CX
Cihang Xie
cs.CVcs.AIcs.CLcs.LGcs.CRstat.MLcs.CYeess.IVcs.NEcs.RO
On Valency
published · living versionsW_eup5mama·v1 · currentpublished
ALPS: Visual State Encoders for World Models
with Yanqing Liu, Letian Zhang, Chengzhi Liu, Zijun Wang +3
1 version
Preprints & journals
103 papers in the corpus · 2015–2026VLAA-GUI: Knowing When to Stop, Recover, and Search, A Modular Framework for GUI Automation2604.21375v3 · Qijun Han, Haoqin Tu, Zijun Wang et al.2026 · 0 citationsarXiv
SkillRL: Evolving Agents via Recursive Skill-Augmented Reinforcement Learning2602.08234v2 · Peng Xia, Jianwen Chen, Hanyang Wang et al.2026 · 0 citationsarXiv
ViT-5: Vision Transformers for The Mid-2020s2602.08071v1 · Feng Wang, Sucheng Ren, Tiezheng Zhang et al.2026 · 0 citationsarXiv
Reliable and Responsible Foundation Models: A Comprehensive Survey2602.08145v1 · Xinyu Yang, Junlin Han, Rishi Bommasani et al.2026 · 0 citationsarXiv
Spiral RoPE: Rotate Your Rotary Positional Embeddings in the 2D Plane2602.03227v1 · Haoyu Liu, Sucheng Ren, Tingyu Zhu et al.2026 · 0 citationsarXiv
OpenVision 3: A Family of Unified Visual Encoder for Both Understanding and Generation2601.15369v2 · Letian Zhang, Sucheng Ren, Yanqing Liu et al.2026 · 0 citationsarXiv
A Unified and Controllable Framework for Layered Image Generation with Visual Effects2601.15507v2 · Jinrui Yang, Qing Liu, Yijun Li et al.2026 · 0 citationsarXiv
SimpleMem: Efficient Lifelong Memory for LLM Agents2601.02553v3 · Jiaqi Liu, Yaofeng Su, Peng Xia et al.2026 · 0 citationsarXiv
LightFusion: A Light-weighted, Double Fusion Framework for Unified Multimodal Understanding and Generation2510.22946v4 · Zeyu Wang, Zilong Chen, Chenhui Gou et al.2025 · 0 citationsarXiv
Alignment Tipping Process: How Self-Evolution Pushes LLM Agents Off the Rails2510.04860v2 · Siwei Han, Kaiwen Xiong, Jiaqi Liu et al.2025 · 0 citationsarXiv
CHAI: Command Hijacking against embodied AI2510.00181v2 · Luis Burbano, Diego Ortiz, Qi Sun et al.2025 · 1 citationarXiv
OpenVision 2: A Family of Generative Pretrained Visual Encoders for Multimodal Learning2509.01644v1 · Yanqing Liu, Xianhang Li, Letian Zhang et al.2025 · 0 citationsarXiv
AHELM: A Holistic Evaluation of Audio-Language Models2508.21376v2 · Tony Lee, Haoqin Tu, Chi Heem Wong et al.2025 · 1 citationarXiv
GPT-IMAGE-EDIT-1.5M: A Million-Scale, GPT-Generated Image Dataset2507.21033v1 · Yuhan Wang, Siwei Yang, Bingchen Zhao et al.2025 · 0 citationsarXiv
Scaling Laws in Patchification: An Image Is Worth 50,176 Tokens And More.41909270 · Wang, Feng, Yu, Yaodong, Shao, Wei et al.2026 · 3 citationsProceedings of machine learning research. 2025;267:65278-65290
Knowledge or Reasoning? A Close Look at How LLMs Think Across Domains2506.02126v1 · Juncheng Wu, Sheng Liu, Haoqin Tu et al.2025 · 0 citationsarXiv
Adventurer: Optimizing Vision Mamba Architecture Designs for Efficiency.41179969 · Wang, Feng, Yang, Timing, Yu, Yaodong et al.2026 · 1 citationProceedings. IEEE Computer Society Conference on Computer Vision and Pattern Recognition. 2025;2025:30157-30166
Mamba-Reg: Vision Mamba Also Needs Registers.41394344 · Wang, Feng, Wang, Jiahao, Ren, Sucheng et al.2026 · 23 citationsProceedings. IEEE Computer Society Conference on Computer Vision and Pattern Recognition. 2025;2025:14944-14953
Robust and Efficient AI-Based Attack Recovery in Autonomous Drones2505.14835v1 · Diego Ortiz Barbosa, Luis Burbano, Siwei Yang et al.2025 · 0 citationsarXiv
OpenVision: A Fully-Open, Cost-Effective Family of Advanced Vision Encoders for Multimodal Learning2505.04601v1 · Xianhang Li, Yanqing Liu, Haoqin Tu et al.2025 · 2 citationsarXiv
: CoT-Like Instruction Generation for Complexity-Controllable Image Editing Benchmark2504.13143v1 · Siwei Yang, Mude Hui, Bingchen Zhao et al.2025 · 0 citationsarXiv
SFT or RL? An Early Investigation into Training R1-Like Reasoning Large Vision-Language Models2504.11468v1 · Hardy Chen, Haoqin Tu, Fali Wang et al.2025 · 0 citationsarXiv
STAR-1: Safer Alignment of Reasoning LLMs with 1K Data2504.01903v2 · Zijun Wang, Haoqin Tu, Yuhan Wang et al.2025 · 3 citationsarXiv
ViLBench: A Suite for Vision-Language Process Reward Modeling2503.20271v1 · Haoqin Tu, Weitao Feng, Hardy Chen et al.2025 · 2 citationsarXiv
Safety at Scale: A Comprehensive Survey of Large Model and Agent Safety2502.05206v6 · Xingjun Ma, Yifeng Gao, Yixu Wang et al.2025 · 18 citationsarXiv
ARFlow: Autoregressive Flow with Hybrid Linear Attention2501.16085v2 · Mude Hui, Rui-Jie Zhu, Songlin Yang et al.2025 · 0 citationsarXiv
Double Visual Defense: Adversarial Pre-training and Instruction Tuning for Improving Vision-Language Model Robustness2501.09446v2 · Zeyu Wang, Cihang Xie, Brian Bartoldson et al.2025 · 1 citationarXiv
Generative Image Layer Decomposition with Visual Effects2411.17864v1 · Jinrui Yang, Qing Liu, Yijun Li et al.2024 · 5 citationsarXiv
CLIPS: An Enhanced CLIP Framework for Learning with Synthetic Captions2411.16828v1 · Yanqing Liu, Xianhang Li, Zeyu Wang et al.2024 · 0 citationsarXiv
M-VAR: Decoupled Scale-wise Autoregressive Modeling for High-Quality Image Generation2411.10433v1 · Sucheng Ren, Yaodong Yu, Nataniel Ruiz et al.2024 · 0 citationsarXiv
AttnGCG: Enhancing Jailbreaking Attacks on LLMs with Attention Manipulation2410.09040v1 · Zijun Wang, Haoqin Tu, Jieru Mei et al.2024 · 0 citationsarXiv
VHELM: A Holistic Evaluation of Vision Language Models2410.07112v2 · Tony Lee, Haoqin Tu, Chi Heem Wong et al.2024 · 16 citationsarXiv
From Pixels to Objects: A Hierarchical Approach for Part and Object Segmentation Using Local and Global Aggregation2409.01353v1 · Yunfei Xie, Cihang Xie, Alan Yuille et al.2024 · 0 citationsarXiv
MedTrinity-25M: A Large-scale Multimodal Dataset with Multigranular Annotations for Medicine2408.02900v3 · Yunfei Xie, Ce Zhou, Lang Gao et al.2024 · 8 citationsarXiv
VideoHallucer: Evaluating Intrinsic and Extrinsic Hallucinations in Large Video-Language Models2406.16338v1 · Yuxuan Wang, Yueqian Wang, Dongyan Zhao et al.2024 · 4 citationsarXiv
What If We Recaption Billions of Web Images with LLaMA-3?2406.08478v2 · Xianhang Li, Haoqin Tu, Mude Hui et al.2024 · 2 citationsarXiv
Autoregressive Pretraining with Mamba in Vision2406.07537v1 · Sucheng Ren, Xianhang Li, Haoqin Tu et al.2024 · 0 citationsarXiv
Scaling White-Box Transformers for Vision2405.20299v4 · Jinrui Yang, Xianhang Li, Druv Pai et al.2024 · 6 citationsarXiv
ARVideo: Autoregressive Pretraining for Self-Supervised Video Representation Learning2405.15160v1 · Sucheng Ren, Hongru Zhu, Chen Wei et al.2024 · 0 citationsarXiv
Mamba-R: Vision Mamba ALSO Needs Registers2405.14858v2 · Feng Wang, Jiahao Wang, Sucheng Ren et al.2024 · 4 citationsarXiv
HQ-Edit: A High-Quality Dataset for Instruction-based Image Editing2404.09990v1 · Mude Hui, Siwei Yang, Bingchen Zhao et al.2024 · 3 citationsarXiv
Scaling (Down) CLIP: A Comprehensive Analysis of Data, Architecture, and Training Strategies2404.08197v2 · Zichao Li, Cihang Xie, Ekin Dogus Cubuk2024 · 1 citationarXiv
3D-TransUNet for Brain Metastases Segmentation in the BraTS2023 Challenge2403.15735v1 · Siwei Yang, Xianhang Li, Jieru Mei et al.2024 · 8 citationsarXiv
AQA-Bench: An Interactive Benchmark for Evaluating LLMs' Sequential Reasoning Ability2402.09404v2 · Siwei Yang, Bingchen Zhao, Cihang Xie2024 · 2 citationsarXiv
Revisiting Adversarial Training at Scale2401.04727v2 · Zeyu Wang, Xianhang Li, Hongru Zhu et al.2024 · 27 citationsarXiv
SPFormer: Enhancing Vision Transformer with Superpixel Representation2401.02931v1 · Jieru Mei, Liang-Chieh Chen, Alan Yuille et al.2024 · 6 citationsarXiv
A Semantic Space is Worth 256 Language Descriptions: Make Stronger Segmentation Models with Descriptive Properties2312.13764v3 · Junfei Xiao, Ziqi Zhou, Wenxuan Li et al.2023 · 1 citationarXiv
Tuning LayerNorm in Attention: Towards Efficient Multi-Modal LLM Finetuning2312.11420v1 · Bingchen Zhao, Haoqin Tu, Chen Wei et al.2023 · 7 citationsarXiv
Audio-Visual LLM for Video Understanding2312.06720v2 · Fangxun Shu, Lei Zhang, Hao Jiang et al.2023 · 10 citationsarXiv
Filter & Align: Leveraging Human Knowledge to Curate Image-Text Data2312.06726v4 · Lei Zhang, Fangxun Shu, Tianyang Liu et al.2023 · 0 citationsarXiv
Career total: 121 works. 103 are in this corpus.Showing the 50 most recent.
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.