Knowledge catalogue
Ram Iyer / TechCrunch: Ramp launches Router, an AI model routing service it has been using internally over the past three years, in the US; Router is free to use for the rest of 2026 — Corporate expen
arXiv:2608.18300v1 Announce Type: new Abstract: LLM-as-a-Judge, which leverages a large language model to evaluate natural language generated by another AI application or model, has become a standard,
#1 open-weight model on Harvey's Legal Agent benchmark! 🙌 Strong enough to handle professional tasks. Small enough to run on your local machine. Qwen3.8-27B is becoming part of your everyday workflows
arXiv:2608.17293v1 Announce Type: cross Abstract: Existing research on irregular time-series forecasting has primarily focused on model design, while evaluation metrics remain insufficiently studied.
arXiv:2608.16926v1 Announce Type: new Abstract: Data selection in supervised fine-tuning aims to select a small set of effective samples from large-scale candidate data, reducing training cost while p
arXiv:2509.10818v2 Announce Type: replace Abstract: When consequential decisions depend on knowledge that exists nowhere in writing, LLMs hallucinate not from retrieval failure but from model absence.
Four Tesla V100s from 2017 matched my RTX 5090 on single-request Qwen 3.8 decode. Repo: https://github.com/dnv2003/v100-skinny https://i.redd.it/5ws2ak3uqckh1.gif The 5090 was not being held back. It
arXiv:2608.17455v1 Announce Type: cross Abstract: Purcell's swimmer is a well-known planar model of a swimming microorganism, governed by low Reynolds number hydrodynamics, which is comprised of three
arXiv:2608.17443v1 Announce Type: new Abstract: Knowledge Graph Reasoning (KGR) aims to discover latent facts by leveraging the structural evidence available in KGs, posing a challenge to the structur
Vibe coding company Replit debuted Free Mode today, a new feature powered by OpenAI’s GPT-5.6 Luna model. The joint announcement, shared exclusively with Fortune, heralds an enhanced partnership betwe
arXiv:2608.17325v1 Announce Type: new Abstract: Tokenization is a fundamental component of language modeling pipelines. Despite its importance, it is often fixed, even though it significantly impacts
arXiv:2608.16955v1 Announce Type: cross Abstract: Post-disaster damage to terrestrial infrastructure can disrupt wireless coverage,while Uncrewed Aerial Vehicle (UAV) swarms provide a promising soluti
arXiv:2508.07195v2 Announce Type: replace-cross Abstract: Recent advances have demonstrated that Large Language Models (LLMs) can be effectively adapted for time series forecasting, revealing strong p
arXiv:2501.18898v4 Announce Type: replace Abstract: Generating full-body human gestures based on speech signals remains challenges on quality and speed. Existing approaches model different body region
arXiv:2511.23043v2 Announce Type: replace-cross Abstract: We present a probabilistic data-driven weather model providing ensembles of high spatial resolution realizations of 87 variables at arbitrary
arXiv:2603.14894v3 Announce Type: replace-cross Abstract: Trust and ethical concerns due to the widespread deployment of opaque machine learning (ML) models motivating the need for reliable model expl
arXiv:2608.15689v1 Announce Type: cross Abstract: This study presents a hybrid epidemiological and behavioural framework to simulate the spread of health misinformation on social media. We extend the
arXiv:2608.14783v1 Announce Type: new Abstract: Part-aware 3D object generation is essential for graphics applications such as controllable modeling, editing, and articulation, where objects are repre
arXiv:2608.15131v1 Announce Type: new Abstract: Digital platforms govern by changing rules: rankings, monetization thresholds, moderation standards, verification systems, disclosure requirements, appe
arXiv:2608.14790v1 Announce Type: new Abstract: Instruction-based video editing is commonly built on video-pretrained generative backbones: a video diffusion transformer is adapted, at considerable co
arXiv:2608.15360v1 Announce Type: cross Abstract: While Parameter-Efficient Fine-Tuning (PEFT) has substantially reduced the hardware cost of adapting Large Language Models (LLMs) by decreasing the nu
arXiv:2608.15295v1 Announce Type: new Abstract: Foundation segmentation models excel at generating high-quality, class-agnostic masks, but they struggle to associate these proposals with specific targ
arXiv:2608.14641v1 Announce Type: new Abstract: Agentic systems increasingly delegate model selection to a router, yet open-source routers are usually evaluated with different tasks, candidate pools,
arXiv:2608.16345v1 Announce Type: new Abstract: Pre-trained models (PTMs) provide a strong foundation for continual learning by offering stable representations that facilitate lightweight adaptation t
arXiv:2608.15736v1 Announce Type: new Abstract: Foundation models (FMs) increasingly support multimodal and geospatial reasoning, yet it remains unclear whether cartographic principles designed for hu
arXiv:2608.16391v1 Announce Type: cross Abstract: As large language models become increasingly widespread, third-party providers that deploy open-weight models have become an important part of the eco
arXiv:2505.19196v2 Announce Type: replace Abstract: Recent advances in text-to-image (T2I) diffusion model fine-tuning leverage reinforcement learning (RL) to align generated images with learnable rew
arXiv:2507.06526v4 Announce Type: replace Abstract: Text-to-image diffusion models remain susceptible to generating undesirable or harmful content. Although concept unlearning mitigates this risk, exi
arXiv:2608.01856v2 Announce Type: replace Abstract: Bi-temporal remote-sensing disaster change captioning often needs to identify sparse and spatially localized changes across large pre- and post-even
arXiv:2608.14047v1 Announce Type: cross Abstract: This paper integrates end-to-end Visual-Language-Action (VLA) models with agentic tool-use to propose Agentic Robot with Tool-use (ART). ART is a tool
arXiv:2502.07580v4 Announce Type: replace Abstract: We present a novel view of diffusion-like generative modeling from the perspective of iterative Gaussian posterior inference. By treating the genera
Here are 22 more gems according to the AI among my bookmarks 1. Researchers compressed 4.1 million recipes into a two-megabyte model of human cooking. The model spans seven languages and represents 1,
arXiv:2608.14361v1 Announce Type: new Abstract: Intrinsic dimensionality (ID) is widely used to probe the representational complexity of language models, but it remains unclear whether ID differences
arXiv:2608.14530v1 Announce Type: cross Abstract: Interactive game world models typically autoregress visual observations directly in pixel or latent space, forcing structured properties such as pose,
arXiv:2606.12838v2 Announce Type: replace-cross Abstract: Predicting single-cell transcriptional responses to genetic, chemical and cytokine perturbations is a fundamental challenge in computational b
Simon Willison / Simon Willison's Weblog: Qwen 3.8 27B shows a 17GB open-weight general purpose model can have long context, effective tool calling, strong vision ability, and competent code generatio
arXiv:2608.13492v1 Announce Type: new Abstract: This report presents an improved version of AlayaWorld. While the backbone architecture, chunk-wise autoregressive generation scheme, and training data
Apple has reportedly trained a custom AI model for the China market alongside domestic tech giant Alibaba, a rare cross-border partnership that cuts across growing tensions between Beijing and Washing
arXiv:2608.12719v1 Announce Type: cross Abstract: Routing each query to a cost-effective large language model (LLM) is critical for balancing quality and cost, yet most routers rely on a centralized t
arXiv:2608.13515v1 Announce Type: new Abstract: Measuring training data influence consistently across language model pretraining is challenging. It is difficult to select downstream tasks or validatio
arXiv:2608.13335v1 Announce Type: new Abstract: Neural networks trained by gradient descent on a smooth cost function can nevertheless learn in steps: the cost holds on long plateaus and then drops ab
arXiv:2506.15577v2 Announce Type: replace Abstract: Estimating above-ground biomass (AGB) from terrestrial laser scanning (TLS) via quantitative structural models (QSMs) is highly accurate under leaf-
arXiv:2608.12811v1 Announce Type: new Abstract: The rapid advancement of AI-generated content has made the reliable detection of generated images an increasingly critical challenge. Existing detection
arXiv:2603.11211v3 Announce Type: replace-cross Abstract: Incremental Learning (IL) aims to learn new tasks while preserving previously acquired knowledge. Integrating the zero-shot learning capabilit
arXiv:2408.06849v3 Announce Type: replace Abstract: The large language model (LLM) has achieved significant success across various domains. However, the inherent complexity of causal problems and caus
arXiv:2608.11942v1 Announce Type: new Abstract: Quantitative MRI (qMRI) provides standardised tissue parameter maps, but the reliability of deep learning-based qMRI mapping methods is often not explic
Powered by @Cerebras, Ultrafast generates up to 750 tokens per second, bringing our most intelligent model to products and workflows where every second counts. Ultrafast is designed for businesses whe
arXiv:2608.12276v1 Announce Type: new Abstract: High-fidelity image generation faces a trade-off between speed and quality. Diffusion models produce strong visuals but require costly iterative samplin
arXiv:2608.09959v1 Announce Type: cross Abstract: AI weather models are in the process of revolutionising weather forecasting. While these models have been shown to achieve superior performance to phy
arXiv:2608.10500v1 Announce Type: new Abstract: Creating photorealistic and temporally coherent animatable human avatars from RGB videos remains challenging. Current methods struggle to capture realis
Enterprise content is no longer just something people read. AI apps and agents are only as useful as the information they can understand, yet much of the world’s enterprise knowledge is locked in docu
Mike Wheatley / SiliconANGLE: Google DeepMind launches SL2T, a multilingual sign-language-to-text model debuting on the Pixel 11 in Gboard and Live Transcribe, first with ASL and English — Google Deep
arXiv:2608.10634v1 Announce Type: new Abstract: Model-based reinforcement learning (MBRL), which learns environment dynamics to generate synthetic experience, is a promising approach to sample-efficie
arXiv:2608.10172v1 Announce Type: new Abstract: Mechanistic interpretability explains models by identifying circuits inside them, but has no way to tell whether a circuit is a property of the model or
arXiv:2608.10517v1 Announce Type: cross Abstract: Accurate physical-layer modeling is increasingly essential for reliable ultra-wideband operation and capacity optimization, especially under the inten
arXiv:2608.10738v1 Announce Type: new Abstract: We study the approximation of dynamical systems by semi-autonomous neural ordinary differential equations (SA-NODEs) over long time horizons. For a sing
arXiv:2608.10131v1 Announce Type: new Abstract: Vision foundation models are increasingly used as reusable encoders in medical image computing, yet their high-dimensional spatial embeddings are diffic
arXiv:2608.10198v1 Announce Type: new Abstract: Latent-space communication allows heterogeneous vision-language model agents to exchange continuous representations without serializing visual and reaso
arXiv:2405.03728v3 Announce Type: replace-cross Abstract: Zero-shot optimization involves optimizing a target task that was not seen during training, aiming to provide the optimal solution without or
The model punches above its weight, outperforming Gemma 4 E2B and Ministral 3 3B across a broad range of visual understanding benchmarks and delivers particularly strong results on document understand