model releases

Latent Chain-of-Thought World Modeling for End-to-End Driving

arXiv:2512.10226v2 Announce Type: replace Abstract: Recent Vision-Language-Action (VLA) models for autonomous driving explore inference-time reasoning as a way to improve driving performance and safet

Latent Planning Emerges with Scale

DGX agent

arXiv:2604.12493v1 Announce Type: cross Abstract: LLMs can perform seemingly planning-intensive tasks, like writing coherent stories or functioning code, without explicitly verbalizing a plan; however

model-releasesarxiv-cs-ai

15 Apr 2026

LaV-CoT: Language-Aware Visual CoT with Multi-Aspect Reward Optimization for Real-World Multilingual VQA

arXiv:2509.10026v4 Announce Type: replace Abstract: As large vision language models (VLMs) advance, their capabilities in multilingual visual question answering (mVQA) have significantly improved. Cha

League of LLMs: A Benchmark-Free Paradigm for Mutual Evaluation of Large Language Models

arXiv:2507.22359v4 Announce Type: replace Abstract: Although large language models (LLMs) have shown exceptional capabilities across a wide range of tasks, reliable evaluation remains a critical chall

Let's talk parsing tables. Two days ago we launched ParseBench,the first document OCR benchmark built for AI agents. This deep dive breaks d…

model-releasesjerry-liu--x

Let's talk parsing tables. Two days ago we launched ParseBench,the first document OCR benchmark built for AI agents. This deep dive breaks down TableRecordMatch (GTRM), our metric for evaluating compl

Leveraging Weighted Syntactic and Semantic Context Assessment Summary (wSSAS) Towards Text Categorization Using LLMs

arXiv:2604.12049v1 Announce Type: cross Abstract: The use of Large Language Models (LLMs) for reliable, enterprise-grade analytics such as text categorization is often hindered by the stochastic natur

Lit2Vec: A Reproducible Workflow for Building a Legally Screened Chemistry Corpus from S2ORC for Downstream Retrieval and Text Mining

arXiv:2604.12498v1 Announce Type: cross Abstract: We present Lit2Vec, a reproducible workflow for constructing and validating a chemistry corpus from the Semantic Scholar Open Research Corpus using co

LLM-Enhanced Log Anomaly Detection: A Comprehensive Benchmark of Large Language Models for Automated System Diagnostics

arXiv:2604.12218v1 Announce Type: new Abstract: System log anomaly detection is critical for maintaining the reliability of large-scale software systems, yet traditional methods struggle with the hete

LLM-Guided Prompt Evolution for Password Guessing

arXiv:2604.12601v1 Announce Type: cross Abstract: Passwords still remain a dominant authentication method, yet their security is routinely subverted by predictable user choices and large-scale credent

Long-Horizon Plan Execution in Large Tool Spaces through Entropy-Guided Branching

arXiv:2604.12126v1 Announce Type: new Abstract: Large Language Models (LLMs) have significantly advanced tool-augmented agents, enabling autonomous reasoning via API interactions. However, executing m

M3D-Stereo: A Multiple-Medium and Multiple-Degradation Dataset for Stereo Image Restoration

arXiv:2604.12917v1 Announce Type: new Abstract: Image restoration under adverse conditions, such as underwater, haze or fog, and low-light environments, remains a highly challenging problem due to com

MedConcept: Unsupervised Concept Discovery for Interpretability in Medical VLMs

arXiv:2604.11868v1 Announce Type: new Abstract: While medical Vision-Language models (VLMs) achieve strong performance on tasks such as tumor or organ segmentation and diagnosis prediction, their opaq

Mema: Memory-Augmented Adapter for Enhanced Vision-Language Understanding

arXiv:2603.00655v2 Announce Type: replace Abstract: Multimodal Large Language Models (MLLMs) have achieved remarkable performance by aligning pretrained visual representations with the linguistic know

Memory as Metabolism: A Design for Companion Knowledge Systems

arXiv:2604.12034v1 Announce Type: new Abstract: Retrieval-Augmented Generation remains the dominant pattern for giving LLMs persistent memory, but a visible cluster of personal wiki-style memory archi

Mining Large Language Models for Low-Resource Language Data: Comparing Elicitation Strategies for Hausa and Fongbe

arXiv:2604.12477v1 Announce Type: cross Abstract: Large language models (LLMs) are trained on data contributed by low-resource language communities, yet the linguistic knowledge encoded in these model

MISID: A Multimodal Multi-turn Dataset for Complex Intent Recognition in Strategic Deception Games

arXiv:2604.12700v1 Announce Type: new Abstract: Understanding human intent in complex multi-turn interactions remains a fundamental challenge in human-computer interaction and behavioral analysis. Whi

Mitigating Shortcut Learning via Feature Disentanglement in Medical Imaging: A Benchmark Study

arXiv:2602.18502v2 Announce Type: replace Abstract: Although deep learning models in medical imaging often achieve excellent classification performance, they can rely on shortcut learning, exploiting

Mixed-Density Diffuser: Efficient Planning with Non-Uniform Temporal Resolution

arXiv:2510.23026v5 Announce Type: replace Abstract: Recent studies demonstrate that diffusion planners benefit from sparse-step planning over single-step planning. Training models to skip steps in the

Mobile GUI Agents under Real-world Threats: Are We There Yet?

arXiv:2507.04227v2 Announce Type: replace-cross Abstract: Recent years have witnessed a rapid development of mobile GUI agents powered by large language models (LLMs), which can autonomously execute d

Modality-Agnostic Prompt Learning for Multi-Modal Camouflaged Object Detection

arXiv:2604.12380v1 Announce Type: new Abstract: Camouflaged Object Detection (COD) aims to segment objects that blend seamlessly into complex backgrounds, with growing interest in exploiting additiona

Modality-Native Routing in Agent-to-Agent Networks: A Multimodal A2A Protocol Extension

arXiv:2604.12213v1 Announce Type: new Abstract: Preserving multimodal signals across agent boundaries is necessary for accurate cross-modal reasoning, but it is not sufficient. We show that modality-n

Monte Carlo Stochastic Depth for Uncertainty Estimation in Deep Learning

arXiv:2604.12719v1 Announce Type: new Abstract: The deployment of deep neural networks in safety-critical systems necessitates reliable and efficient uncertainty quantification (UQ). A practical and w

MoshiRAG: Asynchronous Knowledge Retrieval for Full-Duplex Speech Language Models

arXiv:2604.12928v1 Announce Type: new Abstract: Speech-to-speech language models have recently emerged to enhance the naturalness of conversational AI. In particular, full-duplex models are distinguis

Multi-Head Residual-Gated DeepONet for Coherent Nonlinear Wave Dynamics

arXiv:2604.11972v1 Announce Type: new Abstract: Coherent nonlinear wave dynamics are often strongly shaped by a compact set of physically meaningful descriptors of the initial state. Traditional neura

Multi-region endpoints are available for Claude on Vertex AI

model-releasesgoogle-cloud-ai

Today, we’re announcing U.S. and EU multi-region endpoints for Claude on Vertex AI are available in public preview. By pooling capacity across multiple regions, these endpoints dynamically route reque

MVAdapt: Zero-Shot Multi-Vehicle Adaptation for End-to-End Autonomous Driving

arXiv:2604.11854v1 Announce Type: cross Abstract: End-to-End (E2E) autonomous driving models are usually trained and evaluated with a fixed ego-vehicle, even though their driving policy is implicitly

Narrative-Driven Paper-to-Slide Generation via ArcDeck

arXiv:2604.11969v1 Announce Type: new Abstract: We introduce ArcDeck, a multi-agent framework that formulates paper-to-slide generation as a structured narrative reconstruction task. Unlike existing m

Narrative over Numbers: The Identifiable Victim Effect and its Amplification Under Alignment and Reasoning in Large Language Models

arXiv:2604.12076v1 Announce Type: cross Abstract: The Identifiable Victim Effect (IVE) - the tendency to allocate greater resources to a specific, narratively described victim than to a statistically

NASA wasn’t “closed” before Trump. The US doesn’t pay NATO anywhere close to “trillions of dollars” or “hundreds of billions of dollars a ye…

model-releasesanthropic--x

NASA wasn’t “closed” before Trump. The US doesn’t pay NATO anywhere close to “trillions of dollars” or “hundreds of billions of dollars a year.” Trump hasn’t built anywhere close to “over 1,000 miles

Nemotron 3 Super: Open, Efficient Mixture-of-Experts Hybrid Mamba-Transformer Model for Agentic Reasoning

arXiv:2604.12374v1 Announce Type: cross Abstract: We describe the pre-training, post-training, and quantization of Nemotron 3 Super, a 120 billion (active 12 billion) parameter hybrid Mamba-Attention

NeuroPareto: Calibrated Acquisition for Costly Many-Goal Search in Vast Parameter Spaces

arXiv:2602.03901v4 Announce Type: replace Abstract: The pursuit of optimal trade-offs in high-dimensional search spaces under stringent computational constraints poses a fundamental challenge for cont

NTIRE 2026 The 3rd Restore Any Image Model (RAIM) Challenge: Professional Image Quality Assessment (Track 1)

arXiv:2604.12512v1 Announce Type: cross Abstract: In this paper, we present an overview of the NTIRE 2026 challenge on the 3rd Restore Any Image Model in the Wild, specifically focusing on Track 1: Pr

Nucleus-Image: Sparse MoE for Image Generation

arXiv:2604.12163v1 Announce Type: new Abstract: We present Nucleus-Image, a text-to-image generation model that establishes a new Pareto frontier in quality-versus-efficiency by matching or exceeding

OFA-Diffusion Compression: Compressing Diffusion Model in One-Shot Manner

arXiv:2604.12668v1 Announce Type: new Abstract: The Diffusion Probabilistic Model (DPM) achieves remarkable performance in image generation, while its increasing parameter size and computational overh

ollama launch claude --model glm-5.1:cloud (We are rushing to get more capacity 🙏🙏🙏)

ollama launch claude --model glm-5.1:cloud (We are rushing to get more capacity 🙏🙏🙏) Uber's CTO told @LauraBratton5 that AI coding tools—particularly Anthropic’s Claude Code—has already maxed out its

model-releasesollama--x

Olmo 3

arXiv:2512.13961v2 Announce Type: replace Abstract: We introduce Olmo 3, a family of state-of-the-art, fully-open language models at the 7B and 32B parameter scales. Olmo 3 model construction targets

OmniHands: Towards Robust 4D Hand Mesh Recovery via A Versatile Transformer

arXiv:2405.20330v4 Announce Type: replace-cross Abstract: In this paper, we introduce OmniHands, a universal approach to recovering interactive hand meshes and their relative movement from monocular o

On Higher-Order Geometric Refinements of Classical Covariance Asymptotics: An Approach via Intrinsic and Extrinsic Information Geometry

arXiv:2604.12725v1 Announce Type: cross Abstract: Classical Fisher-information asymptotics describe the covariance of regular efficient estimators through the local quadratic approximation of the log-

On the continuum limit of t-SNE for data visualization

arXiv:2604.12041v1 Announce Type: cross Abstract: This work is concerned with the continuum limit of a graph-based data visualization technique called the t-Distributed Stochastic Neighbor Embedding (

Operationalising the Right to be Forgotten in LLMs: A Lightweight Sequential Unlearning Framework for Privacy-Aligned Deployment in Politically Sensitive Environments

arXiv:2604.12459v1 Announce Type: new Abstract: Large Language Models (LLMs) are increasingly deployed in politically sensitive environments, where memorisation of personal data or confidential conten

Orthogonal Subspace Projection for Continual Machine Unlearning via SVD-Based LoRA

arXiv:2604.12526v1 Announce Type: cross Abstract: Continual machine unlearning aims to remove the influence of data that should no longer be retained, while preserving the usefulness of the model on e

Parametric Interpolation of Dynamic Mode Decomposition for Predicting Nonlinear Systems

arXiv:2604.12103v1 Announce Type: cross Abstract: We present parameter-interpolated dynamic mode decomposition (piDMD), a parametric reduced-order modeling framework that embeds known parameter-affine

Parcae: Scaling Laws For Stable Looped Language Models

arXiv:2604.12946v1 Announce Type: new Abstract: Traditional fixed-depth architectures scale quality by increasing training FLOPs, typically through increased parameterization, at the expense of a high

ParetoBandit: Budget-Paced Adaptive Routing for Non-Stationary LLM Serving

arXiv:2604.00136v2 Announce Type: replace-cross Abstract: Multi-model LLM serving operates in a non-stationary, noisy environment: providers revise pricing, model quality can shift or regress without

Parsing complex tables in PDFs is extremely challenging. Existing metrics for measuring table accuracy, like TEDS (tree edit distance simila…

model-releasesjerry-liu--x

Parsing complex tables in PDFs is extremely challenging. Existing metrics for measuring table accuracy, like TEDS (tree edit distance similarity), overweight exact table structure and underweight sema

Physically Accurate Rigid-Body Dynamics in Particle-Based Simulation

model-releasesarxiv-cs-ro

arXiv:2603.14634v3 Announce Type: replace Abstract: Robotics demands simulation that can reason about the diversity of real-world physical interactions, from rigid to deformable objects and fluids. Cu

Policy-Invisible Violations in LLM-Based Agents

arXiv:2604.12177v1 Announce Type: new Abstract: LLM-based agents can execute actions that are syntactically valid, user-sanctioned, and semantically appropriate, yet still violate organizational polic

PolicyLLM: Towards Excellent Comprehension of Public Policy for Large Language Models

arXiv:2604.12995v1 Announce Type: new Abstract: Large Language Models (LLMs) are increasingly integrated into real-world decision-making, including in the domain of public policy. Yet, their ability t