MLINFO COLLECTION
工程条件、原料ロット、検査値から品質指標や不良リスクを予測するための技術です。
Vector Symbolic Algebras project data structures into a hyperdimensional vector space through the application of their vector algebras to randomly generated atomic vector symbols and fractional power…
Physical Neural Networks (PNNs) introduce new opportunities for cloud continuum computing, but their outputs may be affected by noise, drift, delay, and incomplete reliability information. Existing…
Training state-of-the-art models increasingly requires learning from large, heterogeneous datasets whose examples vary in quality, domain relevance, and source of supervision.…
Protein classifiers are highly sensitive to evaluation protocol: random train/test splits induce phylogenetic leakage, allowing models to exploit taxon-specific correlations and substantially…
Neuro-symbolic (NeSy) predictors that supervise only the task label suffer from reasoning shortcuts: distinct concept mappings achieve the same maximum likelihood, leaving the recovered concepts…
Adding control to video generation often requires training, which demands additional computational resources, data, or architectural changes. We propose a training-free approach that utilizes…
The massively multilingual translation systems that now include Sicilian learned it from noisy, non-standardised web text. To obtain better translation quality, we redevelop the small neural machine…
LLMs are increasingly consulted for moral judgment. We aim to improve performance on such tasks by rewarding good arguments, on the premise that arguing well increases the likelihood of judging well.
Training Arabic large language models faces challenges from noisy web data, dialectal variation, and the high cost of continual pretraining (CPT). We introduce AQL-Lite (AQL: Arabic Quality…
End-to-end autonomous driving has achieved state-of-the-art performance on benchmarks and real-world deployments. Its standard training recipe, however, is expensive across all existing paradigms:…
We introduce EgoHand, a monocular 3D hand reconstruction model that achieves state-of-the-art performance on egocentric video. Central to our approach is the curation of a high-quality training…
Video world models predict future frames from past frames and actions. They serve as simulators in which agents train, plan or are evaluated, and that humans can control interactively.
Today's multimodal assistants are typically prompted to interpret the visual evidence presented to them. To offload the cognitive burden of remembering across long horizons, wearable assistants…
Increasing the attention context length significantly improves streaming video generation quality, while incurring prohibitive memory and computational costs as the context grows. Existing methods…
Language 3D Gaussian Splatting enables open-vocabulary scene understanding by associating Gaussian primitives with language features. These semantic attributes increase model storage, while most…
Training generative models on synthetic data causes loss of diversity and a decrease in performance, a phenomenon known as model collapse. We study this degeneration spectrally in a controlled Markov…
Accuracy alone gives little information about which features or model components improve probabilistic fit, which outcomes benefit, or how fit changes during training. We introduce the InterModel…
A benchmark is not merely a collection of test questions; it naturally induces an empirical measure over difficulty. In this work, we develop this measure-based view of benchmark evaluation.
Diffusion-based video generation models (VGMs) can produce visually plausible videos, yet their camera ego-motion often drifts over long horizons. Camera ego-motion determines how the viewpoint…
Code-switching is a natural linguistic phenomenon, yet its impact on high-level reasoning tasks remains largely unexplored in under-resourced languages like Romanian. Natural language processing…
Reliable uncertainty estimation is important across visual recognition tasks, providing information about the confidence and reliability of model predictions. Many uncertainty estimation methods…
Movement primitives commonly represent robot mo- tions through basis functions indexed by time or phase. Inspired by spacetime representations employed in physics, we propose a spline-based…
This paper presents a novel strategy for UAV detection through visible (RGB) and infrared (IR) fusion, in order to improve accuracy and precision in harsh environments and weather conditions. In this…
Understanding and modeling light transport in human-centric scenes is a longstanding challenge. While recent progress in diffusion models has boosted research in relighting, precise illumination…