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。
As wearable and digital health systems increasingly generate longitudinal physiological records, communicating these observations in patient-accessible language remains a significant challenge. Large…
KV cache compression for multimodal LLMs usually selects the visual tokens to keep once, at prefill, and reuses that selection for the whole generation. We show that this one-shot selection is…
Vision-language-action (VLA) models have become an important paradigm for robotic manipulation by unifying visual perception, language understanding, and action generation. Since reliable…
Visual document understanding is essential for acquiring knowledge from visually rich documents and is attracting growing research interest. Existing surveys emphasize architectures or technical…
Tree-based speculative decoding accelerates large language model inference by verifying multiple candidate branches in parallel. However, in practical serving scenarios, similar requests repeatedly…
We introduce the conditional expected local radius (CELR) and develop a new conformal prediction method for non-Euclidean responses in general metric spaces. CELR measures local conditional…
Evolutionary program search with large language models keeps the structure of an evolutionary algorithm and uses the model as its variation operator. Typically, the model generates each candidate…
During the deep learning era, innovations in remote sensing (RS) vision models primarily focused on optimizing network architectures for specific tasks and conducting end-to-end training. However,…
Long egocentric videos pose a central challenge for multimodal language models: the visual stream must be compressed into a memory representation that can be searched efficiently while still…
Training-free personalization adapts a frozen vision-language model (VLM) to recognize user-defined concepts from only a few exemplars by retrieving concept entries at inference time. While recent…
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…
Limited tumour visibility on intra-operative images complicates surgical navigation, including liver hepatocellular carcinoma (HCC) targeting on computed tomography (CT) imaging. This makes labelled…
Neural architecture search (NAS) on a new dataset often affords only tens of short training runs, so what the search knows before its first evaluation decides its efficiency. Yet most NAS methods…
Reinforcement learning has emerged as an effective approach for combinatorial optimization, but most existing methods focus on problems such as the Travelling Salesperson Problem (TSP) in which all…
Low-light image enhancement (LLIE) aims to recover well-exposed and perceptually faithful images from severely degraded observations. Recent diffusion-based generative methods achieve strong…
LiDAR point cloud semantic segmentation is a fundamental component of 3D perception for autonomous driving and robotics. Projection-based methods map 3D point clouds into 2D representations for…
As AI generated images are getting popular these days, discussions on such generations are widely existed in current public forums, software repositories, and photography tutorials. Moreover, with…
Our previous analysis found that a model's native hashed N-gram table is where continual updates disturb the base least, but its writes needed backpropagation and changed the pretrained table. We…
Measuring animal distance and motion in metric units underpins abundance estimation, morphometrics, and movement ecology, yet monocular video lacks metric scale and wildlife datasets lack metric…
Detailed image captioning is usually framed as an amount problem: a model should mention more visual facts while avoiding hallucination. However, autoregressive VLMs generate captions as ordered…
While functional magnetic resonance imaging (fMRI) decoders reconstruct images and 3D objects, recovering the metric geometry of rooms from a moving viewpoint remains an open challenge. We introduce,…
Multi-agent LLM systems are increasingly used in practice, but their behavior is complex and hard to understand. We design a simple task to ask which model has the most influence on the final…
Multimodal sentiment analysis (MSA) aims to infer sentiment by integrating linguistic, acoustic, and visual information. However, many fusion methods integrate modality-specific representations and…
Approximate unlearning answers a deletion request on a knowledge-graph embedding by editing entity embeddings instead of retraining from scratch. These embeddings keep being updated as new facts…