MLINFO COLLECTION
LoRA、RLHF、SFT、軽量ファインチューニングなど、LLMを用途に合わせる技術を扱います。
Large language models (LLMs) are increasingly used to automate AI research, including language-model (LM) development, offering a potential path toward recursive self-improvement. However, turning…
Safety in Multimodal Large Language Models (MLLMs) depends on unsafe multimodal data for post-training alignment or activation steering. However, such data is hard to collect, must be gathered anew…
Industrial manipulation in flexible manufacturing, e.g., high-mix, low-volume (HMLV) electronics assembly, requires robot policies to adapt to changing products and production conditions. Such…
Fine-grained visual understanding requires distinguishing subtle differences in local attributes and spatial relations, yet remains challenging for existing vision-language models. Unified multimodal…
Recent advances in multimodal large language models (MLLMs) have enabled them to act as autonomous agents, creating and editing 3D models via code or direct software manipulation. In practical…
Agent Skills improve LLM agents by making task knowledge reusable across sessions. Learning transferable Skills requires evidence about a procedure and its conditions of use, which a successful task…
home-llmは、ローカルLIMを使ってスマートホームの制御を可能にするHome Assistantの統合モデルです。
The life-cycle of robotics foundation models crucially depends on data labels. Outcome reward labels are needed for monitoring real-world deployments.
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…
本研究では、生成推奨システムにおけるアイテムIDの構築、調整、生成の手法について、アイテムIDの構築方法を分析しています。
While LLM agents are increasingly capable of gathering and synthesizing evidence from a single homogeneous source, such as structured tables or unstructured data, real-world analytical questions…
The rise of large language models (LLMs) has opened a path toward generalist embodied AI, raising the question of how LLMs can act in the physical world. One straightforward approach is training the…
When a speaker says ``some students passed'', listeners infer that not all of them did. Reasoning models now let users decide how long a model thinks before it answers, but we do not know what extra…
Language-model agents that run long tasks often redo work they have already done: they re-issue a tool call they made earlier and get back exactly the same observation, a step that adds no new…
Structured knowledge retrieval acquires task-relevant evidence from structured knowledge sources for downstream tasks. Existing methods rely on unconstrained retrieval or predefined query-rule…
Spatio-Temporal Video Grounding (STVG) aims to jointly localize a target in space and time given a natural-language query. Despite continued advances, existing STVG benchmarks remain largely centered…
医療では、イメージャは単に画像を解釈するのではなく、複数の画像を比較して診断を行うことが多い。しかし、現在の技術ではこのような比較を行うことは困難であるため、メドリコのDBというデータセットを利用することで、医療の比較推論タスクに対処する技術を提案している。
Memory has become integral to the LLM agent ecosystem, supporting information retention and reuse across interactions. However, most existing agent memory systems construct memory in a query-agnostic…
Few-shot semantic segmentation typically identifies target objects based on positive support examples of a single semantic class. In practice, however, positive cues alone are often underspecified:…
Effective test-time personalization requires LLM agents to adapt to query-dependent user preferences from lightweight interaction. We study persona selection with binary comparisons between candidate…
Improving every agent in an LLM-based multi-agent system can be prohibitively costly, making it important to identify which agent should be prioritized to achieve the greatest system-level gain with…
Vision-language-action (VLA) models have shown strong promise for generalist robotic manipulation, but their inference cost remains a major bottleneck for real-time control. This limitation is…
3D part assembly aims to reconstruct a complete shape from a set of unassembled parts by predicting a rigid SE(3) transformation for each part. Because the placement of a part is rarely determined by…
Long-horizon, semi-verifiable agentic tasks often rely on rubric-based evaluation, but the evidence needed to assess these tasks can be spread across the environment state and the execution trace. A…