2025

MiroThinker: Pushing the Performance Boundaries of Open-Source Research Agents via Model, Context, and Interactive Scaling

MM Team, S Bai, L Bing, C Chen, G Chen, Y Chen, Z Chen, J Dai, et al.

arXiv preprint 2025

MiroThinker scales open-source research agents along three dimensions—model capacity, context length, and interactive reasoning—achieving state-of-the-art performance on research agent benchmarks.

MiroThinker: Pushing the Performance Boundaries of Open-Source Research Agents via Model, Context, and Interactive Scaling

MM Team, S Bai, L Bing, C Chen, G Chen, Y Chen, Z Chen, J Dai, et al.

arXiv preprint 2025

MiroThinker scales open-source research agents along three dimensions—model capacity, context length, and interactive reasoning—achieving state-of-the-art performance on research agent benchmarks.

4D-VLA: Spatiotemporal Vision-Language-Action Pretraining with Cross-Scene Calibration

J Zhang, Y Chen, Y Xu, Z Huang, Yanpeng Zhou, YJ Yuan, X Cai, G Huang, et al.

Neural Information Processing Systems (NeurIPS) 2025

4D-VLA introduces spatiotemporal pretraining for Vision-Language-Action models with cross-scene calibration, enabling embodied agents to better understand and act in dynamic 3D environments.

4D-VLA: Spatiotemporal Vision-Language-Action Pretraining with Cross-Scene Calibration

J Zhang, Y Chen, Y Xu, Z Huang, Yanpeng Zhou, YJ Yuan, X Cai, G Huang, et al.

Neural Information Processing Systems (NeurIPS) 2025

4D-VLA introduces spatiotemporal pretraining for Vision-Language-Action models with cross-scene calibration, enabling embodied agents to better understand and act in dynamic 3D environments.

From Flatland to Space: Teaching Vision-Language Models to Perceive and Reason in 3D

J Zhang, Y Chen, Yanpeng Zhou, Y Xu, Z Huang, J Mei, J Chen, YJ Yuan, X Cai, et al.

Neural Information Processing Systems (NeurIPS) 2025

We propose a framework that lifts Vision-Language Models from 2D flat image understanding to full 3D spatial perception and reasoning, bridging the gap between visual recognition and geometric understanding.

From Flatland to Space: Teaching Vision-Language Models to Perceive and Reason in 3D

J Zhang, Y Chen, Yanpeng Zhou, Y Xu, Z Huang, J Mei, J Chen, YJ Yuan, X Cai, et al.

Neural Information Processing Systems (NeurIPS) 2025

We propose a framework that lifts Vision-Language Models from 2D flat image understanding to full 3D spatial perception and reasoning, bridging the gap between visual recognition and geometric understanding.

Does Your 3D Encoder Really Work? When Pretrain-SFT from 2D VLMs Meets 3D VLMs

H Li, Yanpeng Zhou, Y Gao, T Tang, J Han, Y Yuan, DZ Chen, J Bian, H Xu, et al.

arXiv preprint 2025

We rigorously evaluate 3D encoders by examining what happens when 2D VLM pretrain-SFT pipelines are adapted for 3D VLMs, revealing critical gaps and insights for 3D visual encoder design.

Does Your 3D Encoder Really Work? When Pretrain-SFT from 2D VLMs Meets 3D VLMs

H Li, Yanpeng Zhou, Y Gao, T Tang, J Han, Y Yuan, DZ Chen, J Bian, H Xu, et al.

arXiv preprint 2025

We rigorously evaluate 3D encoders by examining what happens when 2D VLM pretrain-SFT pipelines are adapted for 3D VLMs, revealing critical gaps and insights for 3D visual encoder design.

UniUGG: Unified 3D Understanding and Generation via Geometric-Semantic Encoding

Y Xu, J Zhang, Z Huang, Y Chen, Yanpeng Zhou, Z Chen, YJ Yuan, P Xia, et al.

International Conference on Learning Representations (ICLR) 2025

UniUGG presents a unified framework for 3D scene understanding and generation by jointly encoding geometric structure and semantic content, enabling coherent cross-task 3D reasoning.

UniUGG: Unified 3D Understanding and Generation via Geometric-Semantic Encoding

Y Xu, J Zhang, Z Huang, Y Chen, Yanpeng Zhou, Z Chen, YJ Yuan, P Xia, et al.

International Conference on Learning Representations (ICLR) 2025

UniUGG presents a unified framework for 3D scene understanding and generation by jointly encoding geometric structure and semantic content, enabling coherent cross-task 3D reasoning.

UniGS: Unified Language-Image-3D Pretraining with Gaussian Splatting

H Li, Yanpeng Zhou, T Tang, J Song, Y Zeng, M Kampffmeyer, H Xu, X Liang

International Conference on Learning Representations (ICLR) 2025

UniGS unifies language, image, and 3D understanding through pretraining with Gaussian Splatting representations, enabling a single model to reason across all three modalities.

UniGS: Unified Language-Image-3D Pretraining with Gaussian Splatting

H Li, Yanpeng Zhou, T Tang, J Song, Y Zeng, M Kampffmeyer, H Xu, X Liang

International Conference on Learning Representations (ICLR) 2025

UniGS unifies language, image, and 3D understanding through pretraining with Gaussian Splatting representations, enabling a single model to reason across all three modalities.

VidCraft3: Camera, Object, and Lighting Control for Image-to-Video Generation

S Zheng, Z Peng, Yanpeng Zhou, Y Zhu, H Xu, X Huang, Y Fu

arXiv preprint 2025

VidCraft3 enables fine-grained control over camera movement, object motion, and lighting conditions in image-to-video generation, advancing controllable video synthesis.

VidCraft3: Camera, Object, and Lighting Control for Image-to-Video Generation

S Zheng, Z Peng, Yanpeng Zhou, Y Zhu, H Xu, X Huang, Y Fu

arXiv preprint 2025

VidCraft3 enables fine-grained control over camera movement, object motion, and lighting conditions in image-to-video generation, advancing controllable video synthesis.

2024

UNIT: Unifying Image and Text Recognition in One Vision Encoder

Y Zhu, Yanpeng Zhou, C Wang, Y Cao, J Han, L Hou, H Xu

Neural Information Processing Systems (NeurIPS) 2024

UNIT is a unified vision encoder that jointly handles image and text recognition tasks within a single model, enabling versatile visual understanding without task-specific architectures.

UNIT: Unifying Image and Text Recognition in One Vision Encoder

Y Zhu, Yanpeng Zhou, C Wang, Y Cao, J Han, L Hou, H Xu

Neural Information Processing Systems (NeurIPS) 2024

UNIT is a unified vision encoder that jointly handles image and text recognition tasks within a single model, enabling versatile visual understanding without task-specific architectures.

2022

Investigating Robustness of Biological vs. Backprop Based Learning

Yanpeng Zhou, M Wang, M Gupta, A Ambikapathi, PN Suganthan, S Ramasamy

IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) 2022

We compare the robustness of biologically-inspired learning rules against backpropagation-based methods, evaluating their performance and resilience under various conditions.

Investigating Robustness of Biological vs. Backprop Based Learning

Yanpeng Zhou, M Wang, M Gupta, A Ambikapathi, PN Suganthan, S Ramasamy

IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) 2022

We compare the robustness of biologically-inspired learning rules against backpropagation-based methods, evaluating their performance and resilience under various conditions.

AI as an Active Writer: Interaction Strategies with Generated Text in Human-AI Collaborative Fiction Writing

D Yang, Yanpeng Zhou, Z Zhang, TJJ Li, R Lc

Joint Proceedings of the ACM IUI Workshops 2022

We explore interaction strategies between human writers and AI-generated text in collaborative fiction writing, examining how positioning AI as an active writer changes the creative process.

AI as an Active Writer: Interaction Strategies with Generated Text in Human-AI Collaborative Fiction Writing

D Yang, Yanpeng Zhou, Z Zhang, TJJ Li, R Lc

Joint Proceedings of the ACM IUI Workshops 2022

We explore interaction strategies between human writers and AI-generated text in collaborative fiction writing, examining how positioning AI as an active writer changes the creative process.

2020

Flexible Radiative Cooling Material Based on Amorphous Alumina Nanotubes

Yanpeng Zhou, Y Liu, Y Li, R Jiang, W Li, W Zhao, R Mao, L Deng, P Zhou

Optical Materials Express 2020

We present a flexible radiative cooling material based on amorphous alumina nanotubes that achieves passive cooling through selective thermal emission in the atmospheric transparency window.

Flexible Radiative Cooling Material Based on Amorphous Alumina Nanotubes

Yanpeng Zhou, Y Liu, Y Li, R Jiang, W Li, W Zhao, R Mao, L Deng, P Zhou

Optical Materials Express 2020

We present a flexible radiative cooling material based on amorphous alumina nanotubes that achieves passive cooling through selective thermal emission in the atmospheric transparency window.

2019

Effect of Deposition Potential and Concentration of Electroactive Substances on Bi2Te3 Nanowires Fabricated by Electrochemical Method

L Wenxin, Z Wangchen, Yanpeng Zhou, L Yanning, L Ya, J Ruomei, Z Linbo

Nanotechnology 2019

We investigate the effect of deposition potential and electroactive substance concentration on Bi2Te3 nanowires fabricated via electrochemical deposition, providing insights into controlled synthesis of thermoelectric nanomaterials.

Effect of Deposition Potential and Concentration of Electroactive Substances on Bi2Te3 Nanowires Fabricated by Electrochemical Method

L Wenxin, Z Wangchen, Yanpeng Zhou, L Yanning, L Ya, J Ruomei, Z Linbo

Nanotechnology 2019

We investigate the effect of deposition potential and electroactive substance concentration on Bi2Te3 nanowires fabricated via electrochemical deposition, providing insights into controlled synthesis of thermoelectric nanomaterials.