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。
Personal intelligence systems are taking on increasingly complex everyday tasks, yet repeated questions, unnecessary confirmations, and unwanted outreach can turn capable assistance into interaction…
Should an embodied agent's experience be baked into its policy weights, or kept external and retrieved at inference? A memory-augmented teacher (a VLM that retrieves lessons, with their episode…
Multi-task generalization is an important yet underexplored problem in multi-agent reinforcement learning (MARL). Many real-world applications require multi-agent systems to generalize across…
Recent advances in search agents have enabled large language models to tackle complex tasks by retrieving and synthesizing external information. However, existing search agents often lack…
Large language model (LLM) based multi-agent systems often rely on predefined collaboration structures, limiting their adaptability to evolving task requirements. Although recent approaches enable…
LLM-based chat agents are increasingly used for complex, multi-turn, multilingual medical triage in low- and middle-income countries (LMICs), yet evaluation methods focus on single-turn, English-only…
Training Arabic large language models faces challenges from noisy web data, dialectal variation, and the high cost of continual pretraining (CPT). We introduce AQL-Lite (AQL: Arabic Quality…
Generating an articulated object from a single image requires recovering both its appearance and the mechanism governing its parts. A compact encoding of joint attributes does not by itself ensure…
Dynamic representations based on 4D Gaussian Splatting (4DGS) have shown strong capabilities in reconstruction and rendering, yet current methods remain limited in supporting complex natural-language…
Existing 3D generative approaches are typically developed for individual imaging modalities, requiring substantial modality-specific data and limiting their ability to exploit shared structure across…
Muon updates matrix-valued parameters along approximately orthogonalized directions and often trains large language models faster than AdamW, yet it remains unclear when and why orthogonalization…
Reinforcement learning (RL) is an effective way to strengthen the long-context reasoning of large language models (LLMs), but it needs training data that are long, diverse, challenging, and…
Sequential decision-making under partial observability is difficult because agents must explore to infer hidden, task-relevant information before acting effectively. Learning such…
Vision-language-action (VLA) models have shown promise in robotic manipulation, but imitation learning (IL) alone often struggles to master complex long-horizon skills. Reinforcement learning (RL)…
Today's multimodal assistants are typically prompted to interpret the visual evidence presented to them. To offload the cognitive burden of remembering across long horizons, wearable assistants…
Natural-language software requirements often omit assumptions about performance, operating conditions, user behaviour, and domain constraints, affecting architecture, testing, and deployment. If…
Long-term memory for multimodal agents remains challenging, as it must preserve fine-grained visual evidence while tracking entity evolution across sessions. Existing abstraction-based memories…
Retrieval-augmented generation (RAG) frequently integrates knowledge graphs (KGs) for complex multi-hop question answering. However, their performance is increasingly bottlenecked by the knowledge…
A benchmark is not merely a collection of test questions; it naturally induces an empirical measure over difficulty. In this work, we develop this measure-based view of benchmark evaluation.
Automated radiology report generation for multi-sequence brain MRI holds strong promise for alleviating radiologists' workload, yet it remains a demanding problem: brain MRI studies are inherently…
Learning across medical imaging modalities requires making use of images without paired text and accommodating new domains while retaining existing representations. We propose a medical…
Geometric structure is essential for robotic manipulation and understanding the 3D world. Most VLA models rely on 2D representations of current observations, while geometry-aware approaches often…
General-purpose robots must handle tasks, objects and environments they were never trained on, yet zero-shot generalization remains one of the least solved problems in physical AI. In digital AI,…
Agent memory systems such as Mem0 and Zep decide what to keep before any question arrives; coding agents keep the raw history and let the model search it with its own tools. We ask whether designed…