MLINFO COLLECTION
樹脂、電池、触媒、合金などの配合・組成を、少ない実験回数で改善するためのAI/MI導線です。
Retargeting human motion to humanoids requires preserving motion semantics while accounting for the robot's physical constraints. Kinematic pipelines prescribe a robot trajectory through geometric…
Scientific inference often involves observations from multiple latent populations whose class memberships are uncertain and must be inferred from available data. While full Bayesian mixture modelling…
Semi-implicit variational inference (SIVI) expands the representational capacity of variational families, but optimizing the Evidence Lower Bound (ELBO) remains challenging because the marginal score…
Diffusion models can sometimes reproduce examples from their training data, a phenomenon known as memorization. Existing memorization detection methods for unconditional diffusion models typically…
Estimating neural scaling laws involves an end-to-end pipeline: designing a scaling recipe, training models across scales, evaluating models on a target metric, and deploying an algorithm to fit a…
Within the broader landscape of artificial intelligence architectures, this paper introduces a compact, edge-centric neural framework that resolves the computational bottlenecks of modern…
Most analyses of neural representations focus on trained endpoints, leaving the process by which internal structure forms comparatively unmeasured. We instead treat representation formation itself as…
Bayesian mixtures, and Solomonoff induction in particular, provide an idealized model of prediction learned by minimizing population log loss, and they underlie universal agents such as AIXI. An…
There is growing evidence that the performance of a neural network depends largely on a small subset of its weights, which are typically identified by training a dense network and pruning it…
Hybrid forecasting systems combining machine learning and numerical weather prediction offer a promising route toward improved forecast skill while preserving physical consistency. In this study, we…
We consider online monitoring of an AI system that produces a sequence of decisions. At each round, the system outputs a proposed decision together with a confidence score estimating the…
Auditing whether a text-to-image (T2I) model was fine-tuned on a particular image collection is difficult: a model can absorb collection-level visual characteristics without reproducing training…
Feed-forward models accurately estimate camera motion and 3D geometry from short video windows. However, computational and memory costs prevent direct inference on sequences containing thousands of…
Tasks such as quadrotor dynamic-gate racing require agents to anticipate external motion while maintaining precise high-frequency control. World-model-based reinforcement learning provides a natural…
Understanding catastrophic forgetting, in which learning new tasks degrades performance on previously learned tasks, remains a fundamental challenge in continual learning (CL). Existing theoretical…
Vector quantization (VQ), in particular lattice-based methods, offer strong rate-distortion trade-offs for low-bit large language models (LLMs), yet their behavior under quantization-aware training…
Probabilistic computing has proved useful for combinatorial optimization, but conventional implementations rely on binary stochastic units and sigmoid-based updates. Extending these systems to…
Memory enables language model assistants to maintain continuity across sessions and generate personalized responses, but knowing more about a user does not necessarily produce responses they prefer.…
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…
Reward models score responses for preference optimization, filtering and ranking, and pooling scores across prompts needs them to be comparable. Yet pairwise evaluation compares two responses to the…
Generative modeling for Computer-Aided Design (CAD) remains fundamentally challenged by the need to capture the intricate interplay between discrete topological connectivity and precise spatial…
Offline contextual pricing often relies on logged observational data, but faces challenges from distributional shifts between training and deployment environments. Distributionally robust…
Sub-hourly dispatch, balancing, and storage control increasingly depend on forecasts that anticipate rapid variability in solar generation. Accurate sky-image-based irradiance forecasting requires a…
Just as different languages express the same concept through different words, neural networks express similar functions through incompatible coordinate systems. Different architectures, random…