tesseract — Tesseract Open Source OCR Engine (main repository)
Open Source Computer Vision Libraryは、画像やビデオを分析するためのライブラリです。
文字認識
MLINFO COLLECTION
新着記事
日次更新の新着・公開記事を新しい順に掲載しています。
記事一覧
28 / 125spleeter — Deezer source separation library including pretrained models.
この研究では、重症看護病棟内の気流と光など環境要因が気性変化の予測に利用できるか検討した。その結果、日照時間と音圧レベルを考慮すると、気性変化の予測精度が向上した。
病院での医療対策に関するリスクの予測
awesome-production-machine-learning — A curated list of awesome open source libraries to deploy, monitor, version and scale your machine learning
マシンラーニングを実装するために使用するライブラリを紹介している。
マシンラーニングの実装
OpenEBFM — Open-source code for training and scaling up energy-based foundation models.
Open-source code for training and scaling up energy-based foundation models.
nlp
FastGen — NVIDIA FastGen: Fast Generation from Diffusion Models
この論文では、ディフュージョンモデルの高速化を目的としたNVIDIA FastGenについて説明しています。FastGenは、ディフュージョンモデルから高速に生成することが可能です。
ディフュージョンモデルの高速化
Closed Gates Leak: Decomposing Adjacent-Layer Cancellation in Gated Language Models
In transformer language models with gated multilayer perceptrons (MLPs), adjacent layers write partly against each other into the residual stream. Previous work interpreted this cancellation as…
deep-learning
Tabular foundation models are not a shortcut to calibrated clinical risk prediction: a pre-registered simulation against the true risk
Tabular foundation models are pretrained networks that predict risk from a table without fitting a model. Whether their risks are correct (calibrated) has been judged on real data, where true risk is…
nlp
HEARSAYBENCH: Can AI Navigate from Abstract Human Rights to Lived Lives?
As large language models (LLMs) reach users worldwide, personal counseling has emerged as one of their most consequential applications, sometimes in life-critical situations. Yet broader access does…
nlp
Tracing the Influence of Retrieved Literature on Scientific Ideation in LLMs
Large language models (LLMs) are increasingly used to generate research ideas from scientific literature. Existing systems combine literature retrieval with search, generation, and refinement, making…
nlp
When Does Closed-Loop Curriculum Adaptation Help GRPO? An Analysis on Countdown
Reinforcement fine-tuning has become an effective post-training paradigm for improving the reasoning ability of large language models, but it remains sample-inefficient when the training distribution…
deep-learning
Controlling Continuum Robot Shape in Enclosed Space with Embedded Sensing using IMU and Actuator Feedback
Controlling continuum robots' shape to operate in confined, enclosed environments is challenging, since it cannot rely on external observation. Existing embedded shape sensing methods, although they…
computer-vision
Robotic Data Inoculation
Modern robot learning systems feed on high-quality demonstration data, and their performance hinges on coverage. Without good coverage, small errors compound and the policy can quickly go into…
nlp
BASILISC: Bayesian Alignment of Siamese-Integrated Latents for Inferring Single-cell Correspondence
Single-cell assays study the genome one cell at a time. Unimodal assays measure one molecular layer, the newer multimodal assays measure several.
computer-vision
Reinforcement Learning for the Game of Balatro: A Fast Simulator and Two-Policy Training Approach
Balatro, a 2024 roguelike deckbuilder, presents three difficulties that have historically derailed reinforcement learning methods: a 3,000-action state-dependent action space, horizons of several…
computer-vision
When Should AI Decide, Defer, and Deviate? Responsible Automation for Deceased Donor Kidney Allocation
We ask when an AI trained on historical decisions should be allowed to recommend decisions, defer to human experts, or in other cases, flag concerning patterns in data and deviate from past practice.…
generative-ai
Catch It All!: Generalizable Dynamic Catching with a Dexterous Hand
Catching arbitrary objects requires generalization to novel projectiles and real-time adaptation to unpredictable contact dynamics under noisy visual observations. This paper presents Catch It All!,…
nlp
Modular Bayesian Foundation Models: Bayesian time series encoders for OOD detection, routing and forecasting
Industrial systems continuously generate time series that vary in sampling frequency, scale, dynamics, and operating regime. Consequently a single time-series foundation model may not be able to…
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
LightGenBench: A Benchmark for 3D Emission Generation
Recent generation methods produce 3D assets with detailed geometry and rich textures. However, these assets are non-emissive: they reflect light but emit none.
computer-vision
FairSplit: Decomposing the Embedding Space for Fair Classification
Fair classification faces a twofold challenge: maintaining high classification accuracy while limiting reliance on sensitive information. Our method FairSplit achieves this by learning a…
deep-learning
MCCL: Training Pytorch models across a fleet of Macs at Skywalker Sound
Skywalker Sound, a premier audio post-production facility, operates more than 200 M4 Max Mac Studios on a 10Gb Ethernet network. When not in use by artists, these machines sit idle, representing…
deep-learning
Representation Complexity Along Learning Trajectories: Trading Width for Precision and Time
What computational role does overparameterisation play during learning? Information-plane analyses suggest that neural networks can traverse representations substantially more complex than those…
computer-vision
Distilling the Shape of Uncertainty: What On-Policy Distillation Learns and How to Predict It
On-policy distillation (OPD) is increasingly adopted in the post-training of large language models. However, a stronger teacher may fail to improve the student.
deep-learning
Author-Informed Stance Detection: A Dataset and Findings
Stance detection in social media is challenging, as interpreting a text often requires understanding the author's perspective. We re-frame political stance detection as an author-informed text…
nlp