Search: “models”

Improved visual-information-driven model for crowd simulation and its modular application

arXiv:2504.03758v4 Announce Type: replace-cross Abstract: Crowd movement simulation is crucial for pedestrian safety management and facility design. Data-driven models offer the potential to improve r

safetyarxiv-cs-cv

Inference-Time Scaling in Diffusion Models through Iterative Partial Refinement

DGX agent

arXiv:2605.19317v1 Announce Type: cross Abstract: Inference-time scaling has emerged as a major approach for improving reasoning capabilities, and has been increasingly applied to diffusion models. Ho

researcharxiv-cs-ai

20 May 2026

Jailbreaking on Text-to-Video Models via Scene Splitting Strategy

arXiv:2509.22292v2 Announce Type: replace-cross Abstract: Along with the rapid advancement of numerous Text-to-Video (T2V) models, growing concerns have emerged regarding their safety risks. While rec

safetyarxiv-cs-ai

MetaRA: Metamorphic Robustness Assessment for Multimodal Large Language Model-based Visual Question Answering Systems

arXiv:2605.19307v1 Announce Type: new Abstract: Visual Question Answering (VQA), as the representative multimodal task, serves as a key benchmark for evaluating the reasoning capabilities of Multimoda

MiMuon: Mixed Muon Optimizer with Improved Generalization for Large Models

arXiv:2605.19619v1 Announce Type: cross Abstract: Matrix-structured parameters frequently appear in many artificial intelligence models such as large language models. More recently, an efficient Muon

researcharxiv-cs-ai

No Hard Negatives Required: Concept Centric Learning Leads to Compositionality without Degrading Zero-shot Capabilities of Contrastive Models

arXiv:2603.25722v2 Announce Type: replace Abstract: Contrastive vision-language (V&L) models remain a popular choice for various applications. However, several limitations have emerged, most notably t

PhyWorld: Physics-Faithful World Model for Video Generation

arXiv:2605.19242v1 Announce Type: cross Abstract: World simulators can provide safe and scalable environments for training Physical AI systems before real-world deployment. Large video generation mode

Protein Autoregressive Modeling via Multiscale Structure Generation

arXiv:2602.04883v2 Announce Type: replace-cross Abstract: We present protein autoregressive modeling (PAR), the first multi-scale autoregressive framework for protein backbone generation via coarse-to

Applications

Reducing Diffusion Model Memorization with Higher Order Langevin Dynamics

arXiv:2605.19170v1 Announce Type: cross Abstract: Diffusion/score-based models have emerged as powerful generative models, capable of generating high-quality samples that mimic the training data distr

applicationsarxiv-cs-lg

Robust Basis Spline Decoupling for the Compression of Transformer Models

arXiv:2605.18794v1 Announce Type: cross Abstract: Decoupling is a powerful modeling paradigm for representing multivariate functions as compositions of linear transformations and univariate nonlinear

SciCustom: A Framework for Custom Evaluation of Scientific Capabilities in Large Language Models

arXiv:2605.19357v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly applied to scientific research, yet existing evaluations often fail to reflect the fine-grained capabiliti

The Growing Pains of Frontier Models: When Leaderboards Stop Separating and What to Measure Next

arXiv:2605.18840v1 Announce Type: cross Abstract: Leaderboards rank frontier models on independent axes but do not reveal whether capabilities reinforce or trade off across releases -- and at the fron

A Survey on Foundation Models for Personalized Federated Intelligence

arXiv:2505.06907v2 Announce Type: replace Abstract: The rise of large language models (LLMs), such as ChatGPT, Gemini, and Grok, has reshaped the AI landscape. As prominent instances of foundational m

A Unified Framework for Structured Flow Modeling: From Continuous Fields to Data-Driven Representations

arXiv:2605.18250v1 Announce Type: cross Abstract: Many dynamical systems can be described in terms of structured flows combining source/sink behavior, cyclic dynamics, and topology-constrained transpo

Accelerating Rectified Flow Models via Trajectory-Aware Caching

arXiv:2605.16789v1 Announce Type: new Abstract: Diffusion and rectified flow (RF) models generate high-fidelity images and videos, but their iterative velocity-field evaluations are computationally ex

Accelerating Redshift-Conditioned Galaxy Image Synthesis with One-step Generative Modeling

arXiv:2605.17546v1 Announce Type: cross Abstract: Understanding galaxy morphology evolution across cosmic time requires models that can generate realistic galaxy populations conditioned on redshift. I

Agentic Chunking and Bayesian De-chunking of AI Generated Fuzzy Cognitive Maps: A Model of the Thucydides Trap

arXiv:2605.17903v1 Announce Type: new Abstract: We automatically generate feedback causal fuzzy cognitive maps (FCMs) from text by teaching large-language-model agents to break the text into overlappi

Artificial Intolerance: Stigmatizing Language in Clinical Documentation Skews Large Language Model Decision-Making

arXiv:2605.17228v1 Announce Type: new Abstract: Large Language Models (LLMs) are increasingly deployed in high-stakes domains such as clinical decision support and medical documentation. However, the

safetyarxiv-cs-cl

Applications

Automatic Unsupervised Ensemble Outlier Model Selection--Extended Version

arXiv:2605.16567v1 Announce Type: cross Abstract: Unsupervised outlier detection is attractive because it eliminates the need for labeled data. Moreover, forming multi-model ensembles can improve dete

applicationsarxiv-cs-ai

Beyond Accuracy: Robustness, Interpretability and Expressiveness of EEG Foundation Models

arXiv:2605.17562v1 Announce Type: cross Abstract: EEG foundation models (EEG-FMs) have been evaluated predominantly on clean, in-distribution accuracy, leaving their robustness, interpretability and r

researcharxiv-cs-ai

Beyond Neural Incompatibility: Cross-Scale Knowledge Transfer in Language Models through Latent Semantic Alignment

arXiv:2510.24208v2 Announce Type: replace Abstract: Language Models (LMs) encode substantial knowledge in their parameters, yet it remains unclear how to transfer such knowledge in a fine-grained mann

DARE-EEG: A Foundation Model for Mining Dual-Aligned Representation of EEG

arXiv:2605.18298v1 Announce Type: new Abstract: Foundation models pre-trained through masked reconstruction on large-scale EEG data have emerged as a promising paradigm for learning generalizable neur

Agents

Democratizing Large-Scale Re-Optimization with LLM-Guided Model Patches

arXiv:2605.18692v1 Announce Type: new Abstract: Optimization models developed by operations research (OR) experts are often deployed as decision-support systems in industrial settings. However, real-w

agentsarxiv-cs-ai

Do Vision-Language-Models show human-like logical problem-solving capability in point and click puzzle games?

arXiv:2605.11223v2 Announce Type: replace Abstract: Vision-Language(-Action) Models (VLMs) are increasingly applied to interactive environments, yet existing benchmarks often overlook the complex phys

DP-SelFT: Differentially Private Selective Fine-Tuning for Large Language Models

model-releasesarxiv-cs-lg

arXiv:2605.17432v1 Announce Type: new Abstract: Large language models (LLMs) are commonly adapted to downstream tasks through fine-tuning, but fine-tuning data often contains sensitive information tha

Effort as Ceiling, Not Dial: Reasoning Budget Does Not Modulate Cognitive Cost Alignment Between Humans and Large Reasoning Models

arXiv:2605.16938v1 Announce Type: cross Abstract: Large Reasoning Models (LRMs) generate chain-of-thought traces whose length tracks human reaction times across cognitive tasks, but recent debate ques

Emulating the Forced Response of Climate Models with Flow Matching

arXiv:2605.16929v1 Announce Type: new Abstract: Global climate models are essential tools to simulate past and potential future pathways of climate change, as well as associated climate impacts. Share

Evaluating AI Alignment in LLMs: Output Analysis of Value Priorities Across 75 Models with Human Benchmarking

arXiv:2506.12617v4 Announce Type: replace Abstract: Large language models (LLMs) are increasingly used in human-AI interaction research and practice, yet existing capability and safety benchmarks reve

safetyarxiv-cs-ai

Local Ai

Friends and Grandmothers in Silico: Localizing Entity Cells in Language Models

arXiv:2604.01404v2 Announce Type: replace-cross Abstract: How do language models retrieve entity-specific facts from their parameters? We investigate this question by searching for sparse, entity-sele

local-aiarxiv-cs-ai

GaussianDWM: 3D Gaussian Driving World Model for Unified Scene Understanding and Multi-Modal Generation

arXiv:2512.23180v3 Announce Type: replace Abstract: Driving World Models (DWMs) have been developing rapidly with the advances of generative models. However, existing DWMs lack 3D scene understanding

safetyarxiv-cs-cv

Google launches new Omni model. Google says that today Omni can create and edit (yes, edit!!) video but eventually it is to go from “any inp…

model-releasesallie-k--miller--x

Google launches new Omni model. Google says that today Omni can create and edit (yes, edit!!) video but eventually it is to go from “any input to any output”. Even more of a reason to believe that Sor

HalluScore: Large Language Model Hallucination Question Answering Benchmark

arXiv:2605.17007v1 Announce Type: new Abstract: Large language models (LLMs) have achieved remarkable progress in natural language generation, but remain susceptible to hallucination. In response to g

Incantation: Natural Language as the Action Interface for Multi-Entity Video World Models

arXiv:2605.18601v1 Announce Type: new Abstract: Modern interactive video world models have achieved impressive visual fidelity, yet lack fine-grained multi-entity control and cross-entity, cross-world

LLMForge: Multi-Backend Hardware-Aware Neural Architecture Search with Infinite-Head Attention for Edge Language Models

arXiv:2605.17653v1 Announce Type: cross Abstract: Sub-billion-parameter Transformer language models are increasingly deployed on edge devices, where the privacy, latency, and operating-cost advantages

MentalBench: A DSM-Grounded Benchmark for Evaluating Psychiatric Diagnostic Capability of Large Language Models

arXiv:2602.12871v2 Announce Type: replace Abstract: Large language models (LLMs) have attracted growing interest as supportive tools for psychiatric assessment and clinical decision support. However,

MIRAGE: Robust multi-modal architectures translate fMRI-to-image models from vision to mental imagery

arXiv:2605.17198v1 Announce Type: cross Abstract: To be useful for downstream applications, vision decoding models that are trained to reconstruct seen images from human brain activity must be able to

Scale Determines Whether Language Models Organize Representation Geometry for Prediction

arXiv:2605.17084v1 Announce Type: cross Abstract: In language models, what a representation encodes is determined by the geometry of its representation space: distances, not activations, carry meaning

safetyarxiv-cs-cl

Self-Evolving Spatial Reasoning in Vision Language Models via Geometric Logic Consistency

arXiv:2605.18162v1 Announce Type: cross Abstract: Vision-Language Models (VLMs) have made striking progress, yet their spatial reasoning remains fragile: models that answer an original input correctly

safetyarxiv-cs-ai

Self-Supervised On-Policy Distillation for Reasoning Language Models

model-releasesarxiv-cs-lg

arXiv:2605.17497v1 Announce Type: new Abstract: GRPO-style RLVR trains reasoning models from multiple on-policy attempts per prompt, but typically uses these attempts only through terminal rewards. We

Agents

SWoMo: Neuro-Symbolic World Model for Cataract Surgery Simulation

arXiv:2605.16530v1 Announce Type: new Abstract: Realistic surgical simulation plays a crucial role in training novice surgeons and in the development of autonomous agents. World models can scale such

agentsarxiv-cs-cv

Symmetry Matters: Auditing and Symmetrizing 3D Generative Models

arXiv:2512.18953v2 Announce Type: replace Abstract: Symmetry is a strong prior present in many object categories, yet standard benchmarks for 3D generative models rarely report whether this prior is p

researcharxiv-cs-cv

Task Abstention for Large Language Models in Code Generation

arXiv:2605.17029v1 Announce Type: cross Abstract: Large language models (LLMs) have revolutionized automated code generation. One serious concern, however, is the so-called ``hallucination'', i.e., LL

TeleCom-Bench: How Far Are Large Language Models from Industrial Telecommunication Applications?

arXiv:2605.18025v1 Announce Type: new Abstract: While Large Language Models have achieved remarkable integration in various vertical scenarios, their deployment in the telecommunications domain remain

Time Series Foundation Models as Strong Baselines in Transportation Forecasting: A Large-Scale Benchmark Analysis

model-releasesarxiv-cs-lg

arXiv:2602.24238v2 Announce Type: replace Abstract: Accurate forecasting of transportation dynamics is essential for urban mobility and infrastructure planning. Although recent work has achieved stron

Towards Universal Physical Adversarial Attacks via a Joint Multi-Objective and Multi-Model Optimization Framework

arXiv:2605.17772v1 Announce Type: new Abstract: Physical adversarial attacks often overfit single surrogate models and optimization objectives. While ensemble attacks can mitigate this, existing metho

safetyarxiv-cs-cv

Transitivity Meets Cyclicity: Explicit Preference Decomposition for Dynamic Large Language Model Alignment

arXiv:2605.17342v1 Announce Type: cross Abstract: Standard RLHF relies on transitive scalar rewards, failing to capture the cyclic nature of human preferences. While some approaches like the General P

Universal Inverse Distillation for Matching Models with Real-Data Supervision (No GANs)

arXiv:2509.22459v4 Announce Type: replace-cross Abstract: While achieving exceptional generative quality, modern diffusion, flow, and other matching models suffer from slow inference, as they require

VISTA-Bench: Do Vision-Language Models Really Understand Visualized Text as Well as Pure Text?

arXiv:2602.04802v2 Announce Type: replace Abstract: Vision-Language Models (VLMs) have achieved impressive performance in cross-modal understanding across textual and visual inputs, yet existing bench