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。
Event cameras offer microsecond temporal resolution, high dynamic range and no motion blur, but referring video object segmentation (RVOS) lacks event-stream datasets and models. We introduce…
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…
Electric vehicles produce no tailpipe emissions, but charging them produces emissions that depend on the time-varying generation mix of the electricity consumed. We study an Electric Vehicle Routing…
Failures of deployed clinical artificial intelligence (AI) systems have often originated in how their training data were generated. Whether the programs that train the health AI workforce teach…
Current Vision-Language Models (VLMs) frequently fail to recognize culture-specific concepts, especially from underrepresented regions. Effectively injecting this long-tail knowledge into existing…
Crowd simulation aims to generate agent behaviours that are rich, natural, and appropriate to their surrounding environment. Recent advances in Machine Learning have enabled such behavioural patterns…
In segmentation-based continuous sign language recognition, an untrimmed video is first partitioned into lexical units; segmentation is therefore a means to an end---downstream recognition. However,…
Reasoning informs decision-making by connecting intended actions with their expected consequences. Recent vision-language-action (VLA) models incorporate embodied chains of thought (ECoTs) to guide…
Multi-agent LLM systems increasingly rely on persistent memory and inter-agent communication. These capabilities create privacy risks that extend beyond individual interactions: a release appropriate…
Accurately predicting the transport properties of liquid electrolytes is critical for next-generation battery design and requires force fields that are both quantum-mechanically accurate and fast…
Traditional neural solvers for solving vehicle routing problems (VRPs) often suffer from limited solution diversity, motivating the development of Generative Flow Network (GFlowNet)-based models.…
Self-evolving agent skills enable AI agents to accumulate and refine reusable procedural knowledge from interaction experience without updating model parameters. However, since such skills are…
View- and target-specific echocardiography AI models capture useful but complementary information and may not achieve sufficient predictive performance in isolation. A learned ensemble is a natural…
Giving embodied agents the freedom to act autonomously, initiate interactions, and understand their surroundings through experience is a step toward bringing them to life in the physical world.…
Reliable local search is essential for LLM agents to support everyday decisions and longer plans by finding places that meet users' needs at given times and locations. Yet existing benchmarks provide…
Large language models (LLMs) have shown strong performance on software engineering (SE) tasks, driving the need for high-quality datasets for reliable training and evaluation. SWE-bench-style…
Deep research agents (DRAs) conduct long-horizon reasoning, search, and literature synthesis to provide long-form answers to complex, domain-specific questions. These agents are typically trained and…
Quantifying degradation between a pristine signal and its degraded observation is fundamental to signal processing, yet existing full-reference measures are inherently modality-specific. We introduce…
Chatbots are increasingly consulted about public affairs, and their judgments of policies are useful only if they are robust. We measure this robustness in the setting of an ordinary user, through…
Research on medical item difficulty has largely focused on prediction rather than on identifying interpretable patterns associated with empirical difficulty. This study used empirical difficulty…
Google's AI Overviews (AIOs) are the first result users encounter when searching the web, shifting the work of selecting and evaluating sources from the user to Gemini. This may be especially…
We present SONIC-K1, to our knowledge the first open-weights whole-body motion tracker for the Booster K1 humanoid, obtained by adapting the SONIC framework to this smaller robot. The policy is…
Multimodal tool-using agents augment vision-language models with access to external information and capabilities, enabling them to solve knowledge-intensive and visually complex tasks that cannot be…
Probabilistic graphical models (PGMs) compactly encode structured joint distributions, but Most Probable Explanation (MPE), which finds the highest-probability assignment to unobserved variables,…