MLINFO COLLECTION
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。
Compact chest X-ray (CXR) models that localize findings suit deployment, but box annotations are limited and report-aware multimodal models are expensive at inference. We introduce APED-CXR, which…
We present SpatialDex, a framework that learns 3D-grounded bimanual dexterity from RGB-only human videos through reconstruction-augmented visuomotor pre-training. The central idea is to learn human…
Multimodal large language models (MLLMs) show promising reasoning capabilities, but reliable physical interaction requires planning that accounts for when actions are executable and how they change…
During steady pouring, images and robot pose may remain nearly unchanged while transferred mass accumulates, making the return decision ambiguous for a whole-task vision-language-action (VLA) policy.…
Pixel language models process text as rendered images instead of a finite vocabulary, which gives them strong cross-lingual transfer abilities. However, not much is known about how these abilities…
As social agents become embedded in human relationships, they are expected not only to provide smooth assistance but also to handle rejection, discomfort, jealousy, persistence, and other forms of…
Object detection models for autonomous driving commonly experience substantial performance drops when deployed under adverse weather due to the domain shift between training data and real-world…
Edge medical segmentation must reconcile small model size, high accuracy, and fast inference. TernScope addresses this tradeoff through model--hardware co-design, learning a compact segmentation…
Perceptive locomotion policies typically observe a dense robot-centric elevation map, although only the terrain beneath and around the next footsteps informs the control decision. Learned encoders…
Despite the success of foundation models in image synthesis, achieving fine-grained spatial control remains a significant challenge, typically requiring auxiliary structural adapters or complex…
Existing paired clean-degraded datasets have advanced learning-based underwater image enhancement, but they remain either limited in scale or difficult to acquire, and still fail to adequately cover…
Fine-grained multimodal intelligence requires models to both understand a designated region and localize it from language. Existing methods learn these directions with separate objectives and…
In this report, we introduce pplx-embed-v2-late, a pair of 0.6B and 9B multilingual and multimodal late-interaction models. Both models achieve state-of-the-art results within their respective size…
Curriculum learning orders samples by difficulty, but difficulty alone does not establish supervision reliability for dense prediction. Easy samples can expose shortcuts, hard samples can be…
High-fidelity 4D physical simulation requires accurate physical parameter assignments that align with diverse material properties. Previous methods struggle with critical bottlenecks: they either…
We propose a new generative modeling framework grounded in forward-backward partial differential equations (PDEs). These equations arise naturally in mean-field game (MFG) theory, and are closely…
Recent advances in generative models have enabled highly realistic face forgeries, yet generalizing deepfake detectors to unseen manipulation pipelines remains a major challenge. One critical yet…
A question about a whole-slide image rarely names every morphological finding needed to answer it. Question-guided patch selection can therefore overlook supporting morphology, while slide-level…
Text-to-image generation models do not explicitly receive the syntactic structure of the prompt, i.e., which word modifies which and where each phrase attaches. Consequently, they often struggle to…
Promptable segmentation models such as SAM 3 achieve remarkable open-vocabulary performance but require dedicated architectures, large-scale annotation engines, and task-specific training. We ask a…
Stance classifiers make errors that can be costly to identify under limited human-review budgets. Prioritizing potentially incorrect predictions remains challenging, particularly across heterogeneous…
Knowledge graph question generation (KGQG) generates natural-language questions from structured graph evidence and a target answer. When the input graph is temporal, a valid question must also…
Long-horizon robot manipulation requires a robot to remember task-relevant information beyond its short observation window. Existing memory-augmented policies typically retrieve relevant information…
Accurate localization of neonatal hypoxic--ischemic encephalopathy (HIE) lesions on apparent diffusion coefficient (ADC) images is clinically important but is limited by scarce expert annotations and…