MLINFO COLLECTION
日次更新の新着・公開記事を新しい順に掲載しています。
Large language model (LLM)-based agents interact with external tools through protocols such as the Model Context Protocol (MCP), producing tool-call traces that may expose behavioral signals about…
Knowledge tracing (KT) predicts a student's next response from their history. New platforms often have question texts but no response logs for training, motivating zero-shot cross-domain KT.
We consider forecasting the dynamics of consumer preferences of retail chain customers. A customer's preference is described by a triangular fuzzy number.
Scaling humanoid motion foundation models is constrained by the scarcity of diverse, robot-executable data and by the difficulty of jointly learning from heterogeneous multimodal inputs while…
LLM-based robotic agent systems can generate programs for robot control, yet their generalization to new tasks often depends on elaborate scaffolding. Expanding their skill repertoires alone offers…
Job applicants increasingly use large language models (LLMs) to write cover letters, while employers deploy LLMs to screen them. In this all-AI setting, we ask whether the \emph{choice of model}…
Video director agents orchestrate multistage production to realize users' creative visions. Emerging research on their self-evolution advances screenplay planning effectively.
Simulation benchmarks score robot policies by success rate, and every failed episode counts against the policy. Many of these failures are the simulator's fault, not the policy's; we find the cause…
Conversational explainable AI (ConvXAI) agents often use GUS-style architectures with separate modules for intent recognition, dialogue management, and template-based response generation. While…
While sentence embeddings are primarily designed for semantic generalization, their latent geometry implicitly encodes surface-level lexical properties, a relationship that remains poorly understood.…
Transformers retain an explicit history of the sequence, allowing attention to directly retrieve past representations. However, the size of the KV-Cache and the cost of a new token increase with the…
Inserting an unseen part requires sub-millimetre precision and the correct orientation of keyed features. Current zero-shot agentic manipulation methods built on vision-language models (VLMs) produce…
Multimodal Large Language Models (MLLMs) are increasingly capable of understanding images and performing complex visual reasoning, suggesting the possibility of using them to automate biological…
Recent developments in both high-thrust (HT) and low-thrust (LT) propulsion technologies broaden design options for on-orbit servicing (OOS) missions. However, incorporating LT transfers into OOS…
We develop ReuScope, a protocol for auditing data reuse and evaluation sensitivity, using Capsule Vision 2024 as a case study. It combines measurements of data relationships with two comparisons:…
Accurate BEV map prediction is a critical component of autonomous driving systems, enabling downstream planning and control. Recent approaches such as Mask2Map achieve strong performance by…
Camera localization methods are mostly multi-stage pipelines relying on dedicated and complex maps that are costly to construct, store, and maintain over time. Alternatively, well-structured maps…
Vision Transformers represent each image patch through a canonical token produced under one observation condition. That token is a powerful interface, but it is still one realized state of the patch.
Large closed-source reasoning models expose only their final answers. The intermediate reasoning that produces those answers is hidden behind API surfaces, tool-call policies, and safety filters.
Deep neural networks for time series classification (TSC) are trained almost exclusively by error backpropagation, which imposes update locking and the weight-transport problem. Backpropagation-free…
We show that outlier eigenvectors of the Bethe Hessian achieve weak recovery in the stochastic block model down to the Kesten-Stigum threshold, for every fixed common expected degree $d>1$. This…
Physicians read electrocardiograms (ECGs) from waveform shape and timing, yet accurate deep-learning classifiers rarely show which waveform regions drive their predictions. We introduce LYNX-ECG, a…
Cultural value alignment requires not only model optimization but also a well-specified target grounded in real-human evidence. Yet how such targets should be grounded in human data remains largely…
Continual learning is the study of how a model accumulates knowledge from data received over time, rather than all at once. In practice, this is typically achieved by dividing a dataset into tasks…