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。
Monocular models recover 3D geometry from a single image in one pass, but most assume a pinhole camera and produce distorted geometry on the wide-angle imagery produced by fisheye and panoramic…
Video object removal and injection are reciprocal editing operations between object-present and object-absent video states, yet they differ substantially in training difficulty. Removal can be…
Vision-Language-Action (VLA) models can perform diverse manipulation tasks directly from visual observations and natural language instructions, but they remain prone to mistakes and unpredictable…
Accuracy on medical examinations is common evidence offered for the clinical use of language models, yet a health system that intends to run an open model on its own hardware needs to know…
Recognizing task completion and failure enables robots to stop upon success and initiate recovery or replanning after failure. Existing methods augment Vision Language Action (VLA) policies with task…
Understanding catastrophic forgetting, in which learning new tasks degrades performance on previously learned tasks, remains a fundamental challenge in continual learning (CL). Existing theoretical…
Privacy auditing empirically assesses privacy leakage by using membership inference attacks to establish lower bounds on privacy loss. We consider an observational auditing setting in which the…
Synthetic biparametric MRI (bpMRI) may help alleviate the limited availability of large and representative prostate MRI datasets for deep learning applications. In this work, we present a conditional…
Open-vocabulary 3D semantic maps have emerged as a key spatial memory representation for long-horizon robot autonomy, enabling robots to reason about objects, their spatial relationships, and past…
Many questions about a video concern one physical object. Where does the ball end up after the cups are shuffled?
KV cache compression for multimodal LLMs usually selects the visual tokens to keep once, at prefill, and reuses that selection for the whole generation. We show that this one-shot selection is…
Agentic robot systems combine language-model reasoning with robot policies to monitor execution and recover from failures. However, reviewing every action chunk incurs substantial overhead, even in…
Vision-language-action (VLA) models have become an important paradigm for robotic manipulation by unifying visual perception, language understanding, and action generation. Since reliable…
With the growth of scientific output, the peer review system is approaching a breaking point: reviewers are increasingly hard to secure, and turnaround times lengthen accordingly. LLM-assisted or…
Computer-use agents increasingly handle private information and act on users' behalf across desktop and web applications, including email. Phishing therefore poses privacy and security risks that…
Visual document understanding is essential for acquiring knowledge from visually rich documents and is attracting growing research interest. Existing surveys emphasize architectures or technical…
Local feature matching is typically formulated for image pairs, although structure-from-motion and visual localization commonly match one reference image against many retrieved or covisible…
Exoskeletons have shown great potential for augmenting human physical capabilities, yet generating reliable assistance remains challenging because human motion patterns and interaction requirements…
Online semantic 3D Gaussian Splatting (3DGS) enables open-vocabulary scene understanding from streaming observations. However, existing methods recover geometric context missing from image-derived…
Long egocentric videos pose a central challenge for multimodal language models: the visual stream must be compressed into a memory representation that can be searched efficiently while still…
Training-free personalization adapts a frozen vision-language model (VLM) to recognize user-defined concepts from only a few exemplars by retrieving concept entries at inference time. While recent…
Transformer-based models have shown strong performance across diverse tasks, but their reliance on self-attention mechanisms often leads to high computational costs. Token sparsification, which…
Real-time polyp segmentation in computer-assisted colonoscopy is hampered by the difficulty of deploying high-accuracy models under strict latency budgets. Frame skipping, which performs inference…
We envision a general-purpose protein foundation model as a unified, interactive model of sequence, structure, and function, capable of understanding, generation, and cross-modal translation while…