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。
Interactive video world models aim to follow user actions while maintaining scene consistency over extended interactions. History-based methods reuse generated latents to preserve scene content, but…
Unified multimodal models (UMMs) jointly support visual understanding and image generation, yet information flow between these two capabilities remains largely asymmetric: understanding…
As large language models (LLMs) become more widespread in Africa, their safety in low-resource languages remains largely untested since most red-teaming work focuses on English. This study evaluates…
Long-run RTL simulation of CPU candidates can take hours, while short diagnostic runs may miss performance degradation that emerges later in execution. This evaluation cost can delay design decisions…
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…
Vision-Language-Action (VLA) models excel at instruction following, yet most remain feed-forward: they condition actions only on the current observation and discard both long-horizon temporal context…
Next point-of-interest (POI) recommendation aims to predict a user's next destination from spatio-temporal check-in data, and serves as the foundation for many location-based services. Recent…
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…
In-context learning (ICL) lets tabular foundation models make predictions without dataset-specific training or fine-tuning. These models achieve strong predictive accuracy, but interpreting how…
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…
Deep neural networks achieve strong performance across many tasks but remain vulnerable to adversarial perturbations. Adversarial training (AT) is one of the most effective defenses, yet it suffers…
Medical AI learns from the answers doctors record, but rarely from how they interpret the evidence to reach them. Here we introduce PathCowork, a framework that turns pathologists' narrated…
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 can often identify useful semantic structure in formal artifacts, but their outputs cannot be trusted as proofs or solver decisions. We study whether LLMs can instead guide…
Cyber threat intelligence (CTI) reports describe adversary behavior in natural language, but converting them into structured MITRE ATT&CK mappings remains difficult: existing methods decompose…
Multimodal large language models can recognize visual content yet struggle to reason reliably over it across multiple steps. In counting, a model may see all objects but lose track of which ones it…
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…
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…
Universal Manipulation Interface (UMI) devices allow human experts to demonstrate tasks for robot learning without teleoperating physical robots. Using these demonstrations as training data still…
LLM agents increasingly carry out multi-turn tasks across everyday applications, yet users often see only the agent's report rather than the observations, API calls, and state changes behind it.…
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…
Frontier language models such as GPT 6 Astra have contributed to research mathematics, demonstrating substantial reasoning capabilities. Yet serious reasoning failures persist even in tasks governed…
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…
Long-horizon robotic tasks are commonly decomposed into semantic subgoals to simplify planning. However, subgoal progress in LLM-based planning is typically inferred implicitly from interaction…