MLINFO COLLECTION
日次更新の新着・公開記事を新しい順に掲載しています。
Vision-language models can get individual judgments right while struggling to recover and consistently use the exact properties of a 3D object. To characterize this gap, we introduce BedBench, a…
One-step and few-step text-to-image generation must accurately render the details specified in the prompt despite limited opportunities for refinement. Distribution matching distillation (DMD) uses…
Progress toward artificial general intelligence (AGI) has largely relied on scaling a resource-intensive executive, System-2, through larger models, more data and compute, longer reasoning, and more…
Multimodal large language models can recognize visual content yet struggle to reason reliably over it across multiple steps. In counting, a model may see all objects but lose track of which ones it…
We present Youtu-Parsing-Omni, an omni-modal parser that converts documents, images, audio, and video into structured records grounded in space and time, providing a perception layer for agents that…
Autoregressive (AR) image generators are powerful in principle but inflexible in practice: training with a fixed raster-scan order hardcodes a single factorization of the image distribution into the…
Human cognition flexibly draws on a shared perceptual foundation to understand environments, attend to referenced entities, reason about spatial relationships, and act. Endowing aerial robots with an…
Predicting future physical states stands as a central challenge in embodied intelligence. Existing video world models leave 3D dynamics implicit, action-based formulations remain tied to specific…
An effective agent memory system should adapt to a user's history and task requirements. Human-annotated supervision can guide this adaptation by providing feedback for evaluating and improving…
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…
Proactive agents must decide whether, when, and how far to assist without an explicit request. Existing evaluations often rely on automated scores or binary verdicts, offering limited human diagnosis…
この論文では、予測性維护と健康管理のための大型言語モデルが使用されます。この modelは、故障診断や寿命予測などの問題を解決するように設計されています。
语言サーバーの開発に使用するライブラリを紹介している。
AIエージェントを組み立てるためのライブラリ。
Gymnasiumは、シングルエージェントRLの疑似環境を提供するAPIです。
CLIPという画像認識モデルをオープンソースとして実装したライブラリ。
NestJSベースのAIチャットボット開発ツールです。
Pythonで使えるマシンラーニングライブラリを紹介している。
Content aware image resize library
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。
Although contrast-enhanced (CE) breast MRI is an important tool for cancer detection, intravenous gadolinium administration introduces additional considerations for patients and clinical workflows.…
Image composition labels such as center, diagonal, or rule of thirds describe visual structure rather than object categories. KU-PCP provides image-level labels and class-specific geometric elements,…
Many automated decisions in education involve choosing from a fixed set of options: assigning a rubric score, checking whether an answer meets a marking criterion, or identifying the first wrong step…
Low-precision training reduces computation but introduces additional rounding error. We theoretically study how stochastic rounding (SR) affects prediction risk as model size, training time, and…