Search: “models”

LPM 1.0: Video-based Character Performance Model

arXiv:2604.07823v1 Announce Type: new Abstract: Performance, the externalization of intent, emotion, and personality through visual, vocal, and temporal behavior, is what makes a character alive. Lear

Non-identifiability of Explanations from Model Behavior in Deep Networks of Image Authenticity Judgments

DGX agent

arXiv:2604.07254v1 Announce Type: cross Abstract: Deep neural networks can predict human judgments, but this does not imply that they rely on human-like information or reveal the cues underlying those

researcharxiv-cs-lg

10 Apr 2026

Operator Learning for Surrogate Modeling of Wave-Induced Forces from Sea Surface Waves

arXiv:2604.06433v1 Announce Type: cross Abstract: Wave setup plays a significant role in transferring wave-induced energy to currents and causing an increase in water elevation. This excess momentum f

researcharxiv-cs-lg

Applications

Phantom: Physics-Infused Video Generation via Joint Modeling of Visual and Latent Physical Dynamics

arXiv:2604.08503v1 Announce Type: new Abstract: Recent advances in generative video modeling, driven by large-scale datasets and powerful architectures, have yielded remarkable visual realism. However

applicationsarxiv-cs-cv

PlaneCycle: Training-Free 2D-to-3D Lifting of Foundation Models Without Adapters

arXiv:2603.04165v3 Announce Type: replace-cross Abstract: Large-scale 2D foundation models exhibit strong transferable representations, yet extending them to 3D volumetric data typically requires retr

Plug-and-Play Logit Fusion for Heterogeneous Pathology Foundation Models

arXiv:2604.07779v1 Announce Type: new Abstract: Pathology foundation models (FMs) have become central to computational histopathology, offering strong transfer performance across a wide range of diagn

safetyarxiv-cs-cv

Prompt reinforcing for long-term planning of large language models

model-releasesarxiv-cs-cl

arXiv:2510.05921v2 Announce Type: replace Abstract: Large language models (LLMs) have achieved remarkable success in a wide range of natural language processing tasks and can be adapted through prompt

Robust support vector model based on bounded asymmetric elastic net loss for binary classification

model-releasesarxiv-cs-lg

arXiv:2603.06257v2 Announce Type: replace-cross Abstract: In this paper, we propose a novel bounded asymmetric elastic net (L_{baen}) loss function and combine it with the support vector machine (SV

Search-R3: Unifying Reasoning and Embedding in Large Language Models

arXiv:2510.07048v2 Announce Type: replace Abstract: Despite their remarkable natural language understanding capabilities, Large Language Models (LLMs) have been underutilized for retrieval tasks. We p

tutorialsarxiv-cs-cl

Tesla is down to the last few hundred Model S & X cars in inventory. Poignant end of an era.

Tesla is down to the last few hundred Model S & X cars in inventory. Poignant end of an era. Traded in my 2020 Model S for a brand new plaid X before they discontinue it. Car is amazing, but the FSD h

industryelon-musk--x

Local Ai

VoxCPM TTS model + LoRa training abilities right in Comfy

local-air-stablediffusion

ComfyUI-VoxCPM is a custom node that integrates VoxCPM — a novel tokenizer-free Text-to-Speech system that models speech in a continuous space — directly into ComfyUI's visual workflow environmen...

Anthropic built a model too risky to release

Anthropic's new frontier model, Claude Mythos, is the first model the company has publicly deemed too high-risk for general release , due to its advanced cybersecurity capabilities — including the ...

industryben-s-bites

FlowInOne - A new Multimodal image model . Released on Huggingface

model-releasesr-stablediffusion

FlowInOne is a vision-centric multimodal image generation framework that reformulates multimodal generation as a purely visual flow, converting all inputs into visual prompts and enabling a clean i...

Meta's new AI can predict your brain better than a brain scan. TRIBE v2 is a foundation model trained on 1,000+ hours of brain imaging data …

Meta's new AI can predict your brain better than a brain scan. TRIBE v2 is a foundation model trained on 1,000+ hours of brain imaging data from 720 people. You feed it a video, sound clip, or text, a

industryrowan-cheung--x

Understanding Amazon Bedrock model lifecycle

This post shows you how to manage FM transitions in Amazon Bedrock, so you can make sure your AI applications remain operational as models evolve. We discuss the three lifecycle states, how to plan mi

tutorialsaws-ml-blog

[AINews] Anthropic @ $30B ARR, Project GlassWing and Claude Mythos Preview — first model too dangerous to release since GPT-2

model-releaseslatent-space

Anthropic announced it has grown its ARR from $19B to $30B in just one month, coinciding with the formal unveiling of Claude Mythos Preview — described in leaked company documents as 'by far the m...

8 Apr 2026

AlayaWorld: Interactive Long-Horizon World Modeling - Full Technical Report (v1.1)

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 trained its own AI model for China with help from Alibaba

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

industrythe-verge-ai

Can Generalist Vision Language Models (VLMs) Rival Specialist Medical VLMs? Benchmarking and Strategic Insights

arXiv:2506.17337v5 Announce Type: replace-cross Abstract: Vision Language Models (VLMs) have shown promise in automating image diagnosis and interpretation in clinical settings. However, developing sp

Diagnosing JEPA World Models with Action-Conditioned Predictive Consistency

arXiv:2608.12939v1 Announce Type: new Abstract: Joint-embedding predictive architectures (JEPAs) learn world models that predict in a compact latent space rather than in pixels, reducing the pressure

tutorialsarxiv-cs-lg

Applications

Error-Aware Reverse Auction Mechanism for Large Language Model Routing

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

applicationsarxiv-cs-ai

How Good are Foundation Models in Longitudinal MRI Disease Progression Reasoning?

arXiv:2608.13309v1 Announce Type: new Abstract: Magnetic Resonance Imaging (MRI) interpretation is fundamental to clinical decision-making, requiring radiologists to integrate multi-view anatomical pl

Measuring Task-Agnostic Training Data Influence Across Language Model Pretraining

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

researcharxiv-cs-cl

Neural Quadratic Forms: A Unified Minimal Model for Sudden Learning and Scaling Laws

model-releasesarxiv-cs-lg

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

neurosymbolic world models – exactly what I argued for in 2020 in the Next Decade in AI – for the win.

neurosymbolic world models – *exactly* what I argued for in 2020 in the Next Decade in AI – for the win. Jeremy's excellent work here is a great illustration of a very powerful type of approach: LLM-g

safetygary-marcus--x

Shortest-Path Decomposition for Foliage-Robust 3D Tree Modeling and Above-Ground Biomass Estimation from Point Clouds

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-

Local Ai

Structured Local Differential Modeling for AI-Generated Image Detection

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

local-aiarxiv-cs-cv

A Simple Efficiency Incremental Learning Framework via Vision-Language Model with Nonlinear Multi-Adapters

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

tutorialsarxiv-cs-ai

Accelerating Time Series Foundation Models with Speculative Decoding

arXiv:2511.18191v2 Announce Type: replace Abstract: Time series forecasting drives operational decisions under tight latency budgets, and autoregressive time series foundation models (TSFMs) increasin

researcharxiv-cs-lg

Better Slots, Better Worlds: Representation Quality & Robustness in Object-Centric World Models

arXiv:2608.12078v1 Announce Type: cross Abstract: Learning world models from offline trajectories enables agents to accomplish different tasks through planning. Object-centric (OC) representations, wh

safetyarxiv-cs-ai

Causal Agent based on Large Language Model

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

Conflict and Congruency Effects in Large Language Models: In-Weight and In-Context Competition in a Verbal Conflict Task

arXiv:2608.11510v1 Announce Type: cross Abstract: Congruency effects, observed in conflict tasks such as Stroop and flanker tasks, have been investigated for nearly a century in psychology and neurosc

Applications

Dynamics Models for Offline Hyperparameter Selection in Real-World RL

arXiv:2608.11349v1 Announce Type: cross Abstract: A key obstacle to deploying reinforcement learning in real-world systems is hyperparameter selection, particularly when simulators are unavailable and

applicationsarxiv-cs-ai

Evaluating and Calibrating Diffusion Model-derived Uncertainty for Quantitative MRI Mapping

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

ExRole: From Team Trajectories to Executable Roles in Multi-Agent Language Models

arXiv:2608.11949v1 Announce Type: new Abstract: Roles provide an interpretable interface for organizing language-model agents, yet most multi-agent systems treat them as hand-written prompt labels dis

Powered by @Cerebras, Ultrafast generates up to 750 tokens per second, bringing our most intelligent model to products and workflows where e…

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

model-releasesopenai--x

Program Semantic Inequivalence Game with Large Language Models

arXiv:2505.03818v3 Announce Type: replace-cross Abstract: Large Language Models (LLMs) can achieve strong performance on everyday coding tasks, but they can fail on complex tasks that require non-triv

Thanks. The fact that it works so well for ARC is also a clue to the extent of generalization in these models. It was not at all obvious tha…

researchfrancois-chollet--x

Thanks. The fact that it works so well for ARC is also a clue to the extent of generalization in these models. It was not at all obvious that it would work originally because the model is never traine

Hardware

The Coachella of robotics, world models, and physical AI is Runway’s SF Summit, coming to the Bay Area on September 30. Speaker lineup: @Qua…

hardwarecristobal-valenzuela--x

The Coachella of robotics, world models, and physical AI is Runway’s SF Summit, coming to the Bay Area on September 30. Speaker lineup: @QuanVng from @physical_int, @liu_mingyu from @nvidia, @robertni

Local Ai

Understanding Why Foundation Models Work for Diffusion-Generated Image Detection

arXiv:2608.12155v1 Announce Type: new Abstract: Vision foundation models have recently emerged as powerful feature extractors for detecting AI-generated images, achieving strong generalization across

local-aiarxiv-cs-cv

XYZFlow:Scaling Multi dimensional Shortcut Flows for Efficient Generative Modeling

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

researcharxiv-cs-cv

AIFS-TC: A simple correction competitive with the operational frontier for tropical cyclone intensity forecasting

model-releasesarxiv-cs-lg

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

Can Computational Reducibility Lead to Transferable Models for Graph Combinatorial Optimization?

arXiv:2603.02462v2 Announce Type: replace-cross Abstract: A key challenge in developing unified neural solvers for combinatorial optimization (CO) is the efficient generalization of models from a give

DSAR: Dual-Stream Autoregressive Modeling of Temporal Cloth Dynamics for Photorealistic Animatable Avatars

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

tutorialsarxiv-cs-cv

From Sync APIs to support for the GPT-5 model series and agentic workflows: What’s new in Azure Content Understanding – August 2026

model-releasesmicrosoft-foundry

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

Frozen Brain-MRI Foundation Models Are Site Fingerprints

arXiv:2608.10295v1 Announce Type: cross Abstract: Frozen foundation-model (FM) embeddings are increasingly used as off-the-shelf brain-MRI representations, on the assumption that they capture anatomy.

Generation-Step-Aware Framework for Cross-Modal Representation and Control in Multilingual Speech-Text Models

arXiv:2601.17387v3 Announce Type: replace Abstract: Multilingual speech-text models rely on cross-modal language alignment to transfer knowledge between speech and text, but it remains unclear whether

safetyarxiv-cs-cl

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 (Mike Wheatley/SiliconANGLE)

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

model-releasestechmeme