MLINFO COLLECTION
日次更新の新着・公開記事を新しい順に掲載しています。
In this paper, we formulate clustering analysis as discrete generative modeling. Specifically, when the generator is restricted to a finite candidate space, the generated samples naturally emerge as…
Serving and fine-tuning a large language model on the same GPUs can turn the idle capacity between inference bursts into training progress, and low-rank adaptation (LoRA) makes this co-location cheap…
On-device language models can learn a user's preferences through adapters trained on private data. However, a base-model upgrade may change the layers or vocabulary, leaving the personal adapter…
Industrial computational fluid dynamics (CFD) becomes costly when complex geometries, long transients and coupled physics must be evaluated across large design spaces. We introduce FastAgent, a…
LLM research-ideation systems aim for hypotheses that are both true and non-obvious, yet neither property can normally be checked. We build a testbed in which both can.
Distributed support vector machine (SVM) learning is challenging under heterogeneous local data and limited communication. We develop a Representative Learning framework based on Lifted Empirical…
Mechanistic interpretability (MI) explains a computation in a trained network by identifying the components and variables that implement it and testing them with interventions. Singular learning…
Electrochemistry is central to solving many modern-day challenges, including energy storage systems for a sustainable future, and its advancement relies heavily on the data from past findings.…
Primal-dual methods enforce safety constraints in reinforcement learning through Lagrangian relaxation. For a fixed policy, the exact bounded multiplier response exhibits bang-bang switching at the…
Data-driven control in radio access networks (RANs) selects resource allocations using associations between control actions and key performance indicators (KPIs) learned from network telemetry.…
A robot's next action can depend on recent motion or earlier visual evidence absent from its current observation. A recurrent visual-memory architecture can retain this history in a visual state, but…
Using large language models to interpret experimental evidence, design discriminating experiments and formulate well-supported mechanistic explanations remains a central challenge in materials…
Post-training quantization (PTQ) reduces the com putational cost of large language models (LLMs), but it can introduce internal structural and behavioral changes that are not captured by traditional…
Extracting knowledge from large databases of experimental materials data requires repeated analyses and reusable records of their choices and results. We developed Multi-Agentic AI (MAA), a…
Accelerating modern foundational models has pushed domain-specific compilers toward increasingly complex, multi-tiered optimization pipelines. However, this heavy optimization focus introduces…
Automated configuration of mixed-integer programming (MIP) solvers largely relies on black-box optimization. Each trial requires an expensive solver run and provides only a scalar outcome, so tuning…
A central obstacle in realizing color center cavity-QED-based quantum technologies is inhomogeneity, or disorder, among individual emitters. As the number of emitters increases, so does the…
Transient thermal fields during solidification connect casting process conditions and cooling behaviour to the formation of defect-prone regions in aluminum cast ings. Repeatedly solving this thermal…
Inference-time scaling enhances a model's reasoning by extending its chain-of-thought (CoT). However, existing approaches typically rely on a single policy trained with outcome-reward reinforcement…
The MetaFine Open Competition (RoboFineMani workshop, CoRL 2026) evaluates fine-grained manipulation beyond binary success. Its five simulated tasks, from grasping a bottle by an instructed part to…
Electrocardiograms (ECGs) may contain physiological information related to hereditary cancer susceptibility, but its relationship with future cancer risk remains unclear. Here, we present ECG2Gene, a…
State of the art latent dynamics world models achieve impressive performance for robot planning. But do they actually encode the physics of the world?
Natural-language driven smart home control remains challenging: cloud-hosted Large Language Models (LLMs) raise privacy concerns, while local Small Language Models (SLMs) can generate invalid actions…
Vision-language model (VLM) unlearning is often treated as an objective-design problem: given multimodal forget data, the goal is to optimize a loss that removes undesirable behavior while preserving…