Search: “models”

Can Large Language Models Reliably Correct Errors in Low-Resource ASR? A Contamination-Aware Case Study on West Frisian

model-releasesarxiv-cs-cl

arXiv:2605.19711v1 Announce Type: new Abstract: Automatic speech recognition (ASR) has improved substantially in recent years, yet performance remains limited for low-resource languages. Large languag

Safety

CoLD: Counterfactually-Guided Length Debiasing for Process Reward Models in Mathematical Reasoning

DGX agent

arXiv:2507.15698v2 Announce Type: replace-cross Abstract: Process Reward Models (PRMs) play a central role in evaluating and guiding multi-step reasoning in large language models (LLMs), especially fo

safetyarxiv-cs-ai

20 May 2026

Industry

Command A+ from @cohere is out now :) its our best model yet and its open source apache 2.0

Cohere has released Command A+, their latest and most advanced language model to date, under the Apache 2.0 open-source license. The model is now publicly available for use and development by the comm

industryclem-delangue--x

Composition of Memory Experts for Diffusion World Models

arXiv:2605.18813v1 Announce Type: cross Abstract: World models aim to predict plausible futures consistent with past observations, a capability central to planning and decision-making in reinforcement

applicationsarxiv-cs-ai

Fine-tuning language encoding models on slow fMRI improves prediction for fast ECoG

arXiv:2605.19224v1 Announce Type: new Abstract: Neuroscientists have recently turned to intracranial brain recording methods, like electrocorticography (ECoG), for human experiments because of the fin

researcharxiv-cs-cl

Industry

Grok Build 0.1 is available on Vercel AI Gateway. xAI's beta coding model in Grok Build CLI. 𝚖𝚘𝚍𝚎𝚕: '𝚡𝚊𝚒/𝚐𝚛𝚘𝚔-𝚋𝚞𝚒𝚕𝚍-𝟶.𝟷' …

Grok Build 0.1, xAI's beta coding model, is now available on Vercel AI Gateway for developers to access and integrate into their applications. The model can be accessed via the identifier 'xai/grok-bu

industryelon-musk--x

Agents

Hybrid Training for Vision-Language-Action Models

arXiv:2510.00600v2 Announce Type: replace-cross Abstract: Using Large Language Models to produce intermediate thoughts, a.k.a. Chain-of-thought (CoT), before providing an answer has been a successful

agentsarxiv-cs-ai

Tutorials

Language models struggle with compartmentalization

arXiv:2605.19284v1 Announce Type: new Abstract: In the training data used by large language models (LLMs), the same latent concept is often presented in multiple distinct ways: the same facts appear i

tutorialsarxiv-cs-cl

Lightweight and Fast Backdoor Model Detection

arXiv:2605.18907v1 Announce Type: cross Abstract: Deep neural networks (DNN), despite their remarkable performance, are highly vulnerable to backdoor attacks. Existing defenses mainly rely on activati

Markov Chain Decoders Overcome the Heavy-Tail Limitations of Lipschitz Generative Models

arXiv:2605.18931v1 Announce Type: cross Abstract: Heavy-tailed distributions are prevalent in performance evaluation, network traffic, and risk modeling. This behavior poses a fundamental challenge fo

MSAlign: Aligning Molecule and Mass Spectra Foundation Models for Metabolite Identification

model-releasesarxiv-cs-lg

arXiv:2605.19752v1 Announce Type: new Abstract: Accurately identifying metabolites i.e. small molecules from mass spectrometry data remains a core challenge in metabolomics, with broad applications in

Quantized Machine Learning Models for Medical Imaging in Low-Resource Healthcare Settings

arXiv:2605.19207v1 Announce Type: cross Abstract: Deep learning models have shown strong performance in medical image analysis, but deploying them in low-resource clinical environments remains difficu

applicationsarxiv-cs-ai

Scaling Evaluation-time Compute with Reasoning Models as Evaluators

arXiv:2503.19877v2 Announce Type: replace Abstract: As language model (LM) outputs get more and more natural, it is becoming more difficult than ever to evaluate their quality. Simultaneously, increas

researcharxiv-cs-cl

Hardware

🌍Today we release Mosaic, a probabilistic weather model that shifts the Pareto frontier of ML weather forecasting. It matches the skill of …

🌍Today we release Mosaic, a probabilistic weather model that shifts the Pareto frontier of ML weather forecasting. It matches the skill of state-of-the-art models while generating a 24-member, 10-day

hardwareemad-mostaque--x

Transformers Linearly Represent Highly Structured World Models

arXiv:2605.18847v1 Announce Type: cross Abstract: Do transformers, when trained on sequential reasoning traces, build internal models of the underlying task? And if so, does the structure of those int

When Preference Labels Fall Short: Aligning Diffusion Models from Real Data

arXiv:2605.19839v1 Announce Type: new Abstract: Preference alignment aims to guide generative models by learning from comparisons between preferred and non-preferred samples. In practice, most existin

safetyarxiv-cs-cv

When Tabular Foundation Models Meet Strategic Tabular Data: A Prior Alignment Approach

arXiv:2605.19662v1 Announce Type: new Abstract: Tabular foundation models based on pretrained prior-data fitted networks~(PFNs) have shown strong generalization on diverse tabular tasks, but they are

safetyarxiv-cs-ai

Adversarial Attacks on Downstream Weather Forecasting Models: Application to Tropical Cyclone Trajectory Prediction

arXiv:2510.10140v2 Announce Type: replace Abstract: Deep learning-based weather forecasting (DLWF) models leverage past weather observations to generate future forecasts, supporting a wide range of do

researcharxiv-cs-lg

Attention Hijacking: Response Manipulation Across Queries in Vision-Language Models

arXiv:2605.17310v1 Announce Type: cross Abstract: Existing adversarial attacks on vision-language models (VLMs) can steer model outputs toward attacker-specified target responses, but their effectiven

Tutorials

CBT-Audio: Evaluating Audio Language Models for Patient-Side Distress Intensity Estimation in CBT Session Recordings

arXiv:2605.17370v1 Announce Type: new Abstract: Cognitive behavioural therapy is widely used to help patients understand and manage psychological distress. It is often delivered through spoken convers

tutorialsarxiv-cs-ai

CodeScaler: Scaling Code LLM Training and Test-Time Inference via Reward Models

arXiv:2602.17684v2 Announce Type: replace-cross Abstract: Reinforcement Learning from Verifiable Rewards (RLVR) has driven recent progress in code large language models by leveraging execution-based f

Cracks in the Foundation: A Civil Infrastructure Dataset to Challenge Vision Foundation Models

arXiv:2605.18413v1 Announce Type: new Abstract: Automated structural health monitoring is essential to prevent catastrophic infrastructure failures. Precise, pixel-level defect segmentation is needed

safetyarxiv-cs-cv

DACA-GRPO: Denoising-Aware Credit Assignment for Reinforcement Learning in Diffusion Language Models

arXiv:2605.16342v1 Announce Type: cross Abstract: Diffusion large language models are a compelling alternative to autoregressive models, yet existing RL methods for diffusion treat all denoising steps

safetyarxiv-cs-ai

DAD4TS: Data-Augmentation-Oriented Diffusion Model for Time-Series Forecasting with Small-Scale Data

arXiv:2605.17866v1 Announce Type: new Abstract: Small-scale data is a critical problem in time-series forecasting tasks. Data augmentation is an effective strategy for this task, but it has a limitati

applicationsarxiv-cs-lg

Data Presentation Over Architecture: Resampling Strategies for Credit Risk Prediction with Tabular Foundation Models

arXiv:2605.18635v1 Announce Type: cross Abstract: Credit default prediction is a tabular learning problem with severe class imbalance, heterogeneous features, and tight latency budgets. Tabular Founda

Designing streetscapes from street-view imagery using diffusion models

model-releasesarxiv-cs-cv

arXiv:2605.17527v1 Announce Type: new Abstract: Street-view imagery (SVI) is widely used to quantify key indicators of urban environment, such as green- ery, sky, or road view indices. However, existi

DeTrack: A Benchmark and Altitude-Aware Dual World Model for Drone-embodied Tracking

model-releasesarxiv-cs-cv

arXiv:2605.17451v1 Announce Type: new Abstract: Aerial object tracking has broad applications in public safety, emergency rescue, wildlife monitoring, and related fields. However, existing aerial trac

DocReward: A Document Reward Model for Structuring and Stylizing

arXiv:2510.11391v3 Announce Type: replace-cross Abstract: Recent agentic workflows automate professional document generation but focus narrowly on textual quality, overlooking structural and stylistic

Dynamic robotic cloth folding with efficient Koopman operator-based model predictive control

arXiv:2605.18373v1 Announce Type: cross Abstract: Robotic cloth folding is a challenging task, particularly when considering dynamic folding tasks, which aim at folding cloth by fast motions that leve

researcharxiv-cs-lg

Employing Vision-Language Models for Face Image Quality Assessment

model-releasesarxiv-cs-cv

arXiv:2605.17489v1 Announce Type: new Abstract: Face Image Quality Assessment (FIQA) is a crucial control step in biometric pipelines. It ensures only reliable samples are processed to maintain system

EvoQRE: Modeling Bounded Rationality in Safety-Critical Traffic Simulation via Evolutionary Quantal Response Equilibrium

model-releasesarxiv-cs-ro

arXiv:2601.05653v2 Announce Type: replace Abstract: Existing traffic simulation frameworks for autonomous vehicles typically rely on imitation learning or game-theoretic approaches that solve for Nash

FAM-HRI: Foundation-Model Assisted Multi-Modal Human-Robot Interaction Combining Gaze and Speech

model-releasesarxiv-cs-ro

arXiv:2503.16492v3 Announce Type: replace-cross Abstract: ffective Human-Robot Interaction (HRI) is crucial for enhancing accessibility and usability in real-world robotics applications. However, exis

FediLoRA: Practical Federated Fine-Tuning of Foundation Models Under Missing-Modality Constraints

arXiv:2509.06984v3 Announce Type: replace-cross Abstract: Federated Learning with LoRA fine-tuning offers an efficient and privacy-aware solution for institutions to collaboratively leverage their lar

Agents

GEM: Gaussian Evolution Model for Occupancy Forecasting and Motion Planning

arXiv:2605.17682v1 Announce Type: new Abstract: Future 3D semantic occupancy forecasting and motion planning are central to autonomous driving, as they require models to reason about how surrounding s

agentsarxiv-cs-cv

GRaD-Nav++: Vision-Language Model Enabled Visual Drone Navigation with Gaussian Radiance Fields and Differentiable Dynamics

model-releasesarxiv-cs-ro

arXiv:2506.14009v2 Announce Type: replace Abstract: Autonomous drones capable of interpreting and executing high-level language instructions in unstructured environments remain a long-standing goal. Y

MCQ Difficulty Prediction via Modeling Learner Heterogeneity Using Data-Driven Cognitive Profiling

arXiv:2605.16290v1 Announce Type: cross Abstract: Predicting the difficulty of multiple-choice questions (MCQs) is important for effective assessment, yet current methods typically assume a unimodal s

Metric-Guided Feature Fusion of Visual Foundation Models for Segmentation Tasks

arXiv:2605.16864v1 Announce Type: cross Abstract: Although large-scale visual foundation models (VFMs) achieve remarkable performance in semantic understanding, they still underperform in instance-awa

Hardware

NanoQuant: Efficient Sub-1-Bit Quantization of Large Language Models

arXiv:2602.06694v2 Announce Type: replace Abstract: Weight-only quantization has become a standard approach for efficiently serving large language models (LLMs). However, existing methods fail to effi

hardwarearxiv-cs-lg

OrbiSim: World Models as Differentiable Physics Engines for Embodied Intelligence

arXiv:2605.16395v1 Announce Type: cross Abstract: We present OrbiSim, a novel robotic simulation paradigm that redefines world models as a fully differentiable physics engine for embodied intelligence

safetyarxiv-cs-lg

Self-supervised Hierarchical Visual Reasoning with World Model

arXiv:2605.17537v1 Announce Type: new Abstract: 3D open-world environments with adversarial opponents remain a core challenge for reinforcement learning due to their vast state spaces. Effective reaso

Agents

Task-Level AI Readiness Assessment for Business Process Management:The T-IPO Model and LARA Matrix in Financial-Services IT Operations

arXiv:2605.16297v1 Announce Type: cross Abstract: Which tasks inside an enterprise workflow can a large-language-model agent reliably handle, and under what conditions? Most business process modeling

agentsarxiv-cs-ai

Test-Time Hinting for Black-Box Vision-Language Models

arXiv:2605.16410v1 Announce Type: new Abstract: Test-time scaling (TTS) methods have proven highly effective for LLMs, yet their application to vision-language models (VLMs) remains relatively underex

researcharxiv-cs-cv

Traces of Social Competence in Large Language Models

arXiv:2603.04161v2 Announce Type: replace Abstract: The False Belief Test (FBT) has been the main method for assessing Theory of Mind (ToM) and related socio-cognitive competencies. For Large Language

applicationsarxiv-cs-cl

Training data attribution in diffusion models via mirrored unlearning and noise-consistent skew

arXiv:2605.17938v1 Announce Type: cross Abstract: Training data attribution (TDA) should enable generative model interpretability and foster a variety of related downstream tasks. Nonetheless, current

applicationsarxiv-cs-ai

Vision Foundation Models as Generalist Tokenizers for Image Generation

arXiv:2605.18390v1 Announce Type: new Abstract: In this work, we explore the largely unexplored direction of building a generalist image tokenizer directly on top of a frozen vision foundation model (

researcharxiv-cs-cv

WinQ: Accelerating Quantization-Aware Training of Language Models Around Saddle Points

arXiv:2605.17471v1 Announce Type: new Abstract: Quantization-aware training (QAT) is widely adopted to quantize language models by training full-precision weights using gradients from the quantized mo

researcharxiv-cs-lg

ASRU: Activation Steering Meets Reinforcement Unlearning for Multimodal Large Language Models

arXiv:2605.15687v1 Announce Type: cross Abstract: Multimodal large language models (MLLMs) may memorize sensitive cross-modal information during pretraining, making machine unlearning (MU) crucial. Ex

safetyarxiv-cs-ai

18 May 2026

Can Large Language Models Imitate Human Speech for Clinical Assessment? LLM-Driven Data Augmentation for Cognitive Score Prediction