AFast Robot Localization Method Based on Monte Carlo Sampling
Localization is an essential capability of intelligent robots. However, in real-world constrained environments, robots often cannot rely on external localization systems.
computer-vision
MLINFO COLLECTION
外観検査・欠陥検出
製品画像、顕微鏡画像、表面欠陥を対象に、分類・検出・セグメンテーションを選ぶための導線です。
関連する論文・実装
26 / 50EditAgent: Rethinking Agentic Image Editing
Agentic image editors decompose complex requests into steps, but when a step fails, they mostly retry with the same narrow set of tools and a judge that scores each output by eye directly. We argue…
computer-vision
Comprehensive empirical evaluation of feature extractors in computer vision
Feature detection and matching are fundamental components in computer vision, underpinning a broad spectrum of applications. This study offers a comprehensive evaluation of traditional feature…
deep-learning
The Cost of Working Memory in Streaming Mean Estimation
A streaming estimator must compute from the evidence that fits in memory. We determine when storing an accurate mean is easier than computing it.
computer-vision
Retaining Repair Hypotheses for Cost-Aware Execution
Several corrections of an executable model can fit the same observations while predicting different execution outcomes. We study a repair-to-execution interface that retains compatible finite guard…
computer-vision
CoToan: Executable Rules and a Representation Contract for Reproducible Game AI Evaluation
Game AI results are comparable only when different implementations expose the same decision problem. Yet seemingly minor representation choices can silently change that problem by altering action…
computer-vision
Unlimited OCR Works 2
Unlimited OCR ushers the era of long-horizon parsing, substantially mitigating the growth of working memory as document lengthens. However, as document length scales to hundreds of pages, the visual…
nlp
Online Dense Reinforcement Learning with Planning-Grounding Agent for UI Navigation on Live IOS Apps
While frontier vision-language models demonstrate strong capabilities in user interface (UI) navigation, their high inference costs prohibit everyday use. Conversely, smaller models trained via…
deep-learning
Pair-Dependent Judge Errors Change the Minimax Rate of Semantic Entropy
Semantic entropy, the entropy of the meanings among a language model's sampled answers, is estimated from the verdicts of a judge that declares pairs of answers equivalent or not, and automatic…
computer-vision
Learning Erasing Equal-Length Relational Pattern Languages in the Limit from Positive Data over Binary Alphabets
Relational pattern languages generalize Angluin's pattern languages by requiring the strings substituted for repeated occurrences of a variable to stand in a given relation, rather than to be…
computer-vision
CAPTURER: A Dexterous Aerial Manipulator for Dynamic and Precise Grasping across Diverse Environments
As a representative form of embodied robotic interaction, aerial grasping requires close coordination between the aerial platform and manipulator. Most existing systems perform aerial grasping with…
reinforcement-learning
Scaling Lean Theorem Proving for Real-World Code Verification
We present EasyProver, a Lean proving system built from recursive agents with isolated contexts, asynchronous search, parallel tactic probing, and an elastic elaboration service. Using an…
computer-vision
Echo: Scaling Visual Reinforcement Learning with Off-policy Experience
Scaling visual reinforcement learning (RL) with GPU-accelerated simulation is computationally expensive due to rendering and visual-policy inference costs. Consequently, two-stage teacher--student…
deep-learning
UCVE: Graph Structured Retrieval for Compliance Validation
Structured compliance validation requires determining whether every obligation in a predefined requirement space is satisfied, violated, or unaddressed by a given document. This can be described as a…
nlp
Doubly Robust Deep Kernel Tests for Structured Outcomes
We propose a test of whether two interventions induce the same outcome distribution when outcomes are structured and high-dimensional, such as images, text and graphs. We represent the interventional…
nlp
Vision-Language-Action or World-Action? Just Action Models
The vision-language-action (VLA) and world-action model (WAM) communities debate whether control policies should inherit pretrained knowledge from vision-language models or from visual generators.…
computer-vision
RynnWorld-Latent: A Cross-Embodiment World Model Conditioned on Universal Latent Actions
Learning controllable world dynamics from heterogeneous interaction videos is challenging because robot embodiments use incompatible action spaces, while human videos lack native control labels. We…
deep-learning
Seeing Through Distractions: Context-Stable Attribution via the Least Core
Shapley-value-based explanations are widely used for feature attribution in machine learning. However, in computer vision, a feature may reduce the target-class score when added to the complete…
nlp
Recertifying decisions via e-closure: uniform improvements of conformal risk control and randomized e-BH
Statistical procedures often control expected loss at a prescribed level while leaving part of their risk budget unused. Building on the e-value representation of risk-controlled decisions and the…
computer-vision
Macro Mondrian Conformal Risk Control
Conformal Risk Control (CRC) extends conformal prediction beyond the coverage setting to the control of general monotone loss functions, in a distribution-free and modelagnostic fashion. This makes…
deep-learning
RIDAR: Safeguarding Research Integrity in Autonomous Research Agents via Automated Detection and Runtime Intervention
Autonomous research agents are increasingly used to automate large portions of scientific research, yet they are prone to research integrity violations (RIVs): behaviors that compromise the validity,…
machine-learning
Program-Verified Self-Evolution for Vision-Language Models
Self-evolving vision-language models train on questions they generate from unlabeled images. Since these questions have no gold answers, prior methods label them by majority vote over sampled answers…
computer-vision
FDSML: Formula-Driven Supervised Metric Learning with Parameter-Aware Triplet Loss
Formula-Driven Supervised Learning (FDSL) enables vision pre-training without real images, but existing methods cast pre-training as classification on discretized labels, discarding continuity in the…
deep-learning
Exponential-Nemytskii Neural Operators: Learning Field Evolution Across Step Sizes
In variable-step operator learning, agreement at observed step sizes does not by itself determine predictions at other temporal resolutions. We propose an operator whose step-size dependence is…
computer-vision