MLINFO COLLECTION
製品画像、顕微鏡画像、表面欠陥を対象に、分類・検出・セグメンテーションを選ぶための導線です。
Vision-language models are now routinely tested on theory of mind: whether they can work out what another person sees, knows, and means. A common design asks the model to report that perspective and…
World Action Models (WAMs) have shown strong potential for robot manipulation by jointly learning visual dynamics and executable actions. However, their video and action objectives do not explicitly…
As-built BIM reconstruction from point clouds demands semantic, volumetric, parametric, and editable building components, beyond 2D layouts or planar abstractions. Yet existing scan-to-BIM pipelines…
Omni-modal assistants must remember not only what users say, but also what they show and convey. Existing long-term memory benchmarks are mostly text-and-image or report a single end-to-end score, so…
Predictive representations for robot manipulation should connect scene geometry with the state changes induced by actions. Our intuition is that understanding what an action will change starts with…
In this paper, we investigate why vision-language models (VLMs) produce errors by decomposing them into two sources: visual-representation failures, in which the visual evidence required for the…
Barycenter models, based on stochastic and deterministic optimal transport bridges between probability measures, have proven to be useful for supervised and unsupervised learning for (probability)…
Neural network models are increasingly constructed from synapse-resolution connectomes, and the same circuit is now available in reconstructions from other animals and pipelines. We do not know…
Vision-language-action (VLA) navigation models translate visual observations and instructions into actions. Navigation success assesses whether an agent reaches the goal.
Sharpness-Aware Minimization (SAM) has established itself as a widely used method for training deep neural networks. Despite its popularity, existing convergence guarantees for SAM-type methods…
World action models (WAMs) are shown to substantially diverge under generalization performance based on their generative backbones. We investigate this gap through the representational geometry that…
Human-in-the-loop (HIL) post-training improves vision-language-action (VLA) policies through expert corrections, but costly human supervision and repeated real-robot evaluation limit algorithm…
Vision-based insertion requires correcting alignment errors while retaining useful behavior learned from demonstrations. We present ACT--Flow, an online learning framework that couples an adaptive…
World models predict how embodied systems evolve under actions, but their accuracy can degrade when physical conditions move outside the training distribution. We study two components of causal…
Reward guidance methods sample an exponential tilt of a base density using a diffusion model trained with only samples from the base distribution. Existing methods use what we call external guidance:…
Currently, dexterous humanoid robot hands are widely considered the final hardware bottleneck that hampers generalist robots from physically assisting people at home and work. As conventional…
Accurate 6-DoF object pose tracking is essential for robotic interaction, yet conventional monocular pipelines frequently suffer from catastrophic divergence under rapid object motion. We present…
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…
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.
In contact-rich manipulation, contact conditions can change before a visual policy updates its action plan. Recomputing the plan through the visual policy adds latency, while tactile feedback alone…
Target-based extrinsic calibration estimates the rigid transform between sensors from a few observations of a known target, and its result is commonly assessed by the root-mean-square error of the…
Dexterous multi-finger hands hold promise to unlock diverse skills like functional grasps, in-hand reorientation, and dynamic handover that the human-designed world assumes, yet existing learning…
Motivated by the human ability to integrate experience across language, perception, and action, we introduce UniWALM, a unified world-action-language model that learns video, action, and language in…
Warehouse robot fleets continuously observe operational conditions, but preserving these observations as reusable semantic memory incurs substantial computation, communication, and storage costs. For…