Search: “papers”

arXiv:2605.02262v1 Announce Type: cross Abstract: Recently, video language models (VLMs) have been applied in various fields. However, the visual token sequence of the VLM is too long, which may cause

hardwarearxiv-cs-cl

5 May 2026

Local Ai

Zero-Shot Confidence Estimation for Small LLMs: When Supervised Baselines Aren't Worth Training

DGX agent

arXiv:2605.02241v1 Announce Type: cross Abstract: How reliably can a small language model estimate its own correctness? The answer determines whether local-to-cloud routing-escalating queries a cheap

local-aiarxiv-cs-cl

5 May 2026

A Comparative Analysis of Machine Learning Models for Intrusion Detection in Intelligent Transport Systems

arXiv:2605.00279v1 Announce Type: cross Abstract: AI-powered edge computing security is moving Intelligent Transportation Systems (ITS) from passive, rule-based protections to proactive, smart, zero-t

local-aiarxiv-cs-lg

Tutorials

Adapting Large VLMs with Iterative and Manual Instructions for Generative Low-light Enhancement

arXiv:2507.18064v2 Announce Type: replace Abstract: Most existing low-light image enhancement (LLIE) methods rely on pre-trained model priors, low-light inputs, or both, while neglecting the semantic

tutorialsarxiv-cs-cv

AIDA-ReID: Adaptive Intermediate Domain Adaptation for Generalizable and Source-Free Person Re-Identification

arXiv:2605.00111v1 Announce Type: new Abstract: Person re-identification (Re-ID) aims to match images of the same individual across non-overlapping camera views and remains challenging due to domain s

AirFM-DDA: Air-Interface Foundation Model in the Delay-Doppler-Angle Domain for AI-Native 6G

arXiv:2605.00020v1 Announce Type: new Abstract: The success of large foundation models is catalyzing a new paradigm for AI-native 6G network design: wireless foundation models for physical layer desig

local-aiarxiv-cs-lg

Alethia: A Foundational Encoder for Voice Deepfakes

arXiv:2605.00251v1 Announce Type: cross Abstract: Existing voice deepfake detection and localization models rely heavily on representations extracted from speech foundation models (SFMs). However, dow

Batch Normalization for Neural Networks on Complex Domains

arXiv:2605.00467v1 Announce Type: new Abstract: Riemannian neural networks have proven effective in solving a variety of machine learning tasks. The key to their success lies in the development of pri

Beyond Heuristics: Learnable Density Control for 3D Gaussian Splatting

arXiv:2605.00408v1 Announce Type: new Abstract: While 3D Gaussian Splatting (3DGS) has demonstrated impressive real-time rendering performance, its efficacy remains constrained by a reliance on heuris

Broadband Wide Field of View Imaging with Computational Mirrors

arXiv:2605.00029v1 Announce Type: cross Abstract: Traditional glass-based optics are typically optimized for narrow spectral bands, such as the visible (400-700nm) or shortwave infrared (1000-1800nm).

Agents

Build, Judge, Optimize: A Blueprint for Continuous Improvement of Multi-Agent Consumer Assistants

arXiv:2603.03565v2 Announce Type: replace-cross Abstract: Conversational shopping assistants (CSAs) represent a compelling application of agentic AI, but moving from prototype to production reveals tw

agentsarxiv-cs-cl

Agents

Causality-enhanced Decision-Making for Autonomous Mobile Robots in Dynamic Environments

arXiv:2504.11901v5 Announce Type: replace Abstract: The growing integration of robots in shared environments-such as warehouses, shopping centres, and hospitals-demands a deep understanding of the und

agentsarxiv-cs-ro

Comparative Analysis of Polygon-Based and Global Machine Learning Models for Bus Occupancy Prediction

arXiv:2605.00083v1 Announce Type: new Abstract: Accurate forecasting of bus ridership (passengers numbers) is crucial for efficient management and optimization of public transport systems. Traditional

local-aiarxiv-cs-lg

Deepfakes: we need to re-think the concept of 'real' images

arXiv:2509.21864v2 Announce Type: replace Abstract: The wide availability and low usability barrier of modern image generation models has triggered the reasonable fear of criminal misconduct and negat

Diffusion Models for Solving Inverse Problems via Posterior Sampling with Piecewise Guidance

arXiv:2507.18654v2 Announce Type: replace-cross Abstract: Diffusion models are powerful tools for sampling from high-dimensional distributions by progressively transforming pure noise into structured

Directed Social Regard: Surfacing Targeted Advocacy, Opposition, Aid, Harms, and Victimization in Online Media

arXiv:2605.00776v1 Announce Type: new Abstract: The language in online platforms, influence operations, and political rhetoric frequently directs a mix of pro-social sentiment (e.g., advocacy, helpful

researcharxiv-cs-cl

Discrete Cosine Transform Based Decorrelated Attention for Vision Transformers

arXiv:2405.13901v4 Announce Type: replace Abstract: Self-attention is central to the success of Transformer architectures; however, learning the query, key, and value projections from random initializ

Distance metric learning for conditional anomaly detection

arXiv:2605.00490v1 Announce Type: new Abstract: Anomaly detection methods can be very useful in identifying unusual or interesting patterns in data. A recently proposed conditional anomaly detection f

DMDSC: A Dynamic-Margin Deep Simplex Classifier for Open-Set Recognition on Medical Image Datasets

arXiv:2605.00675v1 Announce Type: new Abstract: Medical imaging datasets are often characterized by extreme class imbalances, where rare pathologies are significantly underrepresented compared to comm

Do Open-Loop Metrics Predict Closed-Loop Driving? A Cross-Benchmark Correlation Study of NAVSIM and Bench2Drive

model-releasesarxiv-cs-ro

arXiv:2605.00066v1 Announce Type: new Abstract: Open-loop evaluation offers fast, reproducible assessment of autonomous driving planners, but its ability to predict real closed-loop driving performanc

Hardware

DPU or GPU for Accelerating Neural Networks Inference -- Why not both? Split CNN Inference

arXiv:2605.00174v1 Announce Type: cross Abstract: Video and image streaming on edge devices requires low latency. To address this, Neural Networks (NNs) are widely used, and prior work mainly focuses

hardwarearxiv-cs-cv

Efficient Spatio-Temporal Vegetation Pixel Classification with Vision Transformers

arXiv:2605.00296v1 Announce Type: new Abstract: Plant phenology-the study of recurrent life cycle events-is essential for understanding ecosystem dynamics and their responses to climate change impacts

EGREFINE: An Execution-Grounded Optimization Framework for Text-to-SQL Schema Refinement

arXiv:2605.00628v1 Announce Type: cross Abstract: Text-to-SQL enables non-expert users to query databases in natural language, yet real-world schemas often suffer from ambiguous, abbreviated, or incon

local-aiarxiv-cs-cl

Evaluating the Architectural Reasoning Capabilities of LLM Provers via the Obfuscated Natural Number Game

model-releasesarxiv-cs-lg

arXiv:2605.00677v1 Announce Type: new Abstract: While Large Language Models have achieved notable success on formal mathematics benchmarks such as MiniF2F, it remains unclear whether these results ste

Exploring the Limits of End-to-End Feature-Affinity Propagation for Single-Point Supervised Infrared Small Target Detection

arXiv:2605.00722v1 Announce Type: new Abstract: Single-point supervised infrared small target detection (IRSTD) drastically reduces dense annotation costs. Current state-of-the-art (SOTA) methods achi

From Backward Spreading to Forward Replay: Revisiting Target Construction in LLM Parameter Editing

arXiv:2605.00358v1 Announce Type: new Abstract: LLM parameter editing methods commonly rely on computing an ideal target hidden-state at a target layer (referred as anchor point) and distributing the

Generative Modeling under Non-Monotone MAR Missingness via Approximate Wasserstein Gradient Flows

arXiv:2604.04567v2 Announce Type: replace-cross Abstract: The prevalence of missing values in data science poses a substantial risk to any further analyses. Despite a wealth of research, principled no

Applications

Geometric analysis of attractor boundaries and storage capacity limits in kernel Hopfield networks

arXiv:2605.00366v1 Announce Type: cross Abstract: High-capacity associative memories based on Kernel Logistic Regression (KLR) exhibit strong storage capabilities, but the dynamical and geometric mech

applicationsarxiv-cs-lg

Applications

GOR-IS: 3D Gaussian Object Removal in the Intrinsic Space

arXiv:2605.00498v1 Announce Type: new Abstract: Recent advances in Neural Radiance Fields (NeRF) and 3D Gaussian Splatting (3DGS) have made it standard practice to reconstruct 3D scenes from multi-vie

applicationsarxiv-cs-cv

Gradient Regularized Newton Boosting Trees with Global Convergence

arXiv:2605.00581v1 Announce Type: cross Abstract: Gradient Boosting Decision Trees (GBDTs) dominate tabular machine learning, with modern implementations like XGBoost, LightGBM, and CatBoost being bas

High-Probability Convergence in Decentralized Stochastic Optimization with Gradient Tracking

model-releasesarxiv-cs-lg

arXiv:2605.00281v1 Announce Type: new Abstract: We study high-probability (HP) convergence guarantees in decentralized stochastic optimization, where multiple agents collaborate to jointly train a mod

How Well Does GPT-4o Understand Vision? Evaluating Multimodal Foundation Models on Standard Computer Vision Tasks

arXiv:2507.01955v3 Announce Type: replace Abstract: Multimodal foundation models (MFMs), such as GPT-4o, have recently made remarkable progress. However, their detailed visual understanding beyond que

Human-in-the-Loop Meta Bayesian Optimization for Fusion Energy and Scientific Applications

arXiv:2605.00068v1 Announce Type: new Abstract: Inertial Confinement Fusion (ICF) holds transformative promise for sustainable, near-limitless clean energy, yet remains constrained by prohibitively hi

Industry

I want to tell you the story of a young woman who you have probably never heard of. Her name is Mary Anne. She was born on a remote island i…

I want to tell you the story of a young woman who you have probably never heard of. Her name is Mary Anne. She was born on a remote island in Scotland, where life was harsh and unforgiving. On May 2,

industryelon-musk--x

Information-geometric adaptive sampling for graph diffusion

arXiv:2605.00250v1 Announce Type: cross Abstract: Standard diffusion models for graph generation typically rely on uniform time-stepping, an approach that overlooks the non-homogeneous dynamics of dis

Safety

InpaintSLat: Inpainting Structured 3D Latents via Initial Noise Optimization

arXiv:2605.00664v1 Announce Type: new Abstract: We present a training-free approach for controllable 3D inpainting based on initial noise optimization. In the structured 3D latent diffusion framework,

safetyarxiv-cs-cv

Introducing nanowhale 🐳! A tiny DeepSeek model fully pretrained by an agent. Inspired by @karpathy's nanochat, we gave ml-intern the task o…

model-releasesclem-delangue--x

Introducing nanowhale 🐳! A tiny DeepSeek model fully pretrained by an agent. Inspired by @karpathy's nanochat, we gave ml-intern the task of training a tiny MoE with all the architectural advancements

Introducing WARM-VR: Benchmark Dataset for Multimodal Wearable Affect Recognition in Virtual Reality

model-releasesarxiv-cs-lg

arXiv:2605.00184v1 Announce Type: new Abstract: With the growing integration of human-computer interaction into everyday life, advances in machine learning have enabled systems to better perceive and

Koopman-Assisted Reinforcement Learning

arXiv:2403.02290v2 Announce Type: replace-cross Abstract: The Bellman equation and its continuous form, the Hamilton-Jacobi-Bellman equation, are ubiquitous in reinforcement learning and control theor

Last-Iterate Analyses of FTRL with the 1/2-Tsallis Entropy in Stochastic Bandits

arXiv:2510.22819v2 Announce Type: replace Abstract: The convergence analysis of online learning algorithms is central to machine learning theory, where the last-iterate convergence is particularly imp

Safety

Learn where to Click from Yourself: On-Policy Self-Distillation for GUI Grounding

arXiv:2605.00642v1 Announce Type: cross Abstract: Graphical User Interface (GUI) grounding maps natural language instructions to the visual coordinates of target elements and serves as a core capabili

safetyarxiv-cs-cv

Lightweight Domain Adaptation of a Large Language Model for Legal Assistance in the Indian Context

arXiv:2505.22003v2 Announce Type: replace Abstract: In India, access to legal assistance for the general public has been observed to have a critical gap, as many citizens are not able to take full adv

Applications

LIMSSR: LLM-Driven Sequence-to-Score Reasoning under Training-Time Incomplete Multimodal Observations

arXiv:2605.00434v1 Announce Type: new Abstract: Real-world multimodal learning is often hindered by missing modalities. While Incomplete Multimodal Learning (IML) has gained traction, existing methods

applicationsarxiv-cs-cv

LLM-Oriented Information Retrieval: A Denoising-First Perspective

arXiv:2605.00505v1 Announce Type: cross Abstract: Modern information retrieval (IR) is no longer consumed primarily by humans but increasingly by large language models (LLMs) via retrieval-augmented g

Agents

Memory in the LLM Era: Modular Architectures and Strategies in a Unified Framework

arXiv:2604.01707v2 Announce Type: replace Abstract: Memory emerges as the core module in the large language model (LLM)-based agents for long-horizon complex tasks (e.g., multi-turn dialogue, game pla

agentsarxiv-cs-cl

MMAudioReverbs: Video-Guided Acoustic Modeling for Dereverberation and Room Impulse Response Estimation

arXiv:2605.00431v1 Announce Type: cross Abstract: Although recent video-to-audio (V2A) models excelled at synthesizing semantically plausible sounds from visual inputs, they do not explicitly model ro

Safety

Model-Based Reinforcement Learning with Double Oracle Efficiency in Policy Optimization and Offline Estimation

arXiv:2605.00393v1 Announce Type: new Abstract: Reinforcement learning (RL) in large environments often suffers from severe computational bottlenecks, as conventional regret minimization algorithms re

safetyarxiv-cs-lg

Modeling Subjective Urban Perception with Human Gaze

arXiv:2605.00764v1 Announce Type: new Abstract: Urban perception describes how people subjectively evaluate urban environments, shaping how cities are experienced and understood. Existing computationa