Search: “models”

USIM and U0: A Vision-Language-Action Dataset and Model for General Underwater Robots

arXiv:2510.07869v4 Announce Type: replace Abstract: Underwater environments pose unique challenges for robotic navigation and manipulation. While existing research has primarily focused on task-specif

researcharxiv-cs-ro

25 May 2026

Research

Decision Potential Surface: A Theoretical and Practical Approximation of Large Language Model Decision Boundary

DGX agent

arXiv:2510.03271v2 Announce Type: replace Abstract: Decision boundary, the subspace of inputs where a machine learning model assigns equal classification probabilities to two classes, is pivotal in re

researcharxiv-cs-lg

23 May 2026

Equilibrium Propagation and Hamiltonian Inference in the Diffusive Fitzhugh-Nagumo Model

arXiv:2605.21568v1 Announce Type: new Abstract: In this work, we extend the Equilibrium Propagation framework to skew-gradient systems and show an equivalence between deep Energy-Based Models and Hami

Relational Linear Properties in Language Models: An Empirical Investigation

arXiv:2605.22532v1 Announce Type: new Abstract: Linear properties are ubiquitous in the representations of language models; however, testing them experimentally remains a challenging task. This work f

six years ago world (cognitive) models were the centerpiece of my essay The Next Decade in AI. their time is finally coming.

six years ago world (cognitive) models were the centerpiece of my essay The Next Decade in AI. their time is finally coming. Demis Hassabis on the limit in today’s AI: language can describe the world,

safetygary-marcus--x

World models have existed for years (though not in LLMs); I take them to be explicit representation of objects, places, events, mechanisms e…

World models have existed for years (though not in LLMs); I take them to be explicit representation of objects, places, events, mechanisms etc you can reason over. Chess computers have them (board, pi

safetygary-marcus--x

Ablate-to-Validate: Are Vision-Language Models Really Using Continuous Thought Tokens?

arXiv:2605.21642v1 Announce Type: new Abstract: Vision-language models (VLMs) are increasingly augmented with continuous or latent non-textual tokens intended to support 'visual thinking.' Despite imp

Enhancing Multimodal Large Language Models for Safety-Critical Driving Video Analysis

arXiv:2605.22185v1 Announce Type: new Abstract: Recent advancements in Multimodal Large Language Models (MLLMs) have demonstrated impressive capabilities in general visual understanding. However, thei

EvoVid: Temporal-Centric Self-Evolution for Video Large Language Models

arXiv:2605.21931v1 Announce Type: new Abstract: Recent Video Large Language Models (Video-LLMs) have demonstrated strong capabilities in video reasoning through reinforcement learning (RL). However, e

agentsarxiv-cs-cv

General Agentic Planning Through Simulative Reasoning with World Models

arXiv:2507.23773v3 Announce Type: replace-cross Abstract: What does it mean to plan? Current agentic systems, whether scaffolded workflows or end-to-end policies, rely on reactive decision-making: sel

agentsarxiv-cs-cl

VSAS-Bench: Real-Time Evaluation of Visual Streaming Assistant Models

researchapple-ml-research

Streaming vision-language models (VLMs) continuously generate responses given an instruction prompt and an online stream of input frames. This is a core mechanism for real-time visual assistants. Exis

Compute Only Once: UG-Separation for Efficient Large Recommendation Models

arXiv:2602.10455v2 Announce Type: replace-cross Abstract: Driven by scaling laws, recommender systems increasingly rely on larger-scale models to capture complex feature interactions and user behavior

Deformba: Vision State Space Model with Adaptive State Fusion

arXiv:2605.21308v1 Announce Type: new Abstract: State Space Models (SSMs) have emerged as a powerful and efficient alternative to Transformers, demonstrating linear-time complexity and exceptional seq

Local Ai

DNACHUNKER: Learnable Tokenization for DNA Language Models

arXiv:2601.03019v4 Announce Type: replace-cross Abstract: DNA language models are increasingly used to represent genomic sequence, yet their effectiveness depends critically on how raw nucleotides are

local-aiarxiv-cs-cl

Dual Quaternion Based Contact Modeling for Fast and Smooth Collision Recovery of Quadrotors

arXiv:2603.14698v3 Announce Type: replace Abstract: Unmanned aerial vehicles (UAVs) operating in cluttered environments require efficient and accurate impact modeling to maintain stability post collis

researcharxiv-cs-ro

Efficient numeracy in language models through single-token number embeddings

arXiv:2510.06824v2 Announce Type: replace Abstract: To drive progress in science and engineering, large language models (LLMs) must be able to process large amounts of numerical data and solve long ca

tutorialsarxiv-cs-lg

FEAT: A Linear-Complexity Foundation Model for Extremely Large Structured Data

arXiv:2603.16513v3 Announce Type: replace Abstract: Structured data is widely used in domains such as healthcare, finance, and scientific data management. Recent studies on structured data foundation

safetyarxiv-cs-lg

LASH: Adaptive Semantic Hybridization for Black-Box Jailbreaking of Large Language Models

arXiv:2605.21362v1 Announce Type: new Abstract: Jailbreak attacks expose a persistent gap between the intended safety behavior of aligned large language models and their behavior under adversarial pro

safetyarxiv-cs-cl

Let EEG Models Learn EEG

arXiv:2605.21280v1 Announce Type: new Abstract: High-fidelity EEG generation is critical for alleviating data scarcity and addressing privacy constraints in large-scale neural modeling. Despite recent

tutorialsarxiv-cs-cv

Applications

MAPS: A Synthetic Dataset for Probing Vision Models in a Controlled 3D Scene Space

arXiv:2605.20549v1 Announce Type: new Abstract: Modern vision models achieve strong performance on standard benchmarks, yet their aggregate accuracy reveals little about which scene properties drive t

applicationsarxiv-cs-cv

Local Ai

Mechanisms of Misgeneralization in Physical Sequence Modeling

arXiv:2605.20299v1 Announce Type: new Abstract: Generative sequence models are often trained to plan motion in physical domains, from robotics to mechanical simulations. When constructing a dataset to

local-aiarxiv-cs-lg

Modeling and Control of a Pneumatic Morphing Soft Quadrotor based on the SOFA Framework for Dynamic Soft Robotic Simulation

arXiv:2605.21031v1 Announce Type: new Abstract: This article presents a novel SOFA based finite element method for the soft body modeling and the corresponding dynamic simulation and control of a pneu

researcharxiv-cs-ro

On the Regularity and Generalization of One-Step Wasserstein-guided Generative Models for PDE-Induced Measures

arXiv:2605.21388v1 Announce Type: new Abstract: Despite the remarkable empirical success of generative models, the available theory on their statistical accuracy in scientific computing remains largel

tutorialsarxiv-cs-lg

Local Ai

PaintCopilot: Modeling Painting as Autonomous Artistic Continuation

arXiv:2605.20941v1 Announce Type: new Abstract: We present PaintCopilot, a co-creative neural painting assistant that models painting as an open-ended autoregressive artistic behavior conditioned on e

local-aiarxiv-cs-cv

Quantum reservoir computing in Jaynes-Cummings models: Nonlinear memory and time-series prediction

model-releasesarxiv-cs-lg

arXiv:2510.00171v2 Announce Type: replace-cross Abstract: We investigate quantum reservoir computing (QRC) using a hybrid qubit-boson system described by the Jaynes-Cummings (JC) Hamiltonian and its d

Robust Subspace-Constrained Quadratic Models for Low-Dimensional Structure Learning

arXiv:2605.20300v1 Announce Type: new Abstract: In this paper, we propose a robust subspace-constrained quadratic model (SCQM) for learning low-dimensional structure from high-dimensional data. Buildi

SynCB: A Synergy Concept-Based Model with Dynamic Routing Between Concepts and Complementary Neural Branches

arXiv:2605.20908v1 Announce Type: new Abstract: Concept-based (CB) models provide interpretability and support test-time human intervention, while standard neural networks (NN) offer strong task perfo

Industry

Ten years ago, I walked into Tesla as an intern — January 2015, back when all we built was the Model S. I never imagined I'd one day lead th…

Ten years ago, I walked into Tesla as an intern — January 2015, back when all we built was the Model S. I never imagined I'd one day lead the Fremont factory where we are building some of the most ama

industryelon-musk--x

Tippett-minimum Fusion of Representation-space Diffusion Models for Multi-Encoder Out-of-Distribution Detection

model-releasesarxiv-cs-cv

arXiv:2605.20502v1 Announce Type: cross Abstract: We address out-of-distribution (OOD) detection across the full spectrum of distribution shifts -- global domain changes, semantic divergence, texture

A Logistic Regression Model to Predict Malaria Severity in Children

arXiv:2605.18900v1 Announce Type: cross Abstract: One of the main causes of death around the globe is malaria. Researchers have sought to develop predictive models for malaria outbreaks based on meteo

agentsarxiv-cs-lg

AffectVerse: Emotional World Models for Multimodal Affective Computing

arXiv:2605.19950v1 Announce Type: new Abstract: Humans infer emotions by integrating observed multimodal cues with expectations about how affective states may unfold. Existing multimodal large languag

Awakening the Hydra: Stabilizing Multi-Concept Backdoor Injection in Text-to-Image Diffusion Models

arXiv:2605.19698v1 Announce Type: cross Abstract: Text-to-image diffusion models are increasingly developed through open-source reuse and repeated downstream fine-tuning, where reused checkpoints are

Conflict-Resilient Multi-Agent Reasoning via Signed Graph Modeling

model-releasesarxiv-cs-ai

arXiv:2605.19418v1 Announce Type: new Abstract: LLM-based multi-agent systems (MAS) have demonstrated strong reasoning and decision-making capabilities that consistently surpass those of single LLM ag

Data-centric Design of Learning-based Surgical Gaze Perception Models in Multi-Task Simulation

arXiv:2602.09259v2 Announce Type: replace Abstract: In robot-assisted minimally invasive surgery (RMIS), reduced haptic feedback and depth cues increase reliance on expert visual perception, motivatin

tutorialsarxiv-cs-ro

Extreme Self-Preference in Language Models

arXiv:2509.26464v2 Announce Type: replace Abstract: Self-preference is a fundamental feature of biological organisms. Since large language models (LLMs) lack sentience, they might be expected to avoid

safetyarxiv-cs-ai

FlowErase-RL: Rethinking Concept Erasure as Reward Optimization in Flow Matching Models

arXiv:2605.19739v1 Announce Type: new Abstract: Recent advances in flow matching models have significantly improved text-to-image generation quality, but also introduce growing safety risks due to the

From Seeing to Thinking: Decoupling Perception and Reasoning Improves Post-Training of Vision-Language Models

arXiv:2605.20177v1 Announce Type: new Abstract: Recent advances in vision-language models (VLMs) emphasize long chain-of-thought reasoning; yet, we find that their performance on visual tasks is prima

researcharxiv-cs-cl

From Simple to Complex: Curriculum-Guided Physics-Informed Neural Networks via Gaussian Mixture Models

model-releasesarxiv-cs-lg

arXiv:2605.19263v1 Announce Type: new Abstract: Physics-informed neural networks (PINNs) offer a mesh-free framework for solving partial differential equations (PDEs), yet training often suffers from

Inverse Design of Metasurface based Absorbers using Physics Guided Conditional Diffusion Models

arXiv:2605.19611v1 Announce Type: new Abstract: Inverse design of metasurfaces for specific electromagnetic responses requires generating geometries that satisfy stringent spectral constraints while m

Learning Abstract World Models with a Group-Structured Latent Space

arXiv:2506.01529v2 Announce Type: replace Abstract: Learning meaningful abstract models of Markov Decision Processes (MDPs) is crucial for improving generalization from limited data. In this work, we

Mathematical Reasoning in Large Language Models: Benchmarks, Architectures, Evaluation, and Open Challenges

model-releasesarxiv-cs-ai

arXiv:2605.19723v1 Announce Type: cross Abstract: Mathematical reasoning is essential for problem-solving in education, science, and industry, serving as a crucial benchmark for evaluating artificial

MetaEarth-MM: Unified Multimodal Remote Sensing Image Generation with Scene-centered Joint Modeling

arXiv:2605.20090v1 Announce Type: new Abstract: Multi-modal remote sensing images are vital for Earth observation, yet complete paired observations are often scarce in practice. Existing generative me

Operationalizing Document AI: A Microservice Architecture for OCR and LLM Pipelines in Production

model-releasesarxiv-cs-ai

arXiv:2605.18818v1 Announce Type: new Abstract: Academic research tends to focus on new models for document understanding creating a wide gap in the literature between model definition and running mod

Rethinking the Design Space of Reinforcement Learning for Diffusion Models: On the Importance of Likelihood Estimation Beyond Loss Design

arXiv:2602.04663v2 Announce Type: replace-cross Abstract: Reinforcement learning has been widely applied to diffusion and flow models for visual tasks such as text-to-image generation. However, these

safetyarxiv-cs-ai

RoVLA: Multi-Consistency Constraints for Robust Vision-Language-Action Models

arXiv:2605.19678v1 Announce Type: new Abstract: Vision-Language-Action (VLA) models have shown strong performance on embodied manipulation, yet they remain brittle under visual observation changes, pa

safetyarxiv-cs-ro

very belated but in retrospect i think @sama's mythical 'build a business that gets better when models get better' is basically what I calle…

very belated but in retrospect i think @sama's mythical 'build a business that gets better when models get better' is basically what I called Agent Labs here. seeing a very direct correlation with mod

agentsswyx--x

A note on connections between the Follmer process and the denoising diffusion probabilistic model

model-releasesarxiv-cs-lg

arXiv:2605.18040v1 Announce Type: cross Abstract: The Follmer process is a Brownian motion conditioned to have a pre-specified distribution at time 1. This process can be interpreted as an 'augmented'

19 May 2026

Ablating Safety: Mechanisms for Removing Alignment in Language Models for Security Applications