JM
Jianbiao Mei
cs.CVcs.AIcs.ROcs.CLcs.LG
On Valency
published · living versionsW_ap69b7ug·v1 · currentpublished
Sage-A1.5: From Long-Horizon Execution to Scientific Exploration with Capability Composition
with Wenjie Lou, Tianshuo Peng, Shiyang Feng, Shengji Tang +94
1 version
Preprints & journals
36 papers in the corpus · 2021–2026Sage-A1.5: From Long-Horizon Execution to Scientific Exploration with Capability Composition2610.28578v1 · Wenjie Lou, Tianshuo Peng, Shiyang Feng et al.2026 · 0 citationsarXivon Valency
Rethinking Relative Policy Differences Transfer of On-Policy Distillation2610.13205v1 · Rong Wu, Daocheng Fu, Yu Yang et al.2026 · 0 citationsarXiv
Quo Vadis, World Modeling?2608.02713v1 · Yu Yang, Xuemeng Yang, Licheng Wen et al.2026 · 0 citationsarXiv
MemHarness: Memory Is Reconstructed, Not Replayed2607.28272v1 · Rong Wu, Daocheng Fu, Licheng Wen et al.2026 · 0 citationsarXiv
Proxy OPD: On-Policy Distillation with Transferable Relative Proxy Update2607.11505v2 · Daocheng Fu, Rong Wu, Yu Yang et al.2026 · 0 citationsarXiv
SPIKE: An Adaptive Dual Controller Framework for Cost-Efficient Long-Horizon Game Agents2605.18636v1 · Wencan Jiang, Jiangning Zhang, Jianbiao Mei et al.2026 · 0 citationsarXiv
LeapVAD: A Leap in Autonomous Driving via Cognitive Perception and Dual-Process Thinking.41343328 · Ma, Yukai, Wei, Tiantian, Zhong, Naiting et al.2026 · 5 citationsIEEE transactions on neural networks and learning systems. 2026;37(4):1963-1977
SPIRAL: Self-Evolving Action-Conditioned Video Generation via Reflective Planning Agents2603.08403v3 · Yu Yang, Yue Liao, Jianbiao Mei et al.2026 · 0 citationsarXiv
The Agent's First Day: Benchmarking Learning, Exploration, and Scheduling in the Workplace Scenarios2601.08173v2 · Daocheng Fu, Jianbiao Mei, Rong Wu et al.2026 · 0 citationsarXiv
UR-Bench: A Benchmark for Multi-Hop Reasoning over Ultra-High-Resolution Images2601.08748v1 · Siqi Li, Xinyu Cai, Jianbiao Mei et al.2025 · 0 citationsarXiv
Vision-Centric 4D Occupancy Forecasting and Planning via Implicit Residual World Models2510.16729v3 · Jianbiao Mei, Yu Yang, Xuemeng Yang et al.2025 · 0 citationsarXiv
EvolveR: Self-Evolving LLM Agents through an Experience-Driven Lifecycle2510.16079v3 · Rong Wu, Xiaoman Wang, Jianbiao Mei et al.2025 · 0 citationsarXiv
Learning on the Job: An Experience-Driven Self-Evolving Agent for Long-Horizon Tasks2510.08002v1 · Cheng Yang, Xuemeng Yang, Licheng Wen et al.2025 · 0 citationsarXiv
RE-Searcher: Robust Agentic Search with Goal-oriented Planning and Self-reflection2509.26048v2 · Daocheng Fu, Jianbiao Mei, Licheng Wen et al.2025 · 0 citationsarXiv
IWR-Bench: Can LVLMs reconstruct interactive webpage from a user interaction video?2509.24709v3 · Yang Chen, Minghao Liu, Yufan Shen et al.2025 · 0 citationsarXiv
3D and 4D World Modeling: A Survey2509.07996v4 · Lingdong Kong, Yu Yang, Jianbiao Mei et al.2025 · 1 citationarXiv
CogDDN: A Cognitive Demand-Driven Navigation with Decision Optimization and Dual-Process Thinking2507.11334v2 · Yuehao Huang, Liang Liu, Shuangming Lei et al.2025 · 2 citationsarXiv
X-Scene: Large-Scale Driving Scene Generation with High Fidelity and Flexible Controllability2506.13558v3 · Yu Yang, Alan Liang, Jianbiao Mei et al.2025 · 5 citationsarXiv
KG-TRACES: Enhancing Large Language Models with Knowledge Graph-constrained Trajectory Reasoning and Attribution Supervision2506.00783v2 · Rong Wu, Pinlong Cai, Jianbiao Mei et al.2025 · 0 citationsarXiv
O-Searcher: A Searching-based Agent Model for Open-Domain Open-Ended Question Answering2505.16582v2 · Jianbiao Mei, Tao Hu, Daocheng Fu et al.2025 · 0 citationsarXiv
ActionCLIP: Adapting Language-Image Pretrained Models for Video Action Recognition.37988204 · Wang, Mengmeng, Xing, Jiazheng, Mei, Jianbiao et al.2025 · 112 citationsIEEE transactions on neural networks and learning systems. 2025;36(1):625-637
DreamForge: Motion-Aware Autoregressive Video Generation for Multi-View Driving Scenes2409.04003v4 · Jianbiao Mei, Tao Hu, Xuemeng Yang et al.2024 · 0 citationsarXiv
DQFormer: Towards Unified LiDAR Panoptic Segmentation with Decoupled Queries2408.15813v1 · Yu Yang, Jianbiao Mei, Liang Liu et al.2024 · 0 citationsarXiv
Driving in the Occupancy World: Vision-Centric 4D Occupancy Forecasting and Planning via World Models for Autonomous Driving2408.14197v3 · Yu Yang, Jianbiao Mei, Yukai Ma et al.2024 · 17 citationsarXiv
LiCROcc: Teach Radar for Accurate Semantic Occupancy Prediction using LiDAR and Camera2407.16197v1 · Yukai Ma, Jianbiao Mei, Xuemeng Yang et al.2024 · 7 citationsarXiv
Continuously Learning, Adapting, and Improving: A Dual-Process Approach to Autonomous Driving2405.15324v2 · Jianbiao Mei, Yukai Ma, Xuemeng Yang et al.2024 · 15 citationsarXiv
M2-CLIP: A Multimodal, Multi-task Adapting Framework for Video Action Recognition2401.11649v1 · Mengmeng Wang, Jiazheng Xing, Boyuan Jiang et al.2024 · 4 citationsAAAI2024
Camera-Based 3D Semantic Scene Completion With Sparse Guidance Network.39325598 · Mei, Jianbiao, Yang, Yu, Wang, Mengmeng et al.2024 · 24 citationsIEEE transactions on image processing : a publication of the IEEE Signal Processing Society. 2024;33:5468-5481
CR-SFP: Learning Consistent Representation for Soft Filter Pruning2312.11555v1 · Jingyang Xiang, Zhuangzhi Chen, Jianbiao Mei et al.2023 · 0 citationsarXiv
PANet: LiDAR Panoptic Segmentation with Sparse Instance Proposal and Aggregation2306.15348v1 · Jianbiao Mei, Yu Yang, Mengmeng Wang et al.2023 · 5 citationsarXiv
SSC-RS: Elevate LiDAR Semantic Scene Completion with Representation Separation and BEV Fusion2306.15349v1 · Jianbiao Mei, Yu Yang, Mengmeng Wang et al.2023 · 27 citationsarXiv
A Coarse-to-Fine Place Recognition Approach using Attention-guided Descriptors and Overlap Estimation2303.06881v3 · Chencan Fu, Lin Li, Jianbiao Mei et al.2023 · 6 citationsarXiv
E-NeRV: Expedite Neural Video Representation with Disentangled Spatial-Temporal Context2207.08132v1 · Zizhang Li, Mengmeng Wang, Huaijin Pi et al.2022 · 105 citationsarXiv
Delving Deeper Into Mask Utilization in Video Object Segmentation.36166565 · Wang, Mengmeng, Mei, Jianbiao, Liu, Lina et al.2022 · 17 citationsIEEE transactions on image processing : a publication of the IEEE Signal Processing Society. 2022;31:6255-6266
MaIL: A Unified Mask-Image-Language Trimodal Network for Referring Image Segmentation2111.10747v2 · Zizhang Li, Mengmeng Wang, Jianbiao Mei et al.2021 · 9 citationsarXiv
TransVOS: Video Object Segmentation with Transformers2106.00588v2 · Jianbiao Mei, Mengmeng Wang, Yeneng Lin et al.2021 · 22 citationsarXiv
Career total: 50 works. 36 are in this corpus.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.