Spectral-Spatial Interpretation
Post-hoc image explanations usually show where a model looks using spatial heatmaps or indicate which channels matter using global channel scores. These separate views are limiting for multispectral…
nlp
MLINFO COLLECTION
製造業の異常検知
センサ時系列、画像検査、予測保全、異常スコアリングに使えるAI技術を整理します。
記事一覧
2 / 37The Trinity:Capability-Driven Recursive Self-Improvement for Multimodal Agents
Multimodal intelligence can be viewed as human-guided co-evolution between worlds and agents through interaction. However, scaling this process faces two bottlenecks: constructing heterogeneous,…
computer-vision
learnopencv — Learn OpenCV : C++ and Python Examples
OpenCVを用いて画像処理の学習方法を紹介している。
OpenCVの学習
HiSTEVE 1.0: Harnessing Human-Interface VLA Agents for Open-World Games
Building virtual embodied agents that operate in open-ended games like human players is a long-standing goal requiring both long-horizon autonomy and reliable native-interface control. As a…
nlp
dlib — A toolkit for making real world machine learning and data analysis applications in C++
機械学習とデータ分析のためのC++のツールキット。
機械学習ツールの提供
Hy-Nomas: Towards Free-form Interactive World Generation
Interactive world generation requires models to follow successive commands while preserving relevant history and action consequences. We present Hy-Nomas, a video world model with an 8B diffusion…
deep-learning
StreamVibe: Proactive Video Agents for Evolving User Intent
Vision-language models are shifting from offline passive understanding toward online proactive interaction. However, prevailing methods largely rely on explicit requests while miss the implicit user…
computer-vision
OpenWorldLib — Unified Codebase for Advanced World Models.
OpenWorldLibは、進化する世界モデルを提供する統一されたコードベースです。
世界モデルを提供する
Look Only When Needed: Certificate-Guided Visual Routing for Efficient Diffusion VLMs
Diffusion vision-language models (DVLMs) process their entire input at every denoising step. Since visual tokens make up 89-97% of this input on the benchmarks we study, most of the decoding…
deep-learning
Can Discrete Tokens Serve as Semantically Lossless Representations of Visual Signals?
Discrete visual tokens represent vision in a discrete form analogous to language, offering a native interface for multimodal modeling under a shared next-token prediction objective. However,…
deep-learning
Reading, Writing, Sharing, and Interacting with the World through Video
Video foundation models have advanced rapidly in understanding and generating visual sequences, while video world models seek to capture the underlying dynamics of the world they depict. Despite…
computer-vision
StreamEval: Evaluating Interactive Streaming Video Generation Models
As streaming video generation advances, enabling real-time interaction with generated video is becoming increasingly important. We introduce StreamEval, a unified benchmark for interactive streaming…
computer-vision
LociArt: A Unified Paradigm for Free-Style Local Video Stylization
Video stylization typically transforms entire scenes, while local artistic editing requires precise region--style association, spatial control, and temporal consistency. We introduce LociArt, a…
computer-vision
OmniShowcase: Omnidirectional Subject-Consistent Video Generation from Multi-View Images
Generating videos of a specific subject from a few reference images remains challenging when the camera reveals surfaces that are not visible in the input. Early subject-to-video (S2V) methods…
computer-vision
EmbodiedLab: Benchmarking Embodied Agents That Act to Know
Embodied agents are expected to accomplish real-world goals by deciding for themselves how and when to interact with their surroundings. For many such goals, changing the physical state of the world…
computer-vision
yolov5 — Ultralytics YOLOv5 in PyTorch for object detection, instance segmentation, classification, training, and export.
YOLOv5という物体検出アルゴリズムをPyTorchから他の言語に変換できるライブラリ。
物体検出
Skill^{infty}: Recursive Self-Improvement for Agent Skill Optimization
Recursive self-improvement (RSI), in which a system also improves the way it improves, is a long-standing aspiration on the path to AGI. Language agents increasingly store procedural knowledge in…
computer-vision
DISC: Domain-Integrated Similarity Cost for Time-Series Dataset
The growth of time-series datasets and foundation models has made dataset comparison a central part of time-series workflows. Assessing source-target transfer before model adaptation requires…
machine-learning
Papers-in-100-Lines-of-Code — Implementation of papers in 100 lines of code.
この作品は机械学習の論文を100行のコードで実装する方法について説明しています。
機械学習論文を100行のコードから実装する
Which Agent's Skill Should Change? Group-Relative Credit Assignment for Evolving Multi-Agent Teams
Cooperative language-model agents can improve without weight updates by revising reusable skills, but only if a shared team reward is traced to the responsible agent and skill. Existing methods…
computer-vision
insightface — State-of-the-art 2D and 3D Face Analysis Project
このプロジェクトは２Ｄおよび３Ｄ顔の分析を実現するための基盤プロジェクトであり、最先端の技術を導入して顔の分析を実現します。
面量認証
AV-FABLE: Audio-Visual Manipulation Forensics in Long-Form Videos
Localized AI manipulations in long-form videos often affect brief events within otherwise authentic content, making video-level classification insufficient for forensic analysis. Existing…
nlp
Cross-modal Steering Vectors Exist Across Both Image and Text Generation
Are concepts and mechanisms unified across modalities in current AI models, or instead implemented separately for each one? We operationalize this broad question of modality unification by studying…
nlp
What Outcome RL Buys: Finishing, Reliability, Rarely Reach
Outcome RL raises pass@1 but not pass@k at large k (Yue et al., 2025). But every pass@1 is scored under a token budget.
computer-vision