MLINFO COLLECTION
過去の実験ノート、技術報告書、特許、論文を探しやすくするための製造業向けRAG導線です。
High linear decodability does not entail causal controllability in continuous-latent text-to-speech (TTS). In VoxCPM2, position-matched probes and equal-norm interventions across 30 speakers and 60…
Gaussian process upper confidence bound (GP-UCB) has been widely studied, though its known regret upper bound is suboptimal. To obtain near-optimal regret upper bounds, existing studies mainly focus…
Few-shot action recognition (FSAR) requires representations that expose discriminative motion dynamics from only a few labeled videos. Recent trajectory-based methods leverage long-term point tracks…
What is the round complexity of Hessian-similar optimization when each round can contact at most $s$ of $m$ clients? Prior rates permit a free master or full participation and do not characterize…
Small-molecule identification from tandem mass spectrometry (MS/MS) may require complementary measurements. Herein, we propose a structure-informed deep Q-network (SI-DQN) that uses existing MS/MS…
Large language models (LLMs) draw on parametric knowledge and retrieval-augmented generation (RAG) to solve knowledge-intensive tasks. Yet problem solving in unfamiliar domains calls for tightly…
Rubric-based rewards enable effective reinforcement learning on non-verifiable tasks. However, because these rewards are typically defined as a weighted measure of rubric coverage, models are trained…
Conditional generative models parameterized by triangular transport maps are widely used for conditional sampling, yet theoretical guarantees on the quality of the conditional measures they produce…
Clinical Question Answering (QA) underpins Clinical Intelligent Decision Support Systems, but progress is severely limited for low-resource languages such as Indonesian by the absence of public…
Multimodal sentiment analysis (MSA) aims to infer sentiment by integrating linguistic, acoustic, and visual information. However, many fusion methods integrate modality-specific representations and…
Graph anomaly detection (GAD) aims to identify irregular entities in graph-structured data, yet heterogeneous anomaly patterns and distributional differences across graphs challenge generalizable…
Vision-language-action (VLA) policies need to recognize gaps in their training knowledge to request useful demonstrations or assistance in new situations, especially when failures are costly.…
Retrieval-augmented generation can expose unwanted concepts through retrieved evidence even when the generator is moderated. We study query-side concept suppression with a fixed encoder and document…
ドキュメントを構造化するために使えるオープンソースのETLソリューション。
Spectroscopic diagnostics provide rich information for characterizing plasma states in tokamak fusion experiments, while existing learning-based approaches are often designed for individual tasks and…
Language models increasingly create 3D content through code, with practical workflows often relying on editing existing programs rather than regenerating them, for speed and precise control. Such…
Understanding how language models were pretrained requires information about their data, processing procedures, and computational resources. However, it remains unclear whether successive releases…
Coverage-evaluation benchmarks quantify whether retrieved evidence covers the different pieces of information needed to satisfy an information need. Existing benchmarks mostly consider factual claims…
We propose Nemotron-Labs-Diffusion-Uni (NLD-Uni), a unified discrete diffusion large language model (DLLM) for visual understanding and generation tasks. Compared with prior unified diffusion models,…
Chemical AI workflows routinely represent the same molecule through multiple co-referring identifiers, including trivial names, IUPAC names, and SMILES, implicitly assuming that these representations…
Voice style conversion (VSC) aims to transform a source utterance to match the timbre, accent, and emotion of a target voice while preserving linguistic content. StyleStream 1.0 introduced the first…
Tool-using voice agents often leave users waiting after speech ends, even when actionable information arrives earlier in the request. Speculative approaches begin work during speech, but…
Financial agents must form forecasts and investment judgments from decision-time evidence, with predictions evaluated against subsequent outcomes. Existing benchmarks assess financial knowledge,…
Despite rapid advances in large language models (LLMs), their deployment in the sports and health domain remains high-risk due to the absence of domain-specific evaluation benchmarks. Existing…