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。
Percutaneous needle insertion is a common practice in minimally invasive procedures whose clinical success depends on accurate needle placement. However, achieving the necessary precision is a…
Existing Scene Text Recognition (STR) models are inherently coupled with a specific decoding strategy by their training paradigms, limiting their flexibility in deployment across diverse recognition…
Gated Delta Networks (GDNs) offer linear-time sequence modeling, yet long-context prefill remains costly due to dense intra-chunk computation, recurrent-state updates, and intermediate state storage.…
Vision-Language-Action (VLA) models enable capable robot behavior, but their large memory footprint limits deployment on resource-constrained robotic platforms. Weight quantization is a natural…
Conditional generation of time-series paths is a central problem in probabilistic modeling, where the goal is to simulate future trajectories that are both realistic and responsive to external…
Online Temporal Action Localization (OnTAL) aims to detect and localize action instances from untrimmed streaming videos in real time. Unlike offline approaches, OnTAL models have no access to future…
In AI for Science scenarios, experimental design and method reproduction require retrieving protocols that satisfy multiple interdependent constraints, yet existing benchmarks lack systematic…
Growing submission volumes have renewed interest in using large language models (LLMs) to support peer review. It remains unclear how such evaluation should be structured, how much the model matters,…
Spatial reasoning in Vision-Language Models (VLMs) has increasingly benefited from tool-integrated pipelines that ground computation in explicit geometry. However, existing systems often compile…
Executing an unfamiliar laboratory protocol requires a robot to identify missing capabilities and determine whether each operation remains valid as the experiment progresses. This letter presents…
Real-world robotic manipulation requires reasoning about cluttered scenes, partially observable or hidden objects, and semantically appropriate actions, in addition to low-level execution within…
We present Queryable Gaussian View Index (QGVI) for querying existing Gaussian scene assets and their associated calibrated reference data. Text-view retrieval and selective RGB camera localization…
Training-free expert pruning makes two decisions: which experts to remove, and what the layer computes when its router still selects a removed expert. Published methods change both at once.
Pre-trained models offer complementary strengths in CT organ segmentation, but their relative accuracy varies across organs and spatial regions. Multi-teacher knowledge distillation can combine these…
In modern information retrieval (IR), documents are increasingly encountered as structured sequences of visually rich, paginated units, rather than as flat text. Example documents encountered in our…
General humanoid motion trackers typically rely on deterministic policies that cannot adapt online without brittle reference editing or costly retraining. We present DiffWBC, shifting whole-body…
Camera--LiDAR perception on mobile robots and intelligent vehicles depends on reliable sensor geometry throughout deployment. Installation variations create uncertainty in the initial extrinsics,…
In this paper, we focus on interaction-preserving motion retargeting, which transfers human demonstrations to humanoids while maintaining spatial relationships with objects and terrain. Previous…
Robots deployed in unstructured environments are susceptible to actuator-authority degradation, which reduces the effective control authority of individual actuators and can cause reinforcement…
Low-light image enhancement (LLIE) focuses not only on visibility recovery but also on preserving structurally meaningful content and perceptual naturalness. Existing learning-based methods may…
Image reconstruction for positron emission tomography (PET) is a challenging inverse problem due to its inherent ill-posedness and Poisson counting noise, particularly in low-dose acquisitions. In…
Learning dexterous manipulation from human videos remains an open challenge, particularly in the context of transferring a single demonstration into a spatially generalizable robotic skill and…
Recent generative models are widely used to provide whole-body motion for humanoid tracking. Current methods combine motion generators with controllers in an open-loop paradigm, which leads to…
Motion planning in clutter is embodiment-specific: the feasible free space and reachable commands depend on each robot's geometry and dynamics. Existing cross-embodiment policies output normalized…