MLINFO COLLECTION
検索拡張生成、文書検索、社内ナレッジQAに関係する論文・実装をまとめます。
An AI system can produce more economically valuable work while delivering less value for the energy it consumes. We therefore ask: How much economic value does an AI system create per unit of energy…
Trained network weights are increasingly treated as data, but there is rarely ground truth about what a population of models should encode, which hampers systematic validation of weight-space…
We study episodic linear Markov decision processes with unknown transitions, adversarial losses, and bandit feedback. The state-of-the-art result for this setting (Liu et al., 2024) either achieves…
Lunar rovers will primarily rely on cameras for localization until navigation satellite services are deployed, and will continue to need them afterwards for relative navigation, hazard detection, and…
Representation learning has substantially improved the efficiency of unconstrained continuous-state Markov Decision Processes (MDPs), but its extension to Constrained MDPs (CMDPs) is difficult…
Modern autonomous Cyber-Physical Systems (CPSs), such as self-driving cars, operate in increasingly complex environments while expected to maintain high reliability. The black-box nature of many of…
Wrist photoplethysmography (PPG) heart rate estimates are vulnerable to motion artifacts, and corrections that reduce mean error can worsen individual windows. We propose an agent architecture with…
Hybrid retrieval, which fuses a sparse lexical retriever with a dense neural one, is widely recommended in the software documentation surveyed in September 2026, usually with reciprocal rank fusion…
A digital twin (DT) for type 1 diabetes (T1D) can predict how an individual's blood glucose will respond to different insulin treatments without actually trying them. For each treatment, downstream…
Formula-Driven Supervised Learning (FDSL) enables vision pre-training without real images, but existing methods cast pre-training as classification on discretized labels, discarding continuity in the…
Structured sparse learning is a leading paradigm for high-dimensional data modeling, as it enables rigorous integration of domain-validated structural priors into the learning process. Among these…
Predicting surrounding vehicles' lane-change intentions enables autonomous vehicles to anticipate potential hazards and respond proactively rather than relying solely on reactive maneuvers. This…
Traffic management has traditionally focused on toll-based and road pricing solutions. However, road pricing often raises concerns about accessibility and public dissatisfaction, leading to its…
AI agents capable of autonomous decision-making introduce significant challenges related to safety, alignment, accountability, and human oversight. Existing Human-in-the-Loop (HITL) and responsible…
Signed graph learning has emerged as a powerful framework for modeling networks with both positive and negative interactions. While graph-filter-based methods have achieved promising empirical…
We propose FiLM-CAM; a conditional-access image watermarking approach that enforces authorized encoding, decoding, and removal through keyed feature modulation. A secret key conditions a Feature-wise…
To enable Industry 5.0, where autonomous systems are widely adopted and integrated with people to promote sustainable development in industries, it is imperative to adapt complex deep learning models…
Retrieval-augmented generation (RAG) systems face security, privacy, and copyright risks including content leakage, source reconstruction, unauthorized access, data poisoning, and prompt injection.…
We prove a self-normalized Bernstein inequality for bounded functions of a regenerative process with independent, identically distributed marked cycles of finite mean length. The bound uses observed…
Adaptive experiments use bandit algorithms to favor interventions with higher expected rewards. However, decision-makers also require reliable inference on current treatment effects: differences…
This paper describes our submission to the WMT 2026 Multilingual Instruction Shared Task. We adapt Qwen3-8B with LoRA using organiser-provided data, EuroAlpaca, a multilingual instruction dataset…
Deep learning models for chest X-ray anomaly detection remain vulnerable to subtle distributional shifts (e.g., acquisition technique, patient-related factors, and preprocessing). Traditional error…
Most contemporary artificial intelligence (AI) systems are released with frozen parameters and improve through external updates, whereas an ideal system would keep improving from its own experience,…
Thyroid ultrasound supports the assessment of nodule malignancy, but classification predictions often lack evidence linked to familiar clinical descriptions. Radiomics provides explicitly defined…