MLINFO COLLECTION
Enterprise agents answer questions over workplace records that evolve through team collaboration. As information is shared, corrected, and revised across documents, chats, and figures, multiple…
Video generation models are promising foundations for embodied world models, but only if their generated rollouts are physically valid and faithful to task instructions. Multimodal large language…
Aiming to modify textual content while preserving the original style, Scene Text Editing (STE) has significant practical value in many applications. STE typically requires paired images before and…
In long-term interactions with large language model (LLM) agents, users reveal habits through their choices and actions. These habits capture implicit user information that agents must infer across…
最適なAIモデルを効率的に学習するためのオーサリングツール。Agent Lightningを使用して、トレーナーをセットアップし、データをトレーニングしてモデルを学習することができる。
Safe robotic task planning requires planners that can reliably achieve task goals while satisfying safety constraints. Classical planners search over explicit symbolic task representations and can…
Autonomous mobile robots require spatial representations that capture geometry and semantics while staying sparse enough for planning in large, unknown environments. Graphs provide a natural…
Mobile manipulators must adapt not only to objects, but also to the spatial context in which they appear: where to position the base, how to manipulate, and where to look while navigating surrounding…
Modern robotic agents are increasingly expected to support steerable control, where a single policy can adjust its behavioral style at runtime under changing user preferences. Preference-conditioned…
Blind and visually impaired individuals face uncertainty when navigating unfamiliar areas. Whether a cane or a guide dog is used for navigation, this may prove to be challenging.
Long-horizon robotic operation requires memory that scales with essential information rather than execution time. We present a parameter-space memory framework where each episode is stored as a…
Evaluations of large language model (LLM) agents report that pricing agents collude at others' expense. Yet collusion is defined by enforcement: a cartel, in which competitors share monopoly profits,…
Large retail chains must tailor assortment and pricing decisions to local customer preferences, yet even retailers with extensive sales records often have limited data for estimating demand at the…
Accurate ground plane normal estimation is essential for odometry in spherical mobile mapping systems (SMMS), which face challenges from rapid rotations and limited ground coverage. We propose two…
Warehouse robot fleets continuously observe operational conditions, but preserving these observations as reusable semantic memory incurs substantial computation, communication, and storage costs. For…
Evaluating and post-training robot policies through physical interaction is costly and difficult to scale, motivating action-conditioned world models as interactive simulators. However, visually…
Agentic robotics systems combine planners with robot harnesses to perform complex manipulation tasks. Recent work improves these systems through better harnesses and external memory, but relies on…
Lunar surface exploration increasingly relies on autonomous rovers that must perceive and traverse unstructured terrain under extreme illumination conditions. Near the lunar poles, low sun elevations…
General-purpose multimodal models have shown promise as direct robot action policies, yet whether they grasp the physics underlying real-world interactions and can apply that understanding to guide…
Classical robot navigation stacks are reliable but often require re-engineering for each new robot type and site. Learning-based navigation shifts this effort from hand-tuned parameters to data…
Reasoning about safety is essential for embodied agents powered by large language models (LLMs). We introduce the Contextual Action and Plan Safety benchmark (CAPSafe), designed to evaluate safety…
Vision-Language-Action (VLA) policies increasingly reason before acting, but existing reasoning models compress this intermediate decision into a single representation. When several plans are valid,…
Learned priors are used to reconstruct regions that measurements barely reach, and to report uncertainty there. They can fail silently: the reported interval excludes the truth while every…
Gaussian process upper confidence bound (GP-UCB) has been widely studied, though its known regret upper bound is suboptimal. To obtain near-optimal regret upper bounds, existing studies mainly focus…