MLINFO COLLECTION
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。
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…
Statistical downscaling is the task of reconstructing high-resolution meteorological fields from coarse inputs. A principled approach formulates downscaling as a Bayesian inverse problem, using a…
Computer-use agents plan on a screenshot for several seconds and then click at a position on the screen; if the page has changed in the meantime, the click lands on an unintended element. Prior work…
Reinforcement learning with verifiable rewards (RLVR) has become a powerful tool for improving multimodal reasoning. However, standard outcome supervision suffers from credit assignment ambiguity, as…
Edited endpoint images make the target of an image-to-video transition explicit and can improve transition completion, but also preserve context in the source image's layout. Full-frame endpoint…
Vision-language models (VLMs) increasingly process multiple views of the same scene, but it remains unclear whether they integrate these observations into a coherent scene-level representation.…
Post-training quantization (PTQ) reduces the memory footprint of vision-language-action (VLA) models, but lowering bit widths while maintaining task performance remains challenging. Existing work has…
Sparse-view cone-beam computed tomography is widely used for fast, low-dose volumetric imaging and lesion localization in dentistry and image-guided interventions, but it introduces severe artifacts.…
Large vision-language models (LVLMs) represent images and videos as long visual-token sequences, substantially increasing inference costs. These costs motivate visual-token pruning, whose…
Time-series forecasters are ranked almost entirely by accuracy metrics, but a forecast's decision value, its effect on the downstream decision, need not track accuracy and is rarely measured. This…
Data augmentation improves visual recognition by exposing models to synthetic training examples that encourage generalization beyond the observed data. Mixed-sample methods extend this idea by…
We present RESPLE2, a recursive multi-sensor state estimation framework using non-uniform B-splines for 6-DoF motion representation. By exploiting the knot-clamping boundary property, we propose a…
World-action models (WAMs) incorporate the prediction of future observations into robot policy learning. However, most WAMs build on billion-parameter vision-language or video-generation backbones,…
Embedding-level scaling expands the capacity of language models through lookup-based memory rather than by increasing model depth, width, or dense computation. Extending this idea to vision-language…
Prediction models degrade when the deployment population differs from the one used to train them, and training data cannot say which feature-response relationships will transfer. Expert elicitation…
Computationally expensive simulations and real-world observations often provide data at a lower temporal resolution than downstream tasks require. Averaging observations at fixed grid points can…
Time Series Foundation Models have demonstrated that pretraining on diverse datasets enables effective transfer to new forecasting tasks. Classical methods like ARIMA, however, remain configured and…
Chain-of-thought (CoT) monitoring aims to detect potentially harmful behaviors in large language models (LLMs) from their CoTs. Intervention-based evaluations measure this property by asking whether…
Controllable 3D part generation is pivotal for digital asset creation, yet existing methods lack the flexibility to accommodate diverse user workflows requiring varying levels of control. In this…
Large language models have shown outstanding performance on text-first tasks such as coding, math, and writing. Recent efforts are shifting models' training to include scientific problems that often…
Local anomaly detection is the task of identifying spatially confined anomalous or out-of-distribution (OOD) regions within an otherwise in-distribution (ID) image. Most existing methods are designed…
Vision-Language Models (VLMs) have shown strong potential for video anomaly detection, but dense frame-level inference makes them impractical for real-time deployment. Existing acceleration commonly…
Recognizing facial expressions in unconstrained video suffers from two coupled problems: self-attention grows quadratically in cost with clip length, and crowdsourced labels are noisy. We present…
The scarcity of positive cases remains a major bottleneck in developing automated diagnostic systems for fetal Congenital Heart Defects~(CHDs), particularly for rare subtypes. Although normal cases…