Knowledge catalogue
arXiv:2604.25120v1 Announce Type: new Abstract: We study clinical trial table reasoning, where answers are not directly stored in visible cells but must be reasoned from semantic understanding through
arXiv:2603.29844v2 Announce Type: replace-cross Abstract: The development of Vision-Language-Action (VLA) models has been significantly accelerated by pre-trained Vision-Language Models (VLMs). Howeve
arXiv:2604.25572v1 Announce Type: cross Abstract: Studying nonlinear dynamical systems through their state space behavior can be challenging, and one possible alternative is to analyze them via their
Did a very different format with @reinerpope – a blackboard lecture where he walks through how frontier LLMs are trained and served. It's shocking how much you can deduce about what the labs are doing
🤖👇 Did you know that you can use the @GoogleAIStudio Gemini Live API for robotics?! Check out @ThePracticalDev blog post from my colleague @thorwebdev to learn more: Finally added Gemini Live to @poll
arXiv:2510.19669v4 Announce Type: replace Abstract: Recent reasoning Large Language Models (LLMs) demonstrate remarkable problem-solving abilities but often generate long thinking traces whose utility
arXiv:2603.20645v2 Announce Type: replace Abstract: Diffusion models have become a leading framework in generative modeling, yet their theoretical understanding -- especially for high-dimensional data
arXiv:2512.17111v2 Announce Type: replace Abstract: This paper presents the first end-to-end pipeline for Handwritten Text Recognition (HTR) for Old Nepali, a historically significant but low-resource
arXiv:2604.25209v1 Announce Type: new Abstract: Dimensionality reduction methods such as UMAP and t-SNE are central tools for visualising high-dimensional data, but their local-neighborhood objectives
arXiv:2604.25050v1 Announce Type: new Abstract: Unlike chatbots, physical AI must act while the world keeps evolving. Therefore, the inter-chunk pause of synchronous executors are fatal for dynamic ta
arXiv:2604.25794v1 Announce Type: cross Abstract: Knowledge distillation (KD) represents a vital mechanism to transfer expertise from complex teacher networks to efficient student models. However, in
Sarah Perez / TechCrunch: Divine, a Vine reboot financed by Jack Dorsey-backed nonprofit “and Other Stuff” and built by an early Twitter employee, debuts with ~500K restored Vine videos — A new projec
arXiv:2604.25423v1 Announce Type: new Abstract: Do large language models (LLMs) truly acquire embodied cognition and cultural conventions from text? We introduce demonstratives, fundamental spatial ex
arXiv:2604.25098v1 Announce Type: cross Abstract: While current Large Language Models (LLMs) exhibit remarkable reasoning capabilities through test-time compute scaling (TTS), their massive parameter
arXiv:2604.24978v1 Announce Type: new Abstract: Enterprise deep research often fails to produce decision-ready reports due to uneven information coverage, context explosion, and premature stopping. We
arXiv:2604.24997v1 Announce Type: new Abstract: Open-vocabulary semantic segmentation requires assigning pixel-level semantic labels while supporting an open and unrestricted set of categories. Traini
arXiv:2604.25231v1 Announce Type: cross Abstract: Diagram question answering (DQA) requires models to interpret structured visual representations such as charts, maps, infographics, circuit schematics
arXiv:2501.17653v3 Announce Type: replace Abstract: This work proposes variational autoencoders (VAEs) to predict a vehicle's jerk signals from torque demand in the context of limited real-world drive
Drone strikes damaged three Amazon Web Services data centers in the Middle East during military conflict, with two facilities in the UAE directly struck and a facility in Bahrain damaged by proximity
Generative models are often deployed to make decisions on behalf of users, such as vision-language models (VLMs) identifying which person in a room is a doctor to help visually impaired individuals. Y
arXiv:2604.25039v1 Announce Type: new Abstract: Large Language Models (LLMs) solve many reasoning tasks via chain-of-thought (CoT) prompting, but smaller models (about 7 to 8B parameters) still strugg
arXiv:2604.25533v1 Announce Type: new Abstract: Worldwide image geo-localization aims to infer the geographic location of an image captured anywhere on Earth, spanning street, city, regional, national
Durable execution is a hallmark of well-built distributed systems, it's been core to LangGraph since the beginning. In the agents-as-software era it is non-negotiable, because agents fail in all sorts
arXiv:2604.25914v1 Announce Type: new Abstract: Real-world data visualization (DV) requires native environmental grounding, cross-platform evolution, and proactive intent alignment. Yet, existing benc
arXiv:2604.25508v1 Announce Type: new Abstract: Safety remains an open problem in reinforcement learning (RL), especially during training. While safety filters are promising to address safe exploratio
arXiv:2604.24972v1 Announce Type: new Abstract: Clinical abnormality grounding for rare diseases is often hindered by data scarcity, making supervised fine-tuning impractical and single-pass inference
arXiv:2604.25021v1 Announce Type: new Abstract: We study online regression with the square loss in a reproducing kernel Hilbert space under a dynamic regret criterion. The learner is compared with a t
arXiv:2604.25267v1 Announce Type: new Abstract: This paper addresses the Dynamic UGV-UAV Cooperative Path Planning (DUCPP) problem involving one unmanned ground vehicle (UGV) assisted by one or more u
Kelly Cloonan / Wall Street Journal: eBay reports Q1 revenue up 19% YoY to 3.09B, vs. 3.04B est., net income up 2% to 512M, GMV up 18% to 22.2B, and forecasts Q2 revenue above estimates — The company
arXiv:2604.25319v1 Announce Type: new Abstract: The exponential surge in high-resolution remote sensing data faces a severe bottleneck in satellite-to-ground transmission. Limited downlink bandwidth f
arXiv:2604.25554v1 Announce Type: cross Abstract: Collision-free motion is often aided by tactile and proximity sensors distributed on the body of the robot due to their resistance to occlusion as opp
arXiv:2604.24770v1 Announce Type: new Abstract: Despite recent progress in automatic speech recognition (ASR), elderly ASR (EASR) remains challenging due to limited training data and the distinct acou
arXiv:2604.25158v1 Announce Type: cross Abstract: Support vector machines (SVMs) are a standard tool for binary classification, but their classical formulations are purely data-driven and offer no dir
Billionaire technology entrepreneur Elon Musk took the stand today in a landmark trial that pits him against OpenAI Group PBC Chief Executive Sam Altman, with the outcome set to have a major impact on
Elon Musk on AI during the OpenAI trial: 'It (AI) could make us more prosperous, but it could also kill us all. We want to be in a Gene Roddenberry movie, like Star Trek, not so much a James Cameron m
About five hours into Elon Musk's testimony, I typed the following sentence into my notes: 'I have never been more sympathetic to Sam Altman in my life.' Musk's direct testimony was an improvement ove
Gary Marcus discusses on CNN the legal merits of Elon Musk's lawsuit, arguing that despite questionable motivations behind the case, there may be legitimate legal grounds supporting it. The post refer
arXiv:2604.25481v1 Announce Type: cross Abstract: We introduce a Hopfield-type associative memory in which effective connectivity is multiplicatively modulated by astrocytic gains evolving under an en
arXiv:2603.16877v2 Announce Type: replace Abstract: Financial analysts face significant challenges extracting information from lengthy 10-K reports, which often exceed 100 pages. This paper presents a
arXiv:2604.25550v1 Announce Type: new Abstract: SignSGD compresses each stochastic gradient coordinate to a single bit, offering substantial memory and communication savings, but its 1-bit quantizatio
As enterprises push agentic AI out of the proof-of-concept phase and into production, AI runtime security — the ability to enforce policy at the exact moment an agent acts — is proving to be the bedro
arXiv:2604.25782v1 Announce Type: cross Abstract: Earth observation satellite imaging scheduling is a challenging NP-hard combinatorial optimisation problem central to space mission operations. While
Ernie-5.1 from @ErnieforDevs lands at #13 in Text Arena — now the #1 highest-ranked model from a Chinese lab. Strongest categories: - #9 Math - #1 Legal & Government - #4 Business, Management & Financ
arXiv:2604.24876v1 Announce Type: new Abstract: Text guided 3D medical image segmentation offers a flexible alternative to class based and spatial prompt based models by allowing users to specify regi
eugene is doing a great job covering it on the @latentspacepod paper club (will post on the youtube soon) https://x.com/picocreator/status/2047626012419313889?s=20 🗒️ Other things - FP4 MoE training -
arXiv:2410.06723v2 Announce Type: replace-cross Abstract: Pathology foundation models (PFMs) have emerged as powerful pretrained encoders for computational pathology, but their robustness under clinic
arXiv:2602.11786v2 Announce Type: replace Abstract: Traditional benchmarks for large language models (LLMs), such as HELM and AIR-BENCH, primarily assess safety through breadth-oriented evaluation acr
arXiv:2604.25119v1 Announce Type: new Abstract: Auditing the fine-tunes of open-weight generative models for harmful specialization has become a new governance challenge for model hosting platforms. T
This post likely references or riffs on the 'two wolves' metaphor—a parable about internal conflict where one must choose which inner nature (often representing good and evil, or competing impulses) t
arXiv:2602.13864v2 Announce Type: replace-cross Abstract: Learning in the presence of missing data can result in biased predictions and poor generalizability, among other difficulties, which data impu
arXiv:2604.25499v1 Announce Type: new Abstract: Time series classification is an important analytical task across diverse domains. However, its practical application is often hindered by the scarcity
arXiv:2604.25885v1 Announce Type: cross Abstract: Graph neural networks such as ParticleNet and transformer based networks on point clouds such as ParticleTransformer achieve state-of-the-art performa
arXiv:2601.22154v2 Announce Type: replace-cross Abstract: Agentic Reinforcement Learning (Agentic RL) has achieved notable success in enabling agents to perform complex reasoning and tool use. However
arXiv:2604.25680v1 Announce Type: new Abstract: Unaddressed pain in neonates can lead to adverse effects, including delayed development and slower weight gain, emphasising the need for more objective
arXiv:2604.25289v1 Announce Type: cross Abstract: Practically, training diffusion models typically requires explicit time conditioning to guide the network through the denoising sampling process. Espe
This post was co-written with Yash Munsadwala, Adam Hood, Justin Guse, and Hector Hernandez from PwC. Contract analysis often consumes significant time for legal, compliance, and procurement teams, es
arXiv:2604.25031v1 Announce Type: new Abstract: When an LLM formalizes natural language, how do we know the output is faithful? We propose a roundtrip verification approach which does not require grou
arXiv:2604.25313v1 Announce Type: new Abstract: Retrieval-Augmented Generation (RAG) models frequently produce answers grounded in parametric memory rather than the retrieved context, undermining the
Falcon Heavy All systems are looking good for Falcon Heavy’s launch of the @viasat-3 F3 mission from Florida. The 85-minute window opens at 10:13 a.m. ET. Teams are keeping an eye on weather → http://
Falcon Heavy is SpaceX's heavy-lift launch vehicle designed to carry large payloads to orbit, featuring three reusable first-stage boosters that can land and be recovered for future missions. This pos