26 accepted papers
Retrieval-Augmented Generation (RAG) systems using Multimodal Large Language Models (MLLMs) show great promise for complex document understanding, yet their development is critically hampered by inadequate evaluation. Current benchmarks often focus on specific part of document RAG system and use syn
Retinal Surgery Robotics is a rapidly emerging field that offers enhanced precision by overcoming human tremors. A key trend of these robotic designs is toward more compact and lightweight structures for improved positioning accuracy and precise force delivery. However, this compactness sacrifices t…
Transformer-based approaches have recently become the dominant paradigm for 3D instance segmentation. These methods typically employ a multi-layer decoder that iteratively refines a set of learnable queries into instance mask predictions. However, we observe that multiple queries often target the sa
We study the gradient flow dynamics of diagonal linear networks for regression tasks under infinitesimal initialization. Extending the saddle-to-saddle dynamics described in Theorem 1 from Pesme & Flammarion (2023), we generalize the analysis to both deep diagonal linear networks and a broader class…
Communication latency in long-distance telerobotic surgery poses a critical safety risk, particularly in high-precision procedures like retinal surgery where tool overshoots can cause irreversible patient injury. This paper introduces the Latency-Aware Telemonitoring for Injection in Ophthalmic Surg…
Predicting street-level socioeconomic indicators from street view imagery is fundamental to urban planning. Existing methods typically extract visual features via pretrained encoders and propagate information through graph-based learning, but they fail to fully exploit the structured, task-relevant,…
In ophthalmic surgery, surgeons or robots manipulate a light probe and an instrument around two separated trocars following sclerotomy to achieve orbital control for eyeball pose adjustment and subsequent surgical tasks referring to microscope frames. However, current methods face significant challe
We propose Any2graph, a generic framework for end-to-end Supervised Graph Prediction (SGP) i.e. a deep learning model that predicts an entire graph for any kind of input. The framework is built on a novel Optimal Transport loss, the Partially-Masked Fused Gromov-Wasserstein, that exhibits all necess…
Robotic ophthalmic surgery is an emerging technology to facilitate high-precision interventions such as subretinal injection and removing swinging tissues in retinal detachment using microscopy and iOCT. However, locating the instrument tip outside iOCT's range-limited ROI is challenging, especially
Intuitive enhancement of surgical precision in robotic retinal surgery highly depends on the stable acquisition of intraocular imaging data. Such acquisition requires segmenting intraocular components, especially instrument-tip positions, to achieve state estimation and subsequent navigation and mot
The pneumatic artificial muscle (PAM) is widely applied in various scenarios due to their compliance and high-efficiency characteristics. However, the online modeling method which can accommodate online data remains an unresolved issue when data cannot be obtained off-line. This letter proposes an o
In this letter, we present a novel portable strategy for the autonomous exploration of highly unstructured three-dimensional environments using ground robots. The proposed planner leverages elevation mapping to estimate traversability, enabling efficient environment mapping while conserving computat
In ophthalmic surgeries, the light probe is responsible for providing safe intraocular illumination and ensuring the visibility of the instrument and its shadow as the only available reference for qualitative depth estimation and landing point prediction in fundus microscopic images. To achieve sust…
In ophthalmic surgeries, such as vitreoretinal operations, surgeons rely on imaging systems, primarily microscopes, for real-time instrument monitoring and motion planning. However, novice surgeons struggle to extract 3D instrument positions from 2D microscope frames, necessitating extensive trial-a…
This paper introduces SparseTSF, a novel, extremely lightweight model for Long-term Time Series Forecasting (LTSF), designed to address the challenges of modeling complex temporal dependencies over extended horizons with minimal computational resources. At the heart of SparseTSF lies the Cross-Perio…
Learning to optimize (L2O) has gained increasing popularity, which automates the design of optimizers by data-driven approaches. However, current L2O methods often suffer from poor generalization performance in at least two folds: (i) applying the L2O-learned optimizer to unseen optimizees, in terms…
Learning to Optimize (L2O) has drawn increasing attention as it often remarkably accelerates the optimization procedure of complex tasks by "overfitting" specific task type, leading to enhanced performance compared to analytical optimizers. Generally, L2O develops a parameterized optimization method…
Animal pose estimation and tracking (APT) is a fundamental task for detecting and tracking animal keypoints from a sequence of video frames. Previous animal-related datasets focus either on animal tracking or single-frame animal pose estimation, and never on both aspects. The lack of APT datasets hi…
Retinal surgery is a complex medical procedure that requires exceptional expertise and dexterity. For this purpose, several robotic platforms are currently under development to enable or improve the outcome of microsurgical tasks. Since the control of such robots is often designed for navigation ins…
Recently, the Local Mahalanobis Distance (LMD) technique was proposed for incipient fault detection, which was shown to be sensitive, robust and distribution assumption-free. Further, this paper explicitly establishes the relation between fault severity and LMD index to take advantage of those excel…
Bilevel optimization has arisen as a powerful tool for many machine learning problems such as meta-learning, hyperparameter optimization, and reinforcement learning. In this paper, we investigate the nonconvex-strongly-convex bilevel optimization problem. For deterministic bilevel optimization, we p…
Impact mitigation is crucial to the stable locomotion of legged robots, especially in high-speed dynamic locomotion. This paper presents a leg locomotion system, including the nonlinear active compliance control and the active impedance control for the steel wire transmission-based legged robot. The…
Bilevel optimization has been widely applied in many important machine learning applications such as hyperparameter optimization and meta-learning. Recently, several momentum-based algorithms have been proposed to solve bilevel optimization problems faster. However, those momentum-based algorithms d…
Machine reading comprehension (MRC) is an AI challenge that requires machines to determine the correct answers to questions based on a given passage. MRC systems must not only answer questions when necessary but also tactfully abstain from answering when no answer is available according to the given…
Stochastic gradient descent (SGD) has been found to be surprisingly effective in training a variety of deep neural networks. However, there is still a lack of understanding on how and why SGD can train these complex networks towards a global minimum. In this study, we establish the convergence of SG…
Unmanned construction machines are used after disasters. Compared with manned construction, time efficiency is lower because of incomplete visual information, communication delay, and lack of tactile experience. We have developed an autonomous camera control system to supply appropriate visual infor…