model releases

LAYUP: Asynchronous decentralized gradient descent with LAYer-wise UPdates

arXiv:2410.05985v4 Announce Type: replace Abstract: The increasing size of deep learning models has made distributed training across multiple devices essential. Synchronous, centralized methods incur

Model Releases

Learning a Normal World Model for Few-Shot Boundary-Calibrated Abnormality Detection

DGX agent

arXiv:2606.22261v1 Announce Type: new Abstract: Abnormality detection in complex systems faces two practical barriers: abnormal labels are scarce, and binary labels do not quantify how far an event ha

model-releasesarxiv-cs-lg

23 Jun 2026

Learning-Augmented Algorithms for Online Vertex Cover

arXiv:2606.22831v1 Announce Type: cross Abstract: This paper studies learning-augmented online weighted vertex cover with advice and a parameter lambda in (0,1). We consider two graph cases: bipartite

Learning Bug Context for PyTorch-to-JAX Translation with LLMs

arXiv:2510.09898v2 Announce Type: replace Abstract: Large language models (LLMs) have shown strong performance on code translation between widely used programming languages. However, translation becom

Learning by Shifting: Temporal View Construction for Time Series Contrastive Learning

arXiv:2606.21957v1 Announce Type: new Abstract: Supervised learning demands large quantities of labeled data, a bottleneck that is expensive and reliant on domain-specific expertise. Self-supervised l

Leaving aside the “Vandalism” stuff for a brief moment: President Trump’s claims today that the reflecting pool “never opened” or was “rarel…

model-releasesanthropic--x

Leaving aside the “Vandalism” stuff for a brief moment: President Trump’s claims today that the reflecting pool “never opened” or was “rarely open” after the Obama repair project are just not true. It

Leveraging LaBSE with Progressive Curriculum Learning for Multicultural Polarization

arXiv:2606.21718v1 Announce Type: cross Abstract: Detecting online polarization remains a critical challenge, particularly in multilingual and multicultural contexts where intergroup hostility is prev

LIBERO-Safety: A Comprehensive Benchmark for Physical and Semantic Safety in Vision-Language-Action Models

model-releasesarxiv-cs-ro

arXiv:2606.23686v1 Announce Type: new Abstract: Despite the impressive manipulation capabilities of Vision-Language-Action (VLA) models, their operational safety under strict constraints remains large

LLM-Based Generalizable Hierarchical Task Planning and Execution for Heterogeneous Robot Teams with Event-Driven Replanning

model-releasesarxiv-cs-ro

arXiv:2511.22354v2 Announce Type: replace Abstract: This paper introduces CoMuRoS (Collaborative Multi-Robot System), a generalizable hierarchical architecture for heterogeneous robot teams that unifi

Load Testing for Machine Learning Model Serving Systems at Scale

arXiv:2606.22013v1 Announce Type: new Abstract: Machine learning (ML) model serving has become a dominant consumer of GPU infrastructure, yet capacity planning in these systems remains largely ad hoc.

Localizing and Editing Knowledge in Large Audio-Language Models

arXiv:2603.14343v2 Announce Type: replace Abstract: Large Audio-Language Models (LALMs) have shown strong performance in speech understanding, making speech a natural interface for accessing factual i

LoCC: Detection and Localization of Lip-Syncing Deepfakes via Counterfactual Frame Consistency

arXiv:2606.22772v1 Announce Type: new Abstract: Lip-syncing deepfakes are among the most challenging forms of manipulated media because their artifacts are localized almost exclusively to the mouth re

LOGOS: LiDAR-Only Gaussian Elevation Splatting for Unified Tiny Obstacle Segmentation

arXiv:2606.21527v1 Announce Type: cross Abstract: Robust obstacle segmentation is essential for the safety of intelligent robots, where LiDAR-based perception systems play a fundamental role in the ro

(Look mom - I made it!) Learn more about configuring agent identity and some of the key decisions we made for Claude Tag- https://claude.com…

This post likely discusses configuration options for setting up Claude agent identity and explains the design decisions behind Claude Tag, Anthropic's tool for customizing Claude's behavior and person

model-releasesthariq--x

Low-variance estimators overcome the phase-gradient bottleneck in complex-valued neural quantum states

arXiv:2606.13912v2 Announce Type: replace-cross Abstract: Complex neural quantum states are difficult to optimize when their wavefunction phase carries gauge, chiral, fermionic, or topological structu

LUMINA-26: Low-Light Understanding for Modeling and Interpreting Night-time Actions

arXiv:2606.23118v1 Announce Type: new Abstract: Low-light human action recognition remains a challenging problem due to poor illumination, amplified noise, motion ambiguity, and diverse real-world sce

LUQ: Layerwise Ultra-Low Bit Quantization for Multimodal Large Language Models

arXiv:2509.23729v3 Announce Type: replace Abstract: Large Language Models (LLMs) with multimodal capabilities have revolutionized vision-language tasks, but their deployment often requires huge memory

MammoExpert: Benchmarking Chain-of-Thought Reasoning in Mammography Diagnosis

arXiv:2606.21119v1 Announce Type: new Abstract: Mammography is an essential tool for breast cancer detection, with millions of examinations conducted annually. However, publicly available high-quality

MapReason-OSM: Can Vision-Language Models Make Graph-Verifiable Mobility Decisions from Street Maps ?

arXiv:2606.22597v1 Announce Type: new Abstract: Vision-language models (VLMs) are increasingly used to read maps for logistics, delivery, and accessible navigation, where the output is an actionable d

Mat-Pref: Verifiable-Reward Training Improves Compositional Reasoning in Inorganic Materials

arXiv:2606.21830v1 Announce Type: new Abstract: Reinforcement learning from verifiable rewards (RLVR) has driven rapid progress in mathematical and code reasoning, but when extended to science, existi

Measuring Intent Comprehension in LLMs

arXiv:2506.16584v3 Announce Type: replace-cross Abstract: People judge interactions with large language models (LLMs) as successful when outputs match what they want, not what they type. Yet LLMs are

MEDLAYXPLAIN: Benchmarking the Expert-Lay Gap in Medical Vision-Language Models

arXiv:2606.21194v1 Announce Type: new Abstract: Medical Vision-Language Models (Med-VLMs) achieve strong expert-level performance, yet their ability to generate patient-accessible descriptions remains

MedTS-TTT: Test-Time Training for Medical Time Series Classification

arXiv:2606.21329v1 Announce Type: new Abstract: Medical time series (MedTS) signals such as electroencephalography (EEG) and electrocardiography (ECG) support many clinical applications. However, subs

Mesh2GS: White-Box 3DGS Construction via Plenoptic Sampling

arXiv:2606.21898v1 Announce Type: cross Abstract: 3D Gaussian Splatting (3DGS) has emerged as a promising method for high-quality, real-time 3D reconstruction. To associate 3DGS with mesh representati

Meta launches cheaper smart glasses without Ray-Ban

model-releasesthe-verge-ai

For the past three years, 'Meta' and 'Ray-Ban' have been synonymous in the smart glasses space. Not anymore. Yesterday, I slipped on several pairs of Meta Glasses - no Ray-Bans - in three different st

Mirage: a Clean-Label Backdoor against LiDAR 3D Object Detection

arXiv:2606.20752v1 Announce Type: new Abstract: Deep neural network-based LiDAR 3D object detection serves as a critical perception component in safety-critical autonomous systems. However, recent stu

Mistral debuts OCR 4, a model featuring structured document extraction with bounding boxes, block classification, and inline confidence scores, in 170 languages (Mistral AI Blog)

Mistral AI Blog: Mistral debuts OCR 4, a model featuring structured document extraction with bounding boxes, block classification, and inline confidence scores, in 170 languages — Today, we're releasi

model-releasestechmeme

Mitigating Measurement-Induced Training Instability in Hybrid Quantum Neural Networks for Protein Classification

arXiv:2606.22551v1 Announce Type: cross Abstract: Hybrid Quantum Neural Network (QNN) classifiers produce logits as expectation values of quantum measurement operators. For standard Pauli measurements

MMGist: A Comprehensive Multimodal Benchmark for 2027

arXiv:2606.22437v1 Announce Type: new Abstract: We conduct a systematic study of 18 widely used vision-language benchmarks and identify three major issues: 1) many items do not rely on visual cues and

MMOU: A Massive Multi-Task Omni Understanding and Reasoning Benchmark for Long and Complex Real-World Videos

arXiv:2603.14145v2 Announce Type: replace-cross Abstract: Multimodal Large Language Models (MLLMs) have shown strong performance in visual and audio understanding when evaluated in isolation. However,

Model Merging in the Essential Subspace

arXiv:2602.20208v2 Announce Type: replace Abstract: Model merging aims to integrate multiple task-specific fine-tuned models derived from a shared pre-trained checkpoint into a single multi-task model

MoECodec: Image Compression for joint human and machine perception via Mixture-of-Experts

arXiv:2606.21033v1 Announce Type: cross Abstract: Image compression for machines calls for a unified codec that serves multiple downstream vision tasks. Existing approaches either adopt task-specific

MOOZY: A Patient-First Foundation Model for Computational Pathology

arXiv:2603.27048v3 Announce Type: replace Abstract: Computational pathology needs whole-slide image (WSI) foundation models that transfer across diverse clinical tasks, yet current approaches remain l

MORL-A2C: Multi-Objective Reinforcement Learning Reranker for Optimizing Healthiness in MOPI-HFRS

arXiv:2606.23603v1 Announce Type: new Abstract: Unhealthy dietary behavior continues to be a persistent public health issue in the United States, exacerbated by recommendation systems that prioritize

Morphology-Aware Multimodal Representation Learning for Insect Phylogenetic Reconstruction

arXiv:2606.22077v1 Announce Type: new Abstract: Morphological traits provide important evidence for phylogenetic reconstruction and evolutionary relationship analysis. Recent image-based approaches ha

MotionHalluc: Diagnosing Kinematic Hallucinations in Fine-Grained Motion Reasoning

arXiv:2606.23061v1 Announce Type: new Abstract: Motion instruction generation in cross-video comparison aims to produce corrective feedback that describes the differences between a query and a referen

Multigrid Training for Molecular Generation using Graph Neural Networks

arXiv:2606.22377v1 Announce Type: new Abstract: Deep learning has demonstrated significant success for modeling biochemical molecular systems, where inputs are commonly represented as graphs or 3D gri

Muown Implicitly Performs Angular Step-size Decay

arXiv:2606.23637v1 Announce Type: new Abstract: Matrix-aware optimizers such as Muon and Muown have recently shown strong empirical performance for pre-training Transformers. In particular, Muown sepa

Neural Parameter Calibration for Finite-State Mean Field Games

arXiv:2606.23155v1 Announce Type: cross Abstract: Mean field games efficiently approximate a very large population of strategic agents. While these games can aid the understanding of complex systems,

Next-Gen CAPTCHAs: Leveraging the Cognitive Gap for Scalable and Diverse GUI-Agent Defense

arXiv:2602.09012v2 Announce Type: replace Abstract: The rapid evolution of GUI-enabled agents has rendered traditional CAPTCHAs obsolete. While previous benchmarks like OpenCaptchaWorld established a

NNiT: Width-Agnostic Neural Network Generation with Structurally Aligned Weight Spaces

arXiv:2603.00180v2 Announce Type: replace Abstract: Generative modeling of neural network parameters is often tied to architectures because standard parameter representations rely on known weight-matr

Non-asymptotic estimates of the minimal risk in statistical learning

arXiv:2606.23295v1 Announce Type: new Abstract: In this paper we prove some concentration inequalities for two types of error probabilities in the Empirical Risk Principle (ERP) in statistical learnin

Nous: A Predictive World Model for Long-Term Agent Memory

arXiv:2606.22030v1 Announce Type: cross Abstract: We present Nous, a novel agent memory architecture grounded in the principle that knowledge is prediction, not storage. Rather than persisting facts a

OGD4All: A Framework for Accessible Interaction with Geospatial Open Government Data Based on Large Language Models

arXiv:2602.00012v3 Announce Type: replace Abstract: We present OGD4All, a transparent, auditable, and reproducible framework based on Large Language Models (LLMs) to enhance citizens' interaction with

Open Annotations and Synthetic Data for Field Localisation in Indian Bank Cheques

arXiv:2606.20682v1 Announce Type: new Abstract: Automated cheque processing requires localising key fields (date, legal amount, IFSC code, account number, signature, and payee name) before any recogni

Open models, global networks: How AT&T and GSMA are accelerating telecom innovation with Gemma

model-releasesgoogle-cloud-ai

Telecommunications is an incredibly complex, highly specialized domain. Modern mobile networks are inherently multi-vendor, featuring diverse and often proprietary data structures. While AI has made m

Open Problem: Is AdamW Effective Under Heavy-Tailed Noise?

arXiv:2606.23676v1 Announce Type: new Abstract: AdamW is the de facto optimizer for training large language models (LLMs), yet the theory behind it still lives mostly in finite-variance regimes. This

OpenAI DevDay 2026 applications are now open! Our biggest developer event gets even bigger. 📍 San Francisco 📅 September 29 Apply by July 1…

OpenAI DevDay 2026, the company's major developer conference, will take place in San Francisco on September 29, 2026, with applications opening for attendees. The application deadline is July 1, 2026.

model-releasesopenai--x