Researcher — paper.dinq.me

Large Language Models (LLMs) have demonstrated remarkable capabilities in reasoning and generation, serving as the foundation for advanced persona simulation and Role-Playing Language Agents (RPLAs). However, achieving authentic alignment with human cognitive and behavioral patterns remains a cri...

社会与人本推理评测与基准OpenReview 项目页

作者位次 #3/5SIGGRAPH 2026Oral· Computer Graphics (Conference Track)

PureSample: Neural Materials Learned by Sampling Microgeometry

Zixuan Li · Zixiong Wang · Jian Yang · Miloš Hašan · Beibei Wang

OpenReview

作者位次 #7/7ICRA 2026Oral· Robotics & Automation

Self-Supervised Point Cloud Single Object Tracking

Yuheng Liu · Le Hui · Ziyue Zhu · Shaohui Mei · Yigong Zhang · Jin Xie · Jian Yang

OpenReview

作者位次 #4/5ICRA 2026Oral· Robotics & Automation

VGGT-Long: Chunk it, Loop it, Align it - Pushing VGGT's Limits on Kilometer-scale Long RGB Sequences

Kai Deng · Zexin Ti · Jiawei Xu · Jian Yang · Jin Xie

对齐与偏好OpenReview

作者位次 #5/7IROS 2026Poster· Robustness in 3D Semantic Scene Perception

Multi-Modal Complementary Fusion for RGB-Thermal Semantic Segmentation

jiawei Liu · Ming Gao · Shuo Gu · Yigong Zhang · Jian Yang · Hui Kong · Jin Xie

多模态Semantic Scene UnderstandingSensor FusionOpenReview

作者位次 #5/5AAAI 2026Poster· Artificial Intelligence

RMLer: Synthesizing Novel Objects Across Diverse Categories via Reinforcement Mixing Learning

Jun Li · Zikun Chen · Haibo Chen · Shuo Chen · Jian Yang

强化学习与后训练OpenReview

作者位次 #8/8AAAI 2026Poster· Artificial Intelligence

SM3Det: A Unified Model for Multi-Modal Remote Sensing Object Detection

Yuxuan Li · Xiang Li · Yunheng Li · Yicheng Zhang · Yimian Dai · Qibin Hou · Ming-Ming Cheng · Jian Yang

多模态OpenReview

作者位次 #6/6AAAI 2026Poster· Artificial Intelligence

Diffusion-Based Contextual Reconstruction for Point Cloud Segmentation with Limited Annotations

Jiawei Lian · Zhengxue Wang · Wentao Qu · Haobo Jiang · Le Hui · Jian Yang

OpenReview

作者位次 #3/4AAAI 2026Poster· Artificial Intelligence

Small but Mighty: Dynamic Wavelet Expert-Guided Fine-Tuning of Large-Scale Models for Optical Remote Sensing Object Segmentation

Yanguang Sun · Chao Wang · Jian Yang · Lei Luo

强化学习与后训练OpenReview

作者位次 #5/5AAAI 2026Poster· Artificial Intelligence

SpatioTemporal Difference Network for Video Depth Super-Resolution

Zhengxue Wang · Yuan Wu · Xiang Li · Zhiqiang Yan · Jian Yang

多模态OpenReview

作者位次 #5/5AAAI 2026Poster· Artificial Intelligence

Shaping Without Tearing: Controllable Diffeomorphic Deformations for Topology-Preserving 3D Point Cloud Augmentation

Jian Bi · Qianliang Wu · Jianjun Qian · Lei Luo · Jian Yang

OpenReview

Jian Yang

获取完整研究档案

联系方式

2026 顶会论文

MotionSight: Boosting Fine-Grained Motion Understanding in Multimodal LLMs

CoDi: Subject-Consistent and Pose-Diverse Text-to-Image Generation

Accelerating Autoregressive Video Diffusion via History-Guided Cache and Residual Correction

DVAR: Dynamic Visual Autoregressive Modeling for Image Super-Resolution

Muses: Designing, Composing, Generating Nonexistent Fantasy 3D Creatures without Training

FabricGen: Microstructure-Aware Woven Fabric Generation

MorphAny3D: Unleashing the Power of Structured Latent in 3D Morphing

VINS-120K: Ultra High-Resolution Image Editing with A Large-Scale Dataset

Adaptive Depth Lightweight RGB-T Tracking with Holistic Token Routing

Bezier Degradation Modeling for LiDAR-based Human Motion Capture

H uman LLM : Benchmarking and Improving LLM Anthropomorphism via Human Cognitive Patterns

PureSample: Neural Materials Learned by Sampling Microgeometry

Self-Supervised Point Cloud Single Object Tracking

VGGT-Long: Chunk it, Loop it, Align it - Pushing VGGT's Limits on Kilometer-scale Long RGB Sequences

Multi-Modal Complementary Fusion for RGB-Thermal Semantic Segmentation

RMLer: Synthesizing Novel Objects Across Diverse Categories via Reinforcement Mixing Learning

SM3Det: A Unified Model for Multi-Modal Remote Sensing Object Detection

Diffusion-Based Contextual Reconstruction for Point Cloud Segmentation with Limited Annotations

Small but Mighty: Dynamic Wavelet Expert-Guided Fine-Tuning of Large-Scale Models for Optical Remote Sensing Object Segmentation

SpatioTemporal Difference Network for Video Depth Super-Resolution

Shaping Without Tearing: Controllable Diffeomorphic Deformations for Topology-Preserving 3D Point Cloud Augmentation

常见合作者