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 models (LLMs) are increasingly described as acquiring "reasoning" skills after reinforcement learning with verifiable rewards. However, whether these gains reflect genuine reasoning or…
Experience can help embodied agents turn high-level plans into grounded actions, but transferring it across tasks remains challenging: previously effective strategies may be inapplicable to the…
Edited endpoint images make the target of an image-to-video transition explicit and can improve transition completion, but also preserve context in the source image's layout. Full-frame endpoint…
Sequential recommenders typically construct history inputs from item identifiers or content features using an embedding map shared across users. The same item therefore yields the same initial…
Inferring jhana-type advanced concentration absorption meditation (ACAM-J) states from fMRI data is challenging due to the spatially distributed nature of meditation-related effects, substantial…
Few-shot voice cloning makes it cheap to produce daily Japanese financial commentary with several synthetic speakers, but kanji words with more than one reading, such as the word for "market" (shijo…
Egocentric video has emerged as one of the most scalable sources of data for learning generalizable manipulation priors. Yet, despite its growing use in pretraining robotic policies, it has been…
In multi-output structured prediction tasks, while only one ground truth label may be provided in the training data, multiple equally valid outputs may be possible, making reliable evaluation a…
Aligning a partial, real-world 3D face scan to a canonical representation requires solving two coupled problems at once: estimating the rigid pose that brings the scan into a common frame, and…
With the rapid advancement of text-to-image diffusion models, increasingly realistic AI-generated content has raised serious concerns about misuse and copyright infringement. Digital watermarking…
The central bottleneck in visual generation and editing has migrated from achieving pixel-level fidelity to satisfying densely constrained user specifications through increasingly agentic workflows.…
Relational pattern languages generalize Angluin's pattern languages by requiring the strings substituted for repeated occurrences of a variable to stand in a given relation, rather than to be…
Large language model (LLM) agents often receive access to more files, accounts, and services than a task requires. Prompt injection turns this excess access into an opportunity to redirect execution…
Spatial transcriptomics (ST) enables joint characterization of tissue morphology and gene expression. However, 3D volumetric ST acquisition remains expensive.
4D perception models, which classify 3D point-cloud videos, are being built into robots, assistive monitoring and AR, yet before deploying one a practitioner cannot check which cue it relies on: how…
In a duopoly with captive and contested consumers, I characterize every pair of consumer and producer surplus that can arise under some market composition and some public segmentation, and construct…
Customizing Pretrained Models (PMs) for downstream tasks demands task-specific data, which burgeoning Web3 applications provide abundantly. Blockchain-powered federated learning (BCFL) offers a…
In sampled cascade linear active disturbance rejection control (LADRC) of quadrotors, the extended-state observer typically receives the instantaneous command, although the delayed measurement…
Operational strategies for long-horizon robotic tasks require reliable evaluation to determine whether execution is progressing, stalling, regressing, or recovering from errors. Yet real- world robot…
Dangerous-capability evaluations often test an AI agent from prepared states at ordered milestones. A clean sheet records no successes.
Self-evolving personal agents act for users and learn from user feedback. However, if an agent obeys an instruction that an untrusted third party hides in content, the third party gains control of…
As a representative form of embodied robotic interaction, aerial grasping requires close coordination between the aerial platform and manipulator. Most existing systems perform aerial grasping with…
Diffusion models evolve noisy states toward a learned data distribution, so their sampling behavior depends on the geometry of the representation in which denoising occurs. This dependence is…
Triple set prediction (TSP) is to recover missing relational triples in a knowledge graph by predicting the triple set instead of isolated links. Existing approaches predominantly rely on the…