Search: “models”

Modular Multimodal Classification Without Fine-Tuning: A Simple Compositional Approach

arXiv:2605.20674v1 Announce Type: new Abstract: We introduce CoMET, extit{extbf{C}omposing extbf{M}odality extbf{E}ncoders with extbf{T}abular foundation models}, a simple yet highly competitive metho

Model Releases

RadProPoser: Probabilistic Radar Tensor Human Pose Estimation That Knows Its Limits

DGX agent

arXiv:2508.03578v2 Announce Type: replace Abstract: Radar-based human pose estimation enables privacy-preserving motion tracking for ambient intelligence, yet the noisy nature of radar sensing makes u

model-releasesarxiv-cs-cv

21 May 2026

Reinforcing Human Behavior Simulation via Verbal Feedback

arXiv:2605.20506v1 Announce Type: cross Abstract: Humans learn social norms and behaviors from verbal feedback (e.g., a parent saying 'that was rude' or a friend explaining 'here's why that hurt'). Ye

Resolving Long-Tail Ambiguity in Unsupervised 3D Point Cloud Segmentation with Language Priors

arXiv:2605.20737v1 Announce Type: new Abstract: Existing approaches for unsupervised 3D point cloud segmentation predominantly rely on a purely visual similarity-based learning-by-clustering paradigm,

Reviving Error Correction in Modern Deep Time-Series Forecasting

arXiv:2605.21088v1 Announce Type: new Abstract: Modern deep-learning models have achieved remarkable success in time-series forecasting. Yet, their performance degrades in long-term prediction due to

Runtime-Certified Bounded-Error Quantized Attention

arXiv:2605.20868v1 Announce Type: new Abstract: KV cache quantization reduces the memory cost of long-context LLM inference, but introduces approximation error that is typically validated only empiric

Local Ai

Semantic Granularity Navigation in Image Editing

arXiv:2605.21190v1 Announce Type: new Abstract: Despite the generative capabilities of diffusion and flow models, real-image editing remains constrained by a persistent trade-off between semantic edit

local-aiarxiv-cs-cv

SR-Ground: Image Quality Grounding for Super-Resolved Content

arXiv:2605.21244v1 Announce Type: new Abstract: Super-Resolution (SR) has advanced rapidly in recent years, with diffusion-based models achieving unprecedented fidelity at the cost of introducing new

researcharxiv-cs-cv

Strategy-Induct: Task-Level Strategy Induction for Instruction Generation

arXiv:2605.20924v1 Announce Type: new Abstract: Designing effective task-level prompts is crucial for improving the performance of Large Language Models (LLMs). While prior work on instruction inducti

researcharxiv-cs-cl

The Devil is in the Condition Numbers: Why is GLU Better than non-GLU Structure?

arXiv:2605.20749v1 Announce Type: new Abstract: Gated Linear Units (GLU) and their variants are widely adopted in modern open-source large language model architectures and consistently outperform thei

Local Ai

The General Theory of Localization Methods

arXiv:2605.20635v1 Announce Type: new Abstract: This paper proposes a general machine learning framework called the localization method, which is fundamentally built on two core concepts: localization

local-aiarxiv-cs-lg

Industry

This is the way

This is the way Elon Musk on why the Model S and Model X succeeded: “Those cars were designed with love. Every part of it, inside and outside, even things people couldn’t see - we put there because we

industryelon-musk--x

Training Language Agents to Learn from Experience

arXiv:2605.20477v1 Announce Type: cross Abstract: Language agents can adapt from experience in interactive environments, but current reflection-based methods can only self-correct within a single task

VDFP: Video Deflickering with Flicker-banding Priors

arXiv:2605.21079v1 Announce Type: new Abstract: Capturing digital screens with smartphones frequently induces severe banding due to hardware synchronization mismatches. Existing video restoration meth

WCXB: A Multi-Type Web Content Extraction Benchmark

arXiv:2605.21097v1 Announce Type: new Abstract: Web content extraction - isolating a page's main content from surrounding boilerplate - is a prerequisite for search indexing, retrieval-augmented gener

Agents

What if Agents Could Imagine? Reinforcing Open-Vocabulary HOI Comprehension through Generation

arXiv:2602.11499v2 Announce Type: replace Abstract: Multimodal Large Language Models have shown promising capabilities in bridging visual and textual reasoning, yet their reasoning capabilities in Ope

agentsarxiv-cs-cv

When Irregularity Helps: A Subclass Analysis of Inductive Bias in Neural Morphology

arXiv:2605.20558v1 Announce Type: new Abstract: Neural morphological generation systems often achieve high aggregate accuracy on benchmark datasets, yet such performance can conceal systematic errors

A Framework for Evaluating Zero-Shot Image Generation in Concept-based Explainability

arXiv:2605.19855v1 Announce Type: cross Abstract: Concept-based Explainable Artificial Intelligence (XAI) interprets deep learning models using human-understandable visual features (e.g., textures or

researcharxiv-cs-ai

Agents

A Methodology for Selecting and Composing Runtime Architecture Patterns for Production LLM Agents

arXiv:2605.20173v1 Announce Type: new Abstract: Production LLM agents combine stochastic model outputs with deterministic software systems, yet the boundary between the two is rarely treated as a firs

agentsarxiv-cs-ai

A Two-Parameter Weibull Framework for Diagnosing Transformer Weight Distributions

arXiv:2605.18898v1 Announce Type: new Abstract: We apply the Weibull distribution -- a two-parameter family from extreme-value theory -- as a diagnostic framework for element-wise weight magnitude dis

Adaptive Power Iteration Method for Differentially Private PCA

arXiv:2602.11454v3 Announce Type: replace-cross Abstract: We study left(epsilon,eltaright)-differentially private algorithms for the problem of approximately computing the top singular vector of a mat

Agent Meltdowns: The Road to Hell Is Paved with Helpful Agents

arXiv:2605.19149v1 Announce Type: new Abstract: Agents operating with computer and Web use inevitably encounter errors: inaccessible webpages, missing files, local and remote misconfigurations, etc. T

Backtracking When It Strays: Mitigating Dual Exposure Biases in LLM Reasoning Distillation

arXiv:2605.19433v1 Announce Type: cross Abstract: Large language models (LLMs) have achieved remarkable success in complex reasoning tasks via long chain-of-thought (CoT), yet their immense computatio

safetyarxiv-cs-ai

BERTO: Intent-Driven Network Time Series Forecasting via Natural Language Operator Preferences

arXiv:2512.05721v2 Announce Type: replace Abstract: Traditional cellular traffic forecasting models are optimized for minimizing symmetric errors, leaving them indifferent to shifting operational prio

safetyarxiv-cs-lg

BrainDyn: A Sheaf Neural ODE for Generative Brain Dynamics

arXiv:2605.19324v1 Announce Type: new Abstract: Efficient neural network models that generate brain-like dynamic activity can be a valuable resource for generating synthetic data, analyzing difference

Applications

CogOmniControl: Reasoning-Driven Controllable Video Generation via Creative Intent Cognition

arXiv:2605.19995v1 Announce Type: new Abstract: Recent diffusion models achieve strong photorealism and fluency in video generation, yet remain fragile under abstract, sparse or complex conditions, le

applicationsarxiv-cs-cv

Distance-Aware Muon: Adaptive Step Scaling for Normalized Optimization

arXiv:2605.18999v1 Announce Type: new Abstract: Muon and related normalized optimizers decouple the choice of update direction from the choice of step scale, but their practical performance remains se

Do Better Volatility Forecasts Lead to Better Portfolios? Evidence from Graph Neural Networks

arXiv:2605.19278v1 Announce Type: cross Abstract: This paper tests whether graph neural networks improve realized volatility forecasts and whether those forecasts improve portfolio performance. Using

Dual-Prompt CLIP with Hybrid Visual Encoders for Occluded Person Re-Identification

arXiv:2605.19527v1 Announce Type: new Abstract: Occluded person re-identification focuses on matching partially visible pedestrians across multiple camera views. However, occlusions disrupt body-regio

DualView: Adaptive Local-Global Fusion for Multi-Hop Document Reranking

arXiv:2605.18767v1 Announce Type: cross Abstract: Multi-hop question answering requires aggregating information from multiple documents, a critical capability for knowledge-intensive applications. A f

Enabling Real-Time Colonoscopic Polyp Segmentation on Commodity CPUs via Ultra-Lightweight Architecture

arXiv:2602.04381v2 Announce Type: replace-cross Abstract: Real-time polyp segmentation is essential for early colorectal cancer detection, yet clinical deployment remains blocked by GPU dependency. We

From Sparsity to Simplicity: Enabling Simpler Sequential Replacements via Sparse Attention Distillation

arXiv:2605.18865v1 Announce Type: cross Abstract: Self-attention serves as the core foundation of large-scale transformer pretraining, but its quadratic token interaction cost makes inference expensiv

Hardware

GEM: GPU-Variability-Aware Expert to GPU Mapping for MoE Systems

arXiv:2605.19945v1 Announce Type: cross Abstract: Mixture-of-Expert (MoE) models enable efficient inference by employing smaller experts and activating only a subset of them per token. MoE serving eng

hardwarearxiv-cs-ai

Generative Recursive Reasoning

arXiv:2605.19376v1 Announce Type: new Abstract: How should future neural reasoning systems implement extended computation? Recursive Reasoning Models (RRMs) offer a promising alternative to autoregres

researcharxiv-cs-ai

Hard-Label Black-Box Attacks on 3D Point Clouds

arXiv:2412.00404v2 Announce Type: replace Abstract: With the maturity of depth sensors in various 3D safety-critical applications, 3D point cloud models have been shown to be vulnerable to adversarial

safetyarxiv-cs-cv

Hardware

HiLiftAeroML: High-Fidelity Computational Fluid Dynamics Dataset for High-Lift Aircraft Aerodynamics

arXiv:2605.19565v1 Announce Type: cross Abstract: This paper describes the first-ever open-source high-fidelity CFD dataset of a high-lift aircraft for the purpose of AI surrogate model development. T

hardwarearxiv-cs-lg

How do LLMs Compute Verbal Confidence

arXiv:2603.17839v3 Announce Type: replace-cross Abstract: Verbal confidence -- prompting LLMs to state their confidence as a number or category -- is widely used to extract uncertainty estimates from

INSHAPE: Instance-Level Shapelets for Interpretable Time-Series Classification

arXiv:2605.20088v1 Announce Type: cross Abstract: Discovering shapelets -- i.e., discriminative temporal patterns within time series -- has been widely studied to address the inherent complexity of ti

it’s in gemini, just create it in ai studio. oh, that’s for your personal google one account. for workspace you need gemini business. no, no…

model-releasessimon-willison--x

it’s in gemini, just create it in ai studio. oh, that’s for your personal google one account. for workspace you need gemini business. no, not gemini advanced, that’s ai pro now. unless you need ai ult

Learning Efficient Guardrails for Compliance

arXiv:2510.03485v2 Announce Type: replace Abstract: Autonomous web agents are increasingly deployed for long-horizon tasks, yet their ability to adhere to real-world policies remains critically undere

Learning When to Adapt

arXiv:2605.19028v1 Announce Type: new Abstract: Low-rank adaptation (LoRA) is a widely used parameter-efficient fine-tuning method, yet its learned correction is static: the same low-rank update is ap

Memory-Augmented Reinforcement Learning Agent for CAD Generation

arXiv:2605.19748v1 Announce Type: new Abstract: Automatic generation of computer-aided design (CAD) models is a core technology for enabling intelligence in advanced manufacturing. Existing generation

safetyarxiv-cs-ai

Minimax Optimal Variance-Aware Regret Bounds for Multinomial Logistic MDPs

arXiv:2605.19768v1 Announce Type: new Abstract: We study reinforcement learning for episodic Markov Decision Processes (MDPs) whose transitions are modelled by a multinomial logistic (MNL) model. Exis

researcharxiv-cs-ai

NGL: Natural Garment Language for Training-Free Sewing Pattern Estimation

arXiv:2602.20700v2 Announce Type: replace Abstract: Estimating sewing patterns from images is a practical approach for creating high-quality 3D garments, but it remains challenging due to the scarcity

OmniGUI: Benchmarking GUI Agents in Omni-Modal Smartphone Environments

arXiv:2605.18758v1 Announce Type: cross Abstract: Current benchmarks for graphical user interface (GUI) agents predominantly rely on static screenshots. However, real-world smartphone interaction rout

Local Ai

Posterior Contraction of Levy Adaptive B-spline Regression in Besov Spaces

arXiv:2605.19610v1 Announce Type: cross Abstract: We investigate the asymptotic properties of the Levy Adaptive B-spline (LABS) regression model, a Bayesian nonparametric method that incorporates B-sp

local-aiarxiv-cs-lg

Real-World On-Vehicle Evaluation of Embedding-Based Anomaly Detection

arXiv:2605.19744v1 Announce Type: new Abstract: Detecting anomalies in traffic scenes is crucial for ensuring safety in autonomous driving, yet collecting representative anomalous data remains challen

Self-Filtered Distillation with LLMs-generated Trust Indicators for Reliable Patent Classification

arXiv:2510.05431v4 Announce Type: replace Abstract: Organizing large-scale patent corpora according to classification schemes is a core information management task that determines the accuracy and eff