Search Results for author:
Found 26 papers, 15 papers with code
On Reasoning Strength Planning in Large Reasoning Models
We then uncover that LRMs encode this reasoning strength through a pre-allocated directional vector embedded in the activations of the model, where the vector's magnitude modulates the reasoning strength.
ChartGalaxy: A Dataset for Infographic Chart Understanding and Generation
We showcase the utility of this dataset through: 1) improving infographic chart understanding via fine-tuning, 2) benchmarking code generation for infographic charts, and 3) enabling example-based infographic chart generation.
Oral Imaging for Malocclusion Issues Assessments: OMNI Dataset, Deep Learning Baselines and Benchmarking
Malocclusion is a major challenge in orthodontics, and its complex presentation and diverse clinical manifestations make accurate localization and diagnosis particularly important.
CKMDiff: A Generative Diffusion Model for CKM Construction via Inverse Problems with Learned Priors
One fundamental problem for CKM-enabled wireless systems lies in how to construct high-quality and complete CKM for all locations of interest, based on only limited and noisy on-site channel knowledge data.
NoisyRollout: Reinforcing Visual Reasoning with Data Augmentation
Recent advances in reinforcement learning (RL) have strengthened the reasoning capabilities of vision-language models (VLMs).
CKMImageNet: A Dataset for AI-Based Channel Knowledge Map Towards Environment-Aware Communication and Sensing
With the increasing demand for real-time channel state information (CSI) in sixth-generation (6G) mobile communication networks, channel knowledge map (CKM) emerges as a promising technique, offering a site-specific database that enables environment-awareness and significantly enhances communication and sensing performance by leveraging a priori wireless channel knowledge.
ToolTipNet: A Segmentation-Driven Deep Learning Baseline for Surgical Instrument Tip Detection
Surgical instrument segmentation becomes relatively easy due to the emergence of the Segmentation Foundation Model, i. e., Segment Anything.
Point Tracking in Surgery--The 2024 Surgical Tattoos in Infrared (STIR) Challenge
Understanding tissue motion in surgery is crucial to enable applications in downstream tasks such as segmentation, 3D reconstruction, virtual tissue landmarking, autonomous probe-based scanning, and subtask autonomy.
Instrument-Splatting: Controllable Photorealistic Reconstruction of Surgical Instruments Using Gaussian Splatting
Real2Sim is becoming increasingly important with the rapid development of surgical artificial intelligence (AI) and autonomy.
SurgPose: a Dataset for Articulated Robotic Surgical Tool Pose Estimation and Tracking
Driven by this limitation, we collected a dataset, dubbed SurgPose, providing instance-aware semantic keypoints and skeletons for visual surgical tool pose estimation and tracking.
Generative CKM Construction using Partially Observed Data with Diffusion Model
Channel knowledge map (CKM) is a promising technique that enables environment-aware wireless networks by utilizing location-specific channel prior information to improve communication and sensing performance.
FunGrasp: Functional Grasping for Diverse Dexterous Hands
In our experiments, we demonstrate that our system enables diverse functional grasping of unseen objects using single RGBD images, and can be successfully deployed across various dexterous robot hands.
FATE: Full-head Gaussian Avatar with Textural Editing from Monocular Video
To the best of our knowledge, FATE is the first animatable and 360$^\circ$ full-head monocular reconstruction method for a 3D head avatar.
A-MFST: Adaptive Multi-Flow Sparse Tracker for Real-Time Tissue Tracking Under Occlusion
Methods: We use the Segment Anything Model2 (SAM2) to detect and mask occlusions by surgical tools, and we develop and integrate into SENDD an Adaptive Multi-Flow Sparse Tracker (A-MFST) with forward-backward consistency metrics, to enhance occlusion and uncertainty estimation.
InternLM2.5-StepProver: Advancing Automated Theorem Proving via Expert Iteration on Large-Scale LEAN Problems
We propose to use large scale LEAN problem datasets Lean-workbook for expert iteration with more than 20, 000 CPU days.
LEAN-GitHub: Compiling GitHub LEAN repositories for a versatile LEAN prover
To address this issue, we propose LEAN-GitHub, a dataset consisting of large-scale formal data extracted from almost all Lean 4 repositories on GitHub.
SegSTRONG-C: Segmenting Surgical Tools Robustly On Non-adversarial Generated Corruptions -- An EndoVis'24 Challenge
Surgical data science has seen rapid advancement due to the excellent performance of end-to-end deep neural networks (DNNs) for surgical video analysis.
Evolving Subnetwork Training for Large Language Models
In this paper, inspired by the redundancy in the parameters of large language models, we propose a novel training paradigm: Evolving Subnetwork Training (EST).
Lean Workbook: A large-scale Lean problem set formalized from natural language math problems
Our results indicate that the synthetic data pipeline can provide useful training data and improve the performance of LLMs in translating and understanding complex mathematical problems and proofs.
Augmenting Efficient Real-time Surgical Instrument Segmentation in Video with Point Tracking and Segment Anything
Inspired by this progress, we present a novel framework that combines an online point tracker with a lightweight SAM model that is fine-tuned for surgical instrument segmentation.
InternLM-Math: Open Math Large Language Models Toward Verifiable Reasoning
We further explore how to use LEAN to solve math problems and study its performance under the setting of multi-task learning which shows the possibility of using LEAN as a unified platform for solving and proving in math.
Domain Separation Graph Neural Networks for Saliency Object Ranking
Then we propose a Shape-Texture Graph Domain Separation (STGDS) module to separate the task-relevant and irrelevant information of target objects by explicitly modelling the relationship between each pair of objects in terms of their shapes and textures respectively.
SCTc-TE: A Comprehensive Formulation and Benchmark for Temporal Event Forecasting
Temporal complex event forecasting aims to predict the future events given the observed events from history.
Context-aware Event Forecasting via Graph Disentanglement
The task of event forecasting aims to model the relational and temporal patterns based on historical events and makes forecasting to what will happen in the future.
HyperCI: A Higher Order Collective Influence Measure for Hypernetwork Dismantling
However, conventional network dismantling approaches focus on simple network which models only pairwise interaction between nodes while groupwise interactions among arbitrary number of nodes are ubiquitous in networked systems like integrated circuits.
Social and Information Networks Physics and Society
