract: Generative data augmentation with latent diffusion models is a promising strategy for addressing class imbalance in medical imaging, yet current approac
arXiv:2605.17500v1 Announce Type: cross Abstract: Generative text-to-image models are typically trained on large-scale web-scraped datasets that include diverse visual content such as copyrighted and
arXiv:2507.16059v2 Announce Type: replace Abstract: Following a stroke, individuals often experience mobility and balance impairments due to lower-limb weakness and loss of independent joint control.
arXiv:2601.20306v2 Announce Type: replace Abstract: All-in-one image restoration aims to address diverse degradation types using a single unified model. Existing methods typically rely on degradation
arXiv:2602.12687v2 Announce Type: replace-cross Abstract: The core of knowledge distillation lies in transferring the teacher's rich 'dark knowledge'-subtle probabilistic patterns that reveal how clas
arXiv:2509.17680v2 Announce Type: replace Abstract: Table question answering (TableQA) is a fundamental task in natural language processing (NLP). The strong reasoning capabilities of large language m
Cursor is an AI tool that can assist with software development tasks including bug fixes, feature additions, test updates, and task investigation based on work item descriptions. The platform enables
arXiv:2603.07514v3 Announce Type: replace-cross Abstract: Drifting models train one-step generators by optimizing a kernel-induced mean-shift discrepancy between the data and model distributions, with
Amrith Ramkumar / Wall Street Journal: Anthropic last week began letting Mythos users share cybersecurity threats with others who may face similar vulnerabilities, modifying its previous stance — How
arXiv:2605.15551v1 Announce Type: new Abstract: Training large-scale deep neural networks (DNNs) is resource-intensive, making model compression a practical necessity. The widely accepted ''learning a
arXiv:2605.15597v1 Announce Type: new Abstract: Modern 3D visual learning relies on observations sampled from metric 3D assets, yet existing scans, meshes, point clouds, simulations, and reconstructio
arXiv:2605.15995v1 Announce Type: cross Abstract: Learning latent representations from complex data is central to modern machine learning, spanning temporal, multimodal, and partially observed systems
arXiv:2605.15721v1 Announce Type: new Abstract: Large Language Models (LLMs) are highly sensitive to their input contexts, motivating the development of automated context engineering. However, existin
arXiv:2605.15254v1 Announce Type: new Abstract: Physics-Informed Neural Networks (PINNs) combine deep learning with physical constraints for solving partial differential equations (PDEs), and are wide
arXiv:2410.01990v3 Announce Type: replace Abstract: This paper explores alternative formulations of the Kolmogorov Superposition Theorem (KST) as a foundation for neural network design. The original K
arXiv:2508.18167v2 Announce Type: replace Abstract: Large Language Models (LLMs) have demonstrated remarkable capabilities in understanding and generating human-like text, yet they largely operate as
arXiv:2512.15067v3 Announce Type: replace-cross Abstract: The rapid growth in wireless infrastructure has increased the need to accurately estimate and forecast electromagnetic field (EMF) levels to e
Finally a semi-useful read on Mythos that is free of myth and talks about what this means more practically (not this is the end of the world as we know it, but how do we deal with faster patches and a
arXiv:2605.16056v1 Announce Type: new Abstract: Research on Vision Language Action (VLA) models has been increasing rapidly in recent years. Although some of them focus on detecting, preventing, and r
arXiv:2605.15689v1 Announce Type: new Abstract: Fine-grained image recognition classifies subcategories such as bird species or car models. While state-of-the-art (SOTA) models are accurate, they are
LTX-2.3 is Lightricks' latest open-source audio-video generation model natively supported in ComfyUI, delivering major quality improvements including enhanced details, portrait video support, and impr
arXiv:2605.16211v1 Announce Type: new Abstract: Traditional scientific modeling typically begins with fixed, instance-wise effective equations and then carries out equation-specific analysis and compu
If you're a R user: the R edition of the book is out now! AI hype can be pretty easy to find. But clear explanations are definitely harder. Deep Learning with R, Third Edition by @fchollet and Tomasz
arXiv:2605.16175v1 Announce Type: new Abstract: Pediatric critical care is a dynamic, high-stakes process involving constant monitoring and adjustments in life-saving treatments. Modeling these interv
In this post, you will learn how to set up the Confluence Cloud integration with Quick. This includes creating a knowledge base for semantic search, setting up Actions to query and manage Confluence p
arXiv:2504.09544v3 Announce Type: replace-cross Abstract: Recent advances in self-supervised deep learning have improved our ability to quantify cellular morphological changes in high-throughput micro
arXiv:2605.15923v1 Announce Type: new Abstract: Modern image encoders achieve high generalization by decoupling semantic meaning from resolution, an ability yet to be fully realized in the 3D domain.
arXiv:2605.15582v1 Announce Type: new Abstract: Modern deep learning models for change detection (CD) often struggle to explicitly represent task-relevant semantic differences. This paper proposes the
Composer 2.5 is a feature or update from Cursor, an AI-powered code editor, likely introducing improvements to its code generation and editing capabilities. The update probably includes enhancements t
Literary journals are now publishing, and awarding prizes to, AI written stories. Surprised this made it into Granta! ‘The Serpent in the Grove’ by Jamir Nazir is a story set in rural Trinidad about a
arXiv:2601.23030v2 Announce Type: replace-cross Abstract: Inference in nonlinear continuous stochastic processes on trees is challenging, particularly when observations are sparse and the topology is
Not all the good stuff at Build happens on the main stage. Join Microsoft for Startups on June 2 for Dev Your Own Way. Hands-on activations with @GitHub, @FireworksAI_HQ and @NVIDIAforStartups. Real c
okay maybe it's a good time? We have a small colbert model trained at pplx, it is a continue-training of pplx-embed-0.6b, so native multilingual, just made it open and added a section how to use MaxSi
arXiv:2605.16142v1 Announce Type: new Abstract: LLMs have shown impressive success in program synthesis, discovering programs that surpass prior solutions. However, these approaches rely on simple num
arXiv:2605.15877v1 Announce Type: cross Abstract: Continual learning enables neural networks to learn tasks sequentially without forgetting previously acquired knowledge. However, neural networks suff
arXiv:2602.14092v2 Announce Type: replace-cross Abstract: Operating complex real-world systems, such as soft robots, can benefit from precise predictive control schemes that require accurate state and
arXiv:2605.16145v1 Announce Type: cross Abstract: We develop a skew-adaptive extension of split conformal prediction for regression. The method starts from an asymmetric interval family centered at a
arXiv:2605.15308v1 Announce Type: new Abstract: LLM-driven program evolution has emerged as a powerful tool for automated scientific discovery, yet existing frameworks offer no principled guide for de
arXiv:2511.15623v2 Announce Type: replace-cross Abstract: We investigate the notion of sufficient explanation, and a sufficiency-degree as attribution score for database tuples in relation to query an
The @cursor_ai team shipped Composer 2 and now Composer 2.5 on the same Kimi K2.5 base model. Performance benchmarks are📈. Frontier quality and open-source economics. 85% of the compute powering these
arXiv:2506.14829v2 Announce Type: replace-cross Abstract: AI for Social Impact (AI4SI) is an emergent field harnessing interdisciplinarities between the fields of artificial intelligence (AI), machine
this seems quite doable in the space of a single 2-3 hour workshop — any brave soul want to try to livecode this for people as a learning exercise? How to land a job at a frontier lab https://vladfein
arXiv:2605.15913v1 Announce Type: cross Abstract: Block attention, which processes the input as separate blocks that cannot attend to one another, offers significant potential to improve KV cache reus
arXiv:2605.15533v1 Announce Type: cross Abstract: Video editing poses a significant challenge. While a series of tuning-free methods circumvent the need for extensive data collection and model trainin
We believe everyone deserves to design exactly what they dream, own their process, and never compromise because of their software. Our team is small, intense, and building what is now becoming the ind
will post more about (final) day 2 of @aiDotEngineer Singapore soon but memorable highlights i wanted to remember is how @theesabina and @bytheophana (both from nyc) were genuinely shocked and on guar
@cerebras IPO'd this week 🔥🔥🔥 More people reached out to me in the last few days is somehow higher than on my birthdays!!! Many thanks to every single one of you. In one of my first conversations at C
finally lecun says something i haven’t been saying all along for years too bad it’s wrong, and he is back on the hype train. Yann LeCun says that within a year to 18 months, we'll have a general metho
Often overlooked is the Frankfurt School’s central role, alongside French postmodernists, in forging Critical Theory and exporting it to America, where it evolved into one of the most influential (des
Yohei Nakajima discusses the lack of elegant primitive implementations for stateful agents, decision traces, and context graphs, which are frequently discussed concepts in AI but rarely demonstrated i
Yann LeCun says that within a year to 18 months, we'll have a general method for training hierarchical world models These models would learn from video and real-world data, then help plan actions in r
ChatGPT for personal finance is interesting, but you need to know what questions to ask and have enough experience to fact-check assumptions. It really needs to ship with some pre-built skills to help
I was discussing with Grok the topic of 'how to build a life on the Moon.' Then Grok offered to show me what the construction of the first lunar city would look like. Grok Imagine animated them, and h
just got back from my second langchain interrupt conf and honestly it's probably the best AI engineering conference right now. what makes it different is that it's deeply practical. less 'AI will chan
Starlink Internet access enables people to learn anything and access the global market for their goods & services, improving their standard of living The internet is the one single thing that literall
The talk about AI & politics seems to be oddly missing a segment (a) assumes extremely capable AI is possible soon and (b) has a strong belief about how to use this technology to make human life bette
arXiv:2605.14416v1 Announce Type: new Abstract: The Capacitated Vehicle Routing Problem (CVRP) is a fundamental NP-hard problem with broad applications in logistics and transportation. Real-world CVRP
arXiv:2512.03637v2 Announce Type: replace-cross Abstract: Transformer-based audio self-supervised learning (SSL) models commonly use spectrograms, vision-style Transformers, and masked modeling object
Apparently at @AIEMiami geoff complained about @SAPConcur being dead software and a SAP guy was in the audience and invited him to SAP to advise on how to do AI transformation for 6800 employees TLDR