MLINFO COLLECTION
RAG、埋め込み、検索評価、要約を使って文書検索や社内QAを作るための技術です。
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…
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…
Principal Component Analysis (PCA) is a fundamental tool for statistical dimension reduction, yet no canonical extension to distribution-valued data has emerged within the framework of optimal…
Long-term agent memory is shifting from predefined workflows toward learnable policies for memory construction and retrieval. Existing learning-based methods either optimize construction alone or…
This article investigates the joint-angle invariance (JAI) of Jacobian-based performance indices for serial robotic manipulators. We identify kinematic conditions under which representative…
Robust and reactive collision avoidance remains a central challenge for deploying Reinforcement Learning (RL) policies on real robotic manipulators, particularly when transferring behaviours learned…
Automated optical inspection of precision components with tiny surface defects remains challenging when different regions of the same component exhibit different defect characteristics and,…
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…
Modern robotic agents are increasingly expected to support steerable control, where a single policy can adjust its behavioral style at runtime under changing user preferences. Preference-conditioned…
Large retail chains must tailor assortment and pricing decisions to local customer preferences, yet even retailers with extensive sales records often have limited data for estimating demand at the…
Learned priors are used to reconstruct regions that measurements barely reach, and to report uncertainty there. They can fail silently: the reported interval excludes the truth while every…
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…
Full conformal prediction offers finite-sample marginal coverage guarantees under exchangeability, but exact computation can be costly, while its classical guarantees do not directly extend to…
Data attribution methods for Language Models (LMs) are typically evaluated using downstream tasks like fact retrieval. However, existing evaluations vary multiple dataset properties simultaneously,…
Luggage re-identification (ReID) is a critical task in video surveillance for forensics, security or border management (suspicious or abandoned luggage recognition), as well as luggage management…
Realistic, fast robotics simulations could enable large-scale training of embodied AI models that transfer to the real world. However, despite decades of progress, available simulations cover only a…
Long-context models repeatedly solve closely related retrieval problems. Attention or global retrieval can retain large stores, but each forward pass again searches for what matters.
Cross-modal scene and instance retrieval aims to retrieve a corresponding 3D environment or object given query 2D images, serving as a foundational mechanism for spatial reasoning in robotics and…
Legal Question Answering (QA) over statutory texts is a challenging task in Natural Language Processing (NLP), especially in low-resource settings with complex legal systems. It requires answers that…
Audio-visual instance segmentation (AVIS) segments and tracks individual sound-producing objects in videos. Existing benchmarks predominantly use monaural audio, which lacks inter-channel cues for…