Search Results for author:
Found 34 papers, 15 papers with code
dARt Vinci: Egocentric Data Collection for Surgical Robot Learning at Scale
The system uses Augmented Reality (AR) hand tracking and a high-fidelity physics engine to capture subtle maneuvers in primitive surgical tasks: By eliminating the need for a physical robot setup and providing flexibility in terms of time, space, and hardware resources-such as multiview sensors and actuators-specialized simulation is a viable alternative.
MoSFormer: Augmenting Temporal Context with Memory of Surgery for Surgical Phase Recognition
We further introduce step filtering to refine history representation and develop a memory caching pipeline to improve training and inference stability, mitigating shortcut learning and overfitting.
Kimi k1.5: Scaling Reinforcement Learning with LLMs
Moreover, we present effective long2short methods that use long-CoT techniques to improve short-CoT models, yielding state-of-the-art short-CoT reasoning results -- e. g., 60. 8 on AIME, 94. 6 on MATH500, 47. 3 on LiveCodeBench -- outperforming existing short-CoT models such as GPT-4o and Claude Sonnet 3. 5 by a large margin (up to +550%).
Neural Finite-State Machines for Surgical Phase Recognition
Surgical phase recognition (SPR) is crucial for applications in workflow optimization, performance evaluation, and real-time intervention guidance.
Language-Model Prior Overcomes Cold-Start Items
Existing solutions for the cold-start problem, such as content-based recommenders and hybrid methods, leverage item metadata to determine item similarities.
Towards Robust Algorithms for Surgical Phase Recognition via Digital Twin-based Scene Representation
This approach takes advantage of the recent vision foundation models that ensure reliable low-level scene understanding to craft DT-based scene representations that support various high-level tasks.
DaRePlane: Direction-aware Representations for Dynamic Scene Reconstruction
Numerous recent approaches to modeling and re-rendering dynamic scenes leverage plane-based explicit representations, addressing slow training times associated with models like neural radiance fields (NeRF) and Gaussian splatting (GS).
Plug-and-Play Performance Estimation for LLM Services without Relying on Labeled Data
This paper introduces a novel method to estimate the performance of LLM services across different tasks and contexts, which can be "plug-and-play" utilizing only a few unlabeled samples like ICL.
Performance and Non-adversarial Robustness of the Segment Anything Model 2 in Surgical Video Segmentation
Fully supervised deep learning (DL) models for surgical video segmentation have been shown to struggle with non-adversarial, real-world corruptions of image quality including smoke, bleeding, and low illumination.
SegSTRONG-C: Segmenting Surgical Tools Robustly On Non-adversarial Generated Corruptions -- An EndoVis'24 Challenge
To address this limitation, we introduce the SegSTRONG-C challenge that aims to promote the development of algorithms robust to unforeseen but plausible image corruptions of surgery, like smoke, bleeding, and low brightness.
Divide and Fuse: Body Part Mesh Recovery from Partially Visible Human Images
Traditional top-down methods, relying on whole-body parametric models like SMPL, falter when only a small part of the human is visible, as they require visibility of most of the human body for accurate mesh reconstruction.
DaReNeRF: Direction-aware Representation for Dynamic Scenes
However, the straightforward decomposition of 4D dynamic scenes into multiple 2D plane-based representations proves insufficient for re-rendering high-fidelity scenes with complex motions.
Logic-Scaffolding: Personalized Aspect-Instructed Recommendation Explanation Generation using LLMs
The unique capabilities of Large Language Models (LLMs), such as the natural language text generation ability, position them as strong candidates for providing explanation for recommendations.
Pre-trained Recommender Systems: A Causal Debiasing Perspective
In particular, we propose to develop a generic recommender that captures universal interaction patterns by training on generic user-item interaction data extracted from different domains, which can then be fast adapted to improve few-shot learning performance in unseen new domains (with limited data).
Personalized Federated Domain Adaptation for Item-to-Item Recommendation
To mitigate this data bottleneck, we postulate that recommendation patterns learned from existing mature market segments (with private data) could be adapted to build effective warm-start models for emerging ones.
GCNSLIM: Graph Convolutional Network with Sparse Linear Methods for E-government Service Recommendation
However, existing GCN-based CF methods are mainly based on matrix factorization and incorporate some optimization tech-niques to enhance performance, which are not enough to handle the complexities of diverse real-world recommendation scenarios.
Few-shot Medical Image Segmentation with Cycle-resemblance Attention
Recently, due to the increasing requirements of medical imaging applications and the professional requirements of annotating medical images, few-shot learning has gained increasing attention in the medical image semantic segmentation field.
Rethinking Causality-driven Robot Tool Segmentation with Temporal Constraints
Method: To address the above limitations, we take temporal relation into consideration and propose a temporal causal model for robot tool segmentation on video sequences.
Twin-S: A Digital Twin for Skull-base Surgery
Twin-S tracks and updates the virtual model in real-time given measurements from modern tracking technologies.
CaRTS: Causality-driven Robot Tool Segmentation from Vision and Kinematics Data
Vision-based segmentation of the robotic tool during robot-assisted surgery enables downstream applications, such as augmented reality feedback, while allowing for inaccuracies in robot kinematics.
Context Uncertainty in Contextual Bandits with Applications to Recommender Systems
Recurrent neural networks have proven effective in modeling sequential user feedbacks for recommender systems.
Language Models as Recommender Systems: Evaluations and Limitations
Pre-trained language models (PLMs) such as BERT and GPT learn general text representations and encode extensive world knowledge; thus, they can be efficiently and accurately adapted to various downstream tasks.
On the Sins of Image Synthesis Loss for Self-supervised Depth Estimation
It is based on the idea that observed frames can be synthesized from neighboring frames if accurate depth of the scene is known - or in this case, estimated.
Influence Selection for Active Learning
To obtain the Influence of the unlabeled sample in the active learning scenario, we design the Untrained Unlabeled sample Influence Calculation(UUIC) to estimate the unlabeled sample's expected gradient with which we calculate its Influence.
Zero-Shot Recommender Systems
This poses a chicken-and-egg problem for early-stage products, whose amount of data, in turn, relies on the performance of their RS.
Recurrent Exploration Networks for Recommender Systems
Recurrent neural networks have proven effective in modeling sequential user feedbacks for recommender systems.
Cross-View Image Synthesis with Deformable Convolution and Attention Mechanism
This is even more laborious when generating images with very different views.
Deeply Shape-guided Cascade for Instance Segmentation
The key to a successful cascade architecture for precise instance segmentation is to fully leverage the relationship between bounding box detection and mask segmentation across multiple stages.
Unsupervised Inductive Graph-Level Representation Learning via Graph-Graph Proximity
We introduce a novel approach to graph-level representation learning, which is to embed an entire graph into a vector space where the embeddings of two graphs preserve their graph-graph proximity.
Ranked #1 on
Graph Classification
on Web
Convolutional Set Matching for Graph Similarity
We introduce GSimCNN (Graph Similarity Computation via Convolutional Neural Networks) for predicting the similarity score between two graphs.
Learning-based Efficient Graph Similarity Computation via Multi-Scale Convolutional Set Matching
Since computing the exact distance/similarity between two graphs is typically NP-hard, a series of approximate methods have been proposed with a trade-off between accuracy and speed.
SimGNN: A Neural Network Approach to Fast Graph Similarity Computation
Our model achieves better generalization on unseen graphs, and in the worst case runs in quadratic time with respect to the number of nodes in two graphs.
Ranked #1 on
Graph Similarity
on IMDb
Multi-Way Multi-Level Kernel Modeling for Neuroimaging Classification
Owing to prominence as a diagnostic tool for probing the neural correlates of cognition, neuroimaging tensor data has been the focus of intense investigation.
Learning from Multi-View Multi-Way Data via Structural Factorization Machines
Real-world relations among entities can often be observed and determined by different perspectives/views.
