HD
Haiwen Diao
cs.CVcs.MMcs.AIcs.ROcs.LGcs.CL
On Valency
published · living versionsW_349p6bt8·v1 · currentpublished
DONIC: Generalist Dexterous Bimanual Tracking Control from Human Demonstrations
with Mingze Sun, Ziang Cao, Yuan Fei, Qiankuan Tao +6
1 version
Preprints & journals
35 papers in the corpus · 2021–2026DONIC: Generalist Dexterous Bimanual Tracking Control from Human Demonstrations2610.29997v1 · Mingze Sun, Ziang Cao, Yuan Fei et al.2026 · 0 citationsarXivon Valency
Has GPT-6-Astra Achieved Embodied Intelligence?2610.22471v2 · SenseNova, Zhongang Cai, Ziang Cao et al.2026 · 0 citationsarXiv
Game2Real-Bench: Do Toy Games Reveal and Transfer to Real-World Visual Reasoning?2610.18834v1 · Qingan Liu, Juntong Feng, Yue Zhu et al.2026 · 0 citationsarXiv
Plan-Bench: Can Existing VLMs Go Well Beyond Perception to Reason and Plan in Embodied Worlds?2610.18836v2 · Juntong Feng, Qingan Liu, Jingru Dong et al.2026 · 0 citationsarXiv
Think Before You Score: Thinking Reward Model for Visual Generation2609.37372v2 · Xuehai Bai, Zhenchen Tang, Yang Shi et al.2026 · 0 citationsarXiv
Learning Native Reflection in Unified Models with Interleaved Reinforcement Learning2609.35767v2 · Yijia Fan, Ziqi Huang, Zhongang Cai et al.2026 · 0 citationsarXiv
VABench: Measuring Embodied Spatial Intelligence through Visual Demonstrations, Active Perception, and Metric Control2609.19554v1 · Zhongbo Zhang, Jiayi Jin, Yifan Wang et al.2026 · 0 citationsarXiv
SenseNova-U1.5: Towards Native Unified Visual Intelligence2609.11929v1 · Haiwen Diao, Jiahao Wang, Chenjing Ding et al.2026 · 0 citationsarXiv
Uncovering Understanding-Generation Synergy in Native Unified Multimodal Models: From Representation, Task to System2609.01607v1 · Penghao Wu, Haiwen Diao, Weichen Fan et al.2026 · 0 citationsarXiv
V-Rubrics: Visual Faithfulness via Rubric-Based Reinforcement Learning2608.25580v1 · Shulin Tian, Minglun Li, Yuhao Dong et al.2026 · 0 citationsarXiv
VBVR-Pro: A Scalable and Verifiable Suite for Native Visual Reasoning2608.26105v2 · Junxiang Xu, Ruisi Wang, Fanyi Pu et al.2026 · 0 citationsarXiv
Vision as Unified Multimodal Generation2607.06560v1 · Xiaoyang Han, Jianhua Li, Kewang Deng et al.2026 · 0 citationsarXiv
ERA: Entropy-Guided Visual Token Pruning with Rectified Attention for Efficient MLLMs2606.31982v1 · Yuhao Wang, Mu Qiao, Haiwen Diao et al.2026 · 0 citationsarXiv
From Pixels to Words -- Towards Native One-Vision Models at Scale2605.28820v1 · Haiwen Diao, Jiahao Wang, Penghao Wu et al.2026 · 0 citationsarXiv
SenseNova-U1: Unifying Multimodal Understanding and Generation with NEO-unify Architecture2605.12500v1 · Haiwen Diao, Penghao Wu, Hanming Deng et al.2026 · 0 citationsarXiv
VISTA-Bench: Do Vision-Language Models Really Understand Visualized Text as Well as Pure Text?2602.04802v3 · Qing'an Liu, Juntong Feng, Yuhao Wang et al.2026 · 0 citationsarXiv
DynamicVLA: A Vision-Language-Action Model for Dynamic Object Manipulation2601.22153v2 · Haozhe Xie, Beichen Wen, Jiarui Zheng et al.2026 · 0 citationsarXiv
The Prism Hypothesis: Harmonizing Semantic and Pixel Representations via Unified Autoencoding2512.19693v5 · Weichen Fan, Haiwen Diao, Quan Wang et al.2025 · 0 citationsarXiv
Visual Jigsaw Post-Training Improves MLLMs2509.25190v1 · Penghao Wu, Yushan Zhang, Haiwen Diao et al.2025 · 0 citationsarXiv
Exploring Dynamic Transformer for Efficient Object Tracking.40173065 · Zhu, Jiawen, Chen, Xin, Diao, Haiwen et al.2025 · 19 citationsIEEE transactions on neural networks and learning systems. 2025;36(8):15502-15514
Regularizing Subspace Redundancy of Low-Rank Adaptation2507.20745v1 · Yue Zhu, Haiwen Diao, Shang Gao et al.2025 · 0 citationsarXiv
End-to-End Vision Tokenizer Tuning2505.10562v1 · Wenxuan Wang, Fan Zhang, Yufeng Cui et al.2025 · 0 citationsarXiv
KARST: Multi-Kernel Kronecker Adaptation with Re-Scaling Transmission for Visual Classification2502.06779v1 · Yue Zhu, Haiwen Diao, Shang Gao et al.2025 · 0 citationsarXiv
EVEv2: Improved Baselines for Encoder-Free Vision-Language Models2502.06788v2 · Haiwen Diao, Xiaotong Li, Yufeng Cui et al.2025 · 2 citationsarXiv
Autoregressive Video Generation without Vector Quantization2412.14169v2 · Haoge Deng, Ting Pan, Haiwen Diao et al.2024 · 0 citationsarXiv
MoTrans: Customized Motion Transfer with Text-driven Video Diffusion Models2412.01343v1 · Xiaomin Li, Xu Jia, Qinghe Wang et al.2024 · 7 citationsarXiv
LLMs Can Evolve Continually on Modality for X-Modal Reasoning2410.20178v2 · Jiazuo Yu, Haomiao Xiong, Lu Zhang et al.2024 · 1 citationarXiv
DenseFusion-1M: Merging Vision Experts for Comprehensive Multimodal Perception2407.08303v2 · Xiaotong Li, Fan Zhang, Haiwen Diao et al.2024 · 3 citationsarXiv
SHERL: Synthesizing High Accuracy and Efficient Memory for Resource-Limited Transfer Learning2407.07523v1 · Haiwen Diao, Bo Wan, Xu Jia et al.2024 · 5 citationsarXiv
Unveiling Encoder-Free Vision-Language Models2406.11832v2 · Haiwen Diao, Yufeng Cui, Xiaotong Li et al.2024 · 11 citationsarXiv
Deep Boosting Learning: A Brand-New Cooperative Approach for Image-Text Matching.38713578 · Diao, Haiwen, Zhang, Ying, Gao, Shang et al.2024 · 13 citationsIEEE transactions on image processing : a publication of the IEEE Signal Processing Society. 2024;33:3341-3352
GSSF: Generalized Structural Sparse Function for Deep Cross-Modal Metric Learning.39480717 · Diao, Haiwen, Zhang, Ying, Gao, Shang et al.2024 · 5 citationsIEEE transactions on image processing : a publication of the IEEE Signal Processing Society. 2024;33:6241-6252
UniPT: Universal Parallel Tuning for Transfer Learning with Efficient Parameter and Memory2308.14316v2 · Haiwen Diao, Bo Wan, Ying Zhang et al.2023 · 18 citationsarXiv
Plug-and-Play Regulators for Image-Text Matching.37071519 · Diao, Haiwen, Zhang, Ying, Liu, Wei et al.2023 · 46 citationsIEEE transactions on image processing : a publication of the IEEE Signal Processing Society. 2023;32:2322-2334
Similarity Reasoning and Filtration for Image-Text Matching2101.01368v1 · Haiwen Diao, Ying Zhang, Lin Ma et al.2021 · 387 citationsarXiv
Career total: 36 works. 35 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.