papers

Publications (31)

cs.RO2024

SLAM assisted 3D tracking system for laparoscopic surgery

Jingwei Song, Ray Zhang, Wenwei Zhang +2

A major limitation of minimally invasive surgery is the difficulty in accurately locating the internal anatomical structures of the target organ due to the lack of tactile feedback…

cs.RO2020

Efficient two step optimization for large embedded deformation graph based SLAM

Jingwei Song, Fang Bai, Liang Zhao +2

Embedded deformation nodes based formulation has been widely applied in deformable geometry and graphical problems. Though being promising in stereo (or RGBD) sensor based SLAM app…

cs.CV2022

BDIS: Bayesian Dense Inverse Searching Method for Real-Time Stereo Surgical Image Matching

Jingwei Song, Qiuchen Zhu, Jianyu Lin +1

In stereoscope-based Minimally Invasive Surgeries (MIS), dense stereo matching plays an indispensable role in 3D shape recovery, AR, VR, and navigation tasks. Although numerous Dee…

cs.CV2024

DynaWeightPnP: Toward global real-time 3D-2D solver in PnP without correspondences

Jingwei Song, Maani Ghaffari

This paper addresses a special Perspective-n-Point (PnP) problem: estimating the optimal pose to align 3D and 2D shapes in real-time without correspondences, termed as corresponden…

cs.CV2018

MIS-SLAM: Real-time Large Scale Dense Deformable SLAM System in Minimal Invasive Surgery Based on Heterogeneous Computing

Jingwei Song, Jun Wang, Liang Zhao +2

Real-time simultaneously localization and dense mapping is very helpful for providing Virtual Reality and Augmented Reality for surgeons or even surgical robots. In this paper, we…

cs.RO2024

VascularPilot3D: Toward a 3D fully autonomous navigation for endovascular robotics

Jingwei Song, Keke Yang, Han Chen +8

This research reports VascularPilot3D, the first 3D fully autonomous endovascular robot navigation system. As an exploration toward autonomous guidewire navigation, VascularPilot3D…

cs.CV2020

Curved Buildings Reconstruction from Airborne LiDAR Data by Matching and Deforming Geometric Primitives

Jingwei Song, Shaobo Xia, Jun Wang +1

Airborne LiDAR (Light Detection and Ranging) data is widely applied in building reconstruction, with studies reporting success in typical buildings. However, the reconstruction of…

cs.CV2020

Combining Deep Learning with Geometric Features for Image based Localization in the Gastrointestinal Tract

Jingwei Song, Mitesh Patel, Andreas Girgensohn +1

Tracking monocular colonoscope in the Gastrointestinal tract (GI) is a challenging problem as the images suffer from deformation, blurred textures, significant changes in appearanc…

cs.RO2017

Convergence and Consistency Analysis for A 3D Invariant-EKF SLAM

Teng Zhang, Kanzhi Wu, Jingwei Song +2

In this paper, we investigate the convergence and consistency properties of an Invariant-Extended Kalman Filter (RI-EKF) based Simultaneous Localization and Mapping (SLAM) algorith…

cs.RO2023

BDIS-SLAM: A lightweight CPU-based dense stereo SLAM for surgery

Jingwei Song, Ray Zhang, Qiuchen Zhu +2

Purpose: Common dense stereo Simultaneous Localization and Mapping (SLAM) approaches in Minimally Invasive Surgery (MIS) require high-end parallel computational resources for real-…

cs.AI2026

MineEvolve: Self-Evolution with Accumulated Knowledge for Long-Horizon Embodied Minecraft Agents

Zhengwei Xie, Zhisheng Chen, Ziyan Weng +7

Long-horizon embodied intelligence requires agents to improve through interaction, not merely to execute plans generated from static goals. A central challenge is therefore to tran…

cs.LG2026

ECHO-2: A Large-Scale Distributed Rollout Framework for Cost-Efficient Reinforcement Learning

Jingwei Song, Meng Chen, Jie Xiao +15

Reinforcement learning (RL) is a critical stage in post-training large language models (LLMs), involving repeated interaction between rollout generation, reward evaluation, and cen…

cs.CV2020

Dynamic Reconstruction of Deformable Soft-tissue with Stereo Scope in Minimal Invasive Surgery

Jingwei Song, Jun Wang, Liang Zhao +2

In minimal invasive surgery, it is important to rebuild and visualize the latest deformed shape of soft-tissue surfaces to mitigate tissue damages. This paper proposes an innovativ…

cs.AI2026

PolarMem: A Training-Free Polarized Latent Graph Memory for Verifiable Vision-Language Models

Zhisheng Chen, Tingyu Wu, Zijie Zhou +7

Memory is not merely a storage mechanism for intelligent systems, but a structure for organizing evidence and constraining belief. This is especially important for multimodal reaso…

cs.AI2026

Group Pattern Selection Optimization: Let LRMs Pick the Right Pattern for Reasoning

Hanbin Wang, Jingwei Song, Jinpeng Li +2

Large reasoning models (LRMs) exhibit diverse high-level reasoning patterns (e.g., direct solution, reflection-and-verification, and exploring multiple solutions), yet prevailing t…

cs.CL2026

PersonaTree: Structured Lifecycle Memory for Person Understanding in LLM Agents

Yubo Hou, Jingwei Song, Hongbo Zhang +4

Persistent LLM agents require memory representations that make the formation of person understanding explicit across long term interaction. Existing agent memory methods emphasize…

cs.RO2023

Optical flow-based vascular respiratory motion compensation

Keke Yang, Zheng Zhang, Meng Li +3

This paper develops a new vascular respiratory motion compensation algorithm, Motion-Related Compensation (MRC), to conduct vascular respiratory motion compensation by extrapolatin…

cs.CV2022

Bayesian dense inverse searching algorithm for real-time stereo matching in minimally invasive surgery

Jingwei Song, Qiuchen Zhu, Jianyu Lin +1

This paper reports a CPU-level real-time stereo matching method for surgical images (10 Hz on 640 * 480 image with a single core of i5-9400). The proposed method is built on the fa…

cs.LG2026

Staleness-Learning Rate Scaling Laws for Asynchronous RLHF

Jingwei Song, Haofeng Xu, Jie Xiao +8

High-throughput RLHF systems often decouple rollout generation from policy optimization, leading to the use of stale rollouts during learner updates. In this work, we study the eff…

cs.CV2022

Fusing Convolutional Neural Network and Geometric Constraint for Image-based Indoor Localization

Jingwei Song, Mitesh Patel, Maani Ghaffari

This paper proposes a new image-based localization framework that explicitly localizes the camera/robot by fusing Convolutional Neural Network (CNN) and sequential images' geometri…

cs.AI2026

Teaching Large Reasoning Models Effective Reflection

Hanbin Wang, Jingwei Song, Jinpeng Li +5

Large Reasoning Models (LRMs) have recently shown impressive performance on complex reasoning tasks, often by engaging in self-reflective behaviors such as self-critique and backtr…

cs.RO2020

Are We Ready for Service Robots? The OpenLORIS-Scene Datasets for Lifelong SLAM

Xuesong Shi, Dongjiang Li, Pengpeng Zhao +15

Service robots should be able to operate autonomously in dynamic and daily changing environments over an extended period of time. While Simultaneous Localization And Mapping (SLAM)…

cs.LG2026

Co-Evolution of Policy and Internal Reward for Language Agents

Xinyu Wang, Hanwei Wu, Jingwei Song +8

Large language model (LLM) agents learn by interacting with environments, but long-horizon training remains fundamentally bottlenecked by sparse and delayed rewards. Existing metho…

cs.DC2025

Speculative Decoding in Decentralized LLM Inference: Turning Communication Latency into Computation Throughput

Jingwei Song, Wanyi Chen, Xinyuan Song +7

Speculative decoding accelerates large language model (LLM) inference by using a lightweight draft model to propose tokens that are later verified by a stronger target model. While…

cs.CV2022

A Closed-Form Uncertainty Propagation in Non-Rigid Structure from Motion

Jingwei Song, Mitesh Patel, Ashkan Jasour +1

Semi-Definite Programming (SDP) with low-rank prior has been widely applied in Non-Rigid Structure from Motion (NRSfM). Based on a low-rank constraint, it avoids the inherent ambig…

eess.IV2022

Uncertainty Quantification for Hyperspectral Image Denoising Frameworks based on Low-rank Matrix Approximation

Jingwei Song, Shaobo Xia, Jun Wang +2

Sliding-window based low-rank matrix approximation (LRMA) is a technique widely used in hyperspectral images (HSIs) denoising or completion. However, the uncertainty quantification…

cs.CL2025

Code-Vision: Evaluating Multimodal LLMs Logic Understanding and Code Generation Capabilities

Hanbin Wang, Xiaoxuan Zhou, Zhipeng Xu +7

This paper introduces Code-Vision, a benchmark designed to evaluate the logical understanding and code generation capabilities of Multimodal Large Language Models (MLLMs). It chall…

cs.RO2019

An observable time series based SLAM algorithm for deforming environment

Jingwei Song, Liang Zhao, Shoudong Huang +1

In this paper, we study the back-end of simultaneous localization and mapping (SLAM) problem in deforming environment, where robot localizes itself and tracks multiple non-rigid so…

cs.RO2024

RKHS-BA: A Robust Correspondence-Free Multi-View Registration Framework with Semantic Point Clouds

Ray Zhang, Jingwei Song, Xiang Gao +5

This work reports a novel multi-frame Bundle Adjustment (BA) framework called RKHS-BA. It uses continuous landmark representations that encode RGB-D/LiDAR and semantic observations…

cs.RO2024

Iterative PnP and its application in 3D-2D vascular image registration for robot navigation

Jingwei Song, Keke Yang, Zheng Zhang +3

This paper reports on a new real-time robot-centered 3D-2D vascular image alignment algorithm, which is robust to outliers and can align nonrigid shapes. Few works have managed to…

cs.LG2026

MARS: Unleashing the Power of Speculative Decoding via Margin-Aware Verification

Jingwei Song, Xinyu Wang, Hanbin Wang +6

Speculative Decoding (SD) accelerates autoregressive large language model (LLM) inference by decoupling generation and verification. While recent methods improve draft quality by t…