Author archive

Chang Nie

Ph.D. Researcher (Final Year)

I am Chang Nie (聂畅), a final-year Ph.D. candidate in Control Science and Engineering at the School of Automation and Intelligent Sensing, Shanghai Jiao Tong University, advised by Prof. Hesheng Wang. I expect to defend my thesis in January 2027.

My research focuses on Embodied AI, VLM & LLM foundation models, and Robot Learning, specializing in end-to-end robot policies (VLA, WAM), VLM/LLM cognitive reasoning for robotics, AI Agent manipulation architectures, generative world models, and 3D perception, with physical robot deployment. Experienced in full-stack mobile dual-arm system integration and real-robot manipulation. Dedicated to driving closed-loop deployment of embodied foundation models (VLM/LLM/VLA), AI agents, and generative world models in physical environments.

Email Google Scholar LinkedIn

On this site

Authored works

11 results

A Franka robot reuses a taught skill to place an object into a container in a changed scene.

Publication 2026 T-RO

Teach and Grow: An Agent-Centered Architecture for General Robot Learning

Hierarchical AI Agent architecture for general robot manipulation, compiling sparse demonstrations into reusable Skill Blocks with frozen foundation backbones and physical self-healing.

Read paper story

VCGS-SLAM — A compact Gaussian map grows with the robot.

Publication 2026 IJCV

Voxelized 3D Gaussian Representation for Dense Visual SLAM on Embedded Vision System

Introduces a voxelized 3D Gaussian representation for dense visual SLAM on embedded vision platforms, combining redundancy pruning and attribute quantization for compact mapping and tracking.

Read paper story

MID — Iterative recovery across data modalities.

Publication 2026 TNNLS

MID: A Self-Supervised Multimodal Iterative Denoising Framework

Presents a self-supervised multimodal iterative denoising framework that learns corruption-stage estimation and residual reversal from noisy data alone without clean ground truth.

Read paper story

HEAR — A physical robot policy using causal acoustic memory and multimodal flow matching.

Publication 2026 IJRR

Towards the Vision-Sound-Language-Action Paradigm: The HEAR Framework for Sound-Centric Manipulation

First to extend Vision-Language-Action (VLA) models to Vision-Sound-Language-Action (VSLA) for manipulation, coupling causal audio memory and flow matching for sound-centric control.

Read paper story

MRASFM — Multiple cameras and journeys form a shared map.

Publication 2026 ICRA

MRASfM: Multi-Camera Reconstruction and Aggregation through Structure-from-Motion in Driving Scenes

Adapts multi-camera Structure-from-Motion to autonomous driving scenes, combining rigid multi-camera geometry, road-surface filtering, and multi-run spatiotemporal map aggregation.

Read paper story

MOVSAM — Scene semantics guide object segmentation.

Publication 2025 IROS

MovSAM: A Single-image Moving Object Segmentation Framework Based on Deep Thinking

Coupling VLM cognitive reasoning with foundation models for single-image moving object segmentation without optical flow.

Read paper story

ERMV — Consistent views of a recorded robot action.

Publication 2025 TCSVT

ERMV: Editing 4D Robotic Multi-view images to enhance embodied agents

A 4D multi-view generative world model for robot demonstration augmentation, editing spatiotemporal appearances while strictly preserving recorded physical actions for downstream VLA policies.

Read paper story

LNR — Shared observations, overlapping geometric regions.

Publication 2024 TPAMI

Robust Multi-Model Fitting through Learning Neighbor Regions

Presents LNR, a coarse-to-fine robust multi-model fitting framework that screens minimal sample sets and refines hypothesis neighborhoods to overcome combinatorial explosion under multi-structure overlap.

Read paper story

DIFFSAC — Diffusion refines confidence over candidate observations.

Publication 2024 IJCV

DiffSAC: Diffusion-guided Sampling for Consensus-based Robust Estimation

Proposes a geometry-conditioned diffusion paradigm for sample consensus, iteratively refining candidate minimal sets to achieve robust estimation under extreme outlier ratios.

Read paper story

RLSAC — Learning to sample from geometric feedback.

Publication 2023 ICCV

RLSAC: Reinforcement Learning Enhanced Sample Consensus for End-to-End Robust Estimation

Reinforcement-learning-guided hypothesis sampling for consensus-based robust estimation under extreme outlier ratios.

Read paper story

DTFI — Fused observations support continuous vehicle tracking.

Publication 2023 TETCI

3D Object Detection and Tracking Based on Lidar-Camera Fusion and IMM-UKF Algorithm Towards Highway Driving

DTFI combines local LiDAR-camera feature fusion with IMM-UKF multiple-model filtering for 3D vehicle detection and tracking in highway driving.

Read paper story