MLINFO COLLECTION
過去の実験ノート、技術報告書、特許、論文を探しやすくするための製造業向けRAG導線です。
Procedural generation plays a key role in synthetic data creation and game development, offering greater controllability, editability, and diversity than static mesh representations. However,…
The goal of a world model is to capture the dynamics of an environment. This has the great appeal that it allows agents to plan and simulate a course of actions with the help of a world model.
Large language models need effective ways to acquire and use external knowledge beyond what they retain from pretraining. Continued pretraining risks catastrophic forgetting, while retrieval at…
Retail sales forecasting underpins inventory planning, yet promotions and calendar events reshape short-term demand. Although each factor usually has historical occurrences, the complete factor…
Medical severity estimation commonly relies on absolute grade annotations, which are fundamentally ordinal, yet existing methods often treat the grades as independent categories. Learning-to-rank…
Online vectorized map construction provides autonomous vehicles with essential, real-time semantic and geometric scene understanding. While leveraging prior maps presents an opportunity to improve…
We study a pricing game in markets with budget-constrained buyers, where each seller offers a single good at a price she sets, and each buyer chooses a utility-maximizing bundle subject to her…
Embedding-based verification often calibrates a false-accept threshold from all impostor pairs among $m$ identities, although these pairs share identities. We characterize a worst-case limit: when…
Standard sequence models encode position by token rank rather than physical coordinate, typically forcing practitioners to destructively resample continuous physical signals such as spectra observed…
We examine how closely pretrained LeWorldModel (LeWM) reproduces the effects of small action changes. Using matched simulator and model responses, we measure action sensitivity with Gram matrices at…
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…
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…
We introduce OvisOCR3, a 0.8B model for a broad range of OCR-related tasks. OvisOCR3 unifies document parsing, general OCR, key information extraction (KIE), document figure captioning, and…
Multimodal rerankers are usually dedicated models: a vision-language model (VLM) is trained on retrieval data to score the candidates of a query. Scoring options is not specific to reranking.
Looped transformers reuse a shared block of layers to increase computational depth without increasing the number of trainable parameters. They are trained with backpropagation through time (BPTT).
LLM agents can improve across tasks without updating model parameters by storing experience from their own executions in external memory and reusing it to guide later decisions. A central design…
Many modern language models have adopted hybrid architectures that incorporate both linear-time recurrence and softmax attention. Modern recurrence layers provide a highly expressive mixing mechanism…
Expanding the vocabulary of conditional text-to-speech (TTS) models typically requires extensive fine-tuning with paired audio, creating a major bottleneck for low-resource and cross-lingual…
Video overlay removal aims to recover scenes obscured by subtitles, titles, and logos while preserving surrounding content. Existing methods use temporal propagation or source-conditioned generation,…
Fine-grained visual understanding requires distinguishing subtle differences in local attributes and spatial relations, yet remains challenging for existing vision-language models. Unified multimodal…
Most automated survey generation systems retrieve papers as flat documents, limiting their ability to capture research structure. We present SurveyGraph, a framework built around a Methods-Entity…
Capturing a loose object inside a spacecraft requires a robot to approach a target that can translate and rotate, and whose motion changes when contact is made. These conditions motivate evaluation…
Extraction pipelines ask language models for JSON that follows a schema, and the schema can set a minimum number of list entries. We ask what models do when the document holds fewer items than that…
When tool-use agents write files, execute code, or send data, their final responses do not explain the resulting security events, and heterogeneous runtimes expose the relevant evidence through…