Search: “models”

arXiv:2605.26601v1 Announce Type: new Abstract: Vision-language models have progressed rapidly, but Tibetan remains a severely underserved low-resource language due to the lack of reproducible trainin

arXiv:2602.16449v2 Announce Type: replace-cross Abstract: Generative model evaluation commonly relies on high-dimensional embedding spaces to compute distances between samples. We show that dataset re

KREA 2 Image, KREA's foundational image generation model trained from scratch with adjustable creativity and style parameters, has been integrated as a partner node within ComfyUI. This integration al

arXiv:2605.26256v1 Announce Type: new Abstract: Multimodal large language model (MLLM)-based embodied agents have shown strong potential for solving complex tasks in physical environments. However, pe

arXiv:2605.25446v1 Announce Type: new Abstract: Electrocardiography (ECG) is central to cardiovascular care, but conventional AI models are often restricted to common arrhythmias and may generalize po

arXiv:2605.26045v1 Announce Type: cross Abstract: Activation oracles aim to make the activations of other models legible to humans and yield promising results compared to white-box interpretability te

arXiv:2604.04453v2 Announce Type: replace-cross Abstract: Granular flows govern many natural and industrial processes, yet their interior kinematics and mechanics remain largely unobservable, as exper

Human in the loop 🤖 Made in @ComfyUI with a laundry list of tools: @ltx_model 2.3 + @thesystms FLW LoRA, @Alibaba_Wan 2.2 I2V + T2V, Florence2, @Meta Sapiens2, @OpenAI GPT Image 2.0, @suno , @AdobeAE

Launching our new paper on arXiv: we trained the largest multilingual food model ever built. 4.1M recipes. 7 languages. 1,790 ingredients. 300 dimensions. All of human cooking compressed into 2 megaby

A comparative test of three AI image generation models—SenseNova U1, GPT Image 2, and Nano Banana 2—evaluating their performance on infographic generation tasks. GPT Image 2 proved more reliable for e

arXiv:2602.10635v2 Announce Type: replace Abstract: Socially intelligent AI systems must entail reasoning across diverse human behavioral tasks, and generalization to new contexts. However, AI has yet

The goal of training a machine learning model is loss minimization. That was just being applied to algorithms, and now it's being applied to whole enterprises. Loss minimization is one thing that the

arXiv:2605.24938v1 Announce Type: cross Abstract: Multimodal retrieval relies heavily on single-vector retrievers, which compress rich, sequential token sequences into one single global representation

arXiv:2510.04567v2 Announce Type: replace-cross Abstract: Graph Neural Networks (GNNs) are powerful tools for processing relational data but often struggle to generalize to unseen graphs, giving rise

Grok foundation model V9-Medium (1.5T) has finished training. Evals look good. A lot of Cursor data was added in supplementary training and there is more to come. Fine-tuning is underway and reinforce

arXiv:2605.23603v1 Announce Type: cross Abstract: We introduce the Preisach Attention Layer (PAL), a novel sequence modelling architecture grounded in the classical Preisach hysteresis operator from m

The Grok Build team is one of the most productive teams I have worked with. I need something to adopt my diverse workflow from model training to validating the Cybercab manufacturing process. Their da

Gary Marcus critiques OpenAI's business model sustainability, suggesting it lacks transparency or clear long-term viability beyond investor confidence. The post implies skepticism about OpenAI's path

And it is the model that makes it so it is the labs, as opposed to every other software vendor, can ultimately be the sole provider of products. Their post-training and their harnesses and their contr

arXiv:2605.22671v1 Announce Type: new Abstract: Vision-Language-Action (VLA) models often suffer from performance degradation under distribution shifts, as they struggle to learn generalized behavior

i suspect that this is a wild underestimate, both ignoring the costs in developing the model and ignoring the fact that many questions may well have been posed that didn’t succeed. If this is true, us

arXiv:2605.20274v1 Announce Type: cross Abstract: Hexahedral meshes are widely used in simulation pipelines, yet automatic generation remains challenging for complex CAD geometries. Polycube-based hex

Ashley Stewart / Business Insider: Sources and documents detail Satya Nadella's effort to revamp Microsoft's senior leadership, creating a startup-style operating model to compete in the AI race — CEO

Zuby experienced Tesla's Full Self-Driving (FSD) for the first time in a Sapphire Model Y running software version 14.3.2 in Austin, generating a notably positive reaction. The anecdote was shared by

Sense1 is announced as the first model capable of mapping olfactory activation patterns across multiple dimensions, establishing a standardized system for smell comparable to how RGB defines color and

arXiv:2605.20756v1 Announce Type: new Abstract: Preconditioned optimizers are central to language model training, but their stochastic update rules are usually treated as direct approximations to popu

For anyone who isn't sure, this is how you release a model and talk about the performance. Not 3-5 cherry-picked benchmarks. Performance：Qwen3.7-Max performs strongly across benchmarks in coding agent

arXiv:2605.20246v1 Announce Type: new Abstract: Recently, vision-language model (VLM) agents have shown promising progress in open-world tasks, where successful task completion often requires multiple

arXiv:2502.17773v5 Announce Type: replace-cross Abstract: Large language models (LLMs) are increasingly used to simulate survey responses, but synthetic data can be misaligned with the human populatio

arXiv:2605.21081v1 Announce Type: cross Abstract: This study aims to enhance the quality of music generation using Transformers by incorporating meta-information. While Transformer-based approaches ar

nor do we know how the (new) model works nor how it does on anything else nor how it was trained. scientists wait for facts; cheerleaders (over and over) rush to judgments that have often been wrong.

This article presents a maturity model for ML operations that leverages agent skills to improve on-call practices and incident response workflows. It likely discusses how organizations can evolve thei

arXiv:2605.20308v1 Announce Type: new Abstract: Gradient-based attacks are important methods for evaluating model robustness. However, since the proposal of APGD, it has been difficult for such method

while everyone seems to be focused on text, vision, and audio, i'm excited to be backing a company building a foundational model for smell 👃 that's right, they've: - mapped how olfactory receptors rea

arXiv:2605.20275v1 Announce Type: new Abstract: Existing deep learning approaches for wearable fall detection systems rely on self-attention mechanisms that impose quadratic computational overhead, di

arXiv:2501.09203v2 Announce Type: replace Abstract: Visual-Spatial Systems has become increasingly essential in concrete crack inspection. However, existing methods often lacks adaptability to diverse

a general-purpose model solved a major open problem in mathematics. we'll be saying this a lot over the coming years, but this is a kinda big milestone. i'm very excited for AI to greatly extend our u

arXiv:2510.03589v2 Announce Type: replace Abstract: Spatio-temporal sensor data in real-world systems is often sparse, noisy, and irregular, making latent field reconstruction fundamentally underconst

arXiv:2605.19600v1 Announce Type: new Abstract: In the field of Vision-Language Navigation (VLN), aerial datasets remain limited in their ability to combine scale, diversity, and realism, often relyin

Love this concept. Always been a proponent of event-driven architectures, and the actor model. Neat to see how it’s applied to the agent runtime here. i'm excited to open source Active Graph: an event

arXiv:2605.18893v1 Announce Type: new Abstract: Graph Neural Networks (GNNs) are powerful tools for learning from graph-structured data, but their scalability is increasingly strained by the size of r

arXiv:2605.19218v1 Announce Type: cross Abstract: Vision-Language Models suffer severe KV cache pressure at inference, as a single image often encodes into thousands of tokens. Most existing methods e

We added 600+ new voices on Together AI! Introducing MiniMax Speech 2.8 Turbo on Together AI, an enterprise TTS model for expressive real-time voice agents. AI natives can now deploy @MiniMax_AI Speec

arXiv:2605.16768v1 Announce Type: new Abstract: Semantic segmentation of multi-source remote sensing images is a fundamental task for Earth observation applications. Existing methods often struggle wi

arXiv:2605.16824v1 Announce Type: cross Abstract: Large language models (LLMs) generate not only reasoning text, but also token-level confidence trajectories that record how uncertainty evolves during

arXiv:2605.16575v1 Announce Type: new Abstract: Negotiation requires more than inferring what the other side wants: it requires using that information to make advantageous offers and counteroffers ove