HY
Hanrong Ye
cs.CVcs.LGcs.AIcs.CLcs.MAcs.SDeess.ASeess.IVcs.IRcs.RO
On Valency
published · living versionsW_xgra3rkn·v1 · currentpublished
You don't need long context
with Peter Belcak, Saurav Muralidharan, Jindong Jiang, Yonggan Fu +7
1 version
W_g5evqafh·v1published
W_qm6rzwyn·v1published
Preprints & journals
36 papers in the corpus · 2018–2026When Do We Need On-Policy Distillation? Distilling on Offline Student Rollouts Is Often Better2610.11291v1 · Siyan Zhao, Yonggan Fu, Jindong Jiang et al.2026 · 0 citationsarXiv
VERA: Scaling Verifiable Environments for Agentic co-Evolution2610.05923v1 · Junqi Liu, Yongyang Pan, Zhuosong Jiang et al.2026 · 0 citationsarXiv
BaT: Towards Self-Evolving Medical Research Agent with Stage Rubrics2608.16211v1 · Junqi Liu, Yufan He, Yexiao He et al.2026 · 0 citationsarXiv
Audio-Visual Flamingo: Open Audio-Visual Intelligence for Long and Complex Videos2607.16107v1 · Sreyan Ghosh, Arushi Goel, Kaousheik Jayakumar et al.2026 · 0 citationsarXiv
Nemotron-Labs-Diffusion-Image: Advancing Masked Discrete Diffusion for High-Resolution Image Synthesis2606.29814v2 · Shufan Li, Greg Heinrich, Hanrong Ye et al.2026 · 0 citationsarXiv
Vesta: A Generalist Embodied Reasoning Model2606.20905v1 · Johan Bjorck, Zhiqi Li, Yunze Man et al.2026 · 0 citationsarXiv
Scaling Parallel Sequence Models to Foundation-Scale Vision Encoders2606.00746v1 · Yitong Jiang, Hongjun Wang, Collin McCarthy et al.2026 · 0 citationsarXiv
JetViT: Efficient High-Resolution Vision Transformer with Post-Training Attention Search2605.26636v1 · Dongyun Zou, Zhuoyang Zhang, Junyu Chen et al.2026 · 0 citationsarXiv
Nemotron 3 Nano Omni: Efficient and Open Multimodal Intelligence2604.24954v2 · NVIDIA: Amala Sanjay Deshmukh, Kateryna Chumachenko, Tuomas Rintamaki et al.2026 · 1 citationarXiv
Attend Before Attention: Efficient and Scalable Video Understanding via Autoregressive Gazing2603.12254v1 · Baifeng Shi, Stephanie Fu, Long Lian et al.2026 · 0 citationsarXiv
Speech-Hands: A Self-Reflection Voice Agentic Approach to Speech Recognition and Audio Reasoning with Omni Perception2601.09413v2 · Zhen Wan, Chao-Han Huck Yang, Jinchuan Tian et al.2026 · 0 citationsarXiv
GSPN-2: Efficient Parallel Sequence Modeling2512.07884v1 · Hongjun Wang, Yitong Jiang, Collin McCarthy et al.2025 · 0 citationsarXiv
ToolOrchestra: Elevating Intelligence via Efficient Model and Tool Orchestration2511.21689v1 · Hongjin Su, Shizhe Diao, Ximing Lu et al.2025 · 1 citationarXiv
Nemotron-Flash: Towards Latency-Optimal Hybrid Small Language Models2511.18890v1 · Yonggan Fu, Xin Dong, Shizhe Diao et al.2025 · 0 citationsarXiv
OmniVinci: Enhancing Architecture and Data for Omni-Modal Understanding LLM2510.15870v2 · Hanrong Ye, Chao-Han Huck Yang, Arushi Goel et al.2025 · 1 citationarXiv
QeRL: Beyond Efficiency -- Quantization-enhanced Reinforcement Learning for LLMs2510.11696v1 · Wei Huang, Yi Ge, Shuai Yang et al.2025 · 0 citationsarXiv
UALM: Unified Audio Language Model for Understanding, Generation and Reasoning2510.12000v1 · Jinchuan Tian, Sang-gil Lee, Zhifeng Kong et al.2025 · 0 citationsarXiv
Test-Time Scaling Strategies for Generative Retrieval in Multimodal Conversational Recommendations2508.18132v1 · Hung-Chun Hsu, Yuan-Ching Kuo, Chao-Han Huck Yang et al.2025 · 0 citationsarXiv
Scaling RL to Long Videos2507.07966v4 · Yukang Chen, Wei Huang, Baifeng Shi et al.2025 · 4 citationsarXiv
I Think, Therefore I Diffuse: Enabling Multimodal In-Context Reasoning in Diffusion Models2502.10458v1 · Zhenxing Mi, Kuan-Chieh Wang, Guocheng Qian et al.2025 · 1 citationarXiv
Multi-Task Label Discovery via Hierarchical Task Tokens for Partially Annotated Dense Predictions2411.18823v2 · Jingdong Zhang, Hanrong Ye, Xin Li et al.2024 · 2 citationsarXiv
InvPT++: Inverted Pyramid Multi-Task Transformer for Visual Scene Understanding.38709604 · Ye, Hanrong, Xu, Dan2024 · 21 citationsIEEE transactions on pattern analysis and machine intelligence. 2024;46(12):7493-7508
MM-Ego: Towards Building Egocentric Multimodal LLMs for Video QA2410.07177v2 · Hanrong Ye, Haotian Zhang, Erik Daxberger et al.2024 · 0 citationsarXiv
MIA-Bench: Towards Better Instruction Following Evaluation of Multimodal LLMs2407.01509v5 · Yusu Qian, Hanrong Ye, Jean-Philippe Fauconnier et al.2024 · 1 citationarXiv
X-VILA: Cross-Modality Alignment for Large Language Model2405.19335v1 · Hanrong Ye, De-An Huang, Yao Lu et al.2024 · 3 citationsarXiv
DiffusionMTL: Learning Multi-Task Denoising Diffusion Model from Partially Annotated Data2403.15389v1 · Hanrong Ye, Dan Xu2024 · 12 citationsarXiv
SegGen: Supercharging Segmentation Models with Text2Mask and Mask2Img Synthesis2311.03355v2 · Hanrong Ye, Jason Kuen, Qing Liu et al.2023 · 5 citationsarXiv
TaskExpert: Dynamically Assembling Multi-Task Representations with Memorial Mixture-of-Experts2307.15324v1 · Hanrong Ye, Dan Xu2023 · 42 citationsICCV 2023
Contrastive Multi-Task Dense Prediction2307.07934v1 · Siwei Yang, Hanrong Ye, Dan Xu2023 · 10 citationsarXiv
Joint 2D-3D Multi-Task Learning on Cityscapes-3D: 3D Detection, Segmentation, and Depth Estimation2304.00971v3 · Hanrong Ye, Dan Xu2023 · 1 citationICLR 2023
InvPT: Inverted Pyramid Multi-task Transformer for Dense Scene Understanding2203.07997v3 · Hanrong Ye, Dan Xu2022 · 2 citationsECCV 2022
Bi-Directional Exponential Angular Triplet Loss for RGB-Infrared Person Re-Identification.33351761 · Ye, Hanrong, Liu, Hong, Meng, Fanyang et al.2021 · 80 citationsIEEE transactions on image processing : a publication of the IEEE Signal Processing Society. 2021;30:1583-1595
MOFA: Modular Factorial Design for Hyperparameter Optimization2011.09545v2 · Bo Xiong, Yimin Huang, Hanrong Ye et al.2020 · 1 citationarXiv
An Asymptotically Optimal Multi-Armed Bandit Algorithm and Hyperparameter Optimization2007.05670v2 · Yimin Huang, Yujun Li, Hanrong Ye et al.2020 · 4 citationsarXiv
Self-Refining Deep Symmetry Enhanced Network for Rain Removal1811.04761v3 · Hong Liu, Hanrong Ye, Xia Li et al.2018 · 7 citationsarXiv
Video Logo Retrieval based on local Features1808.03735v4 · Bochen Guan, Hanrong Ye, Hong Liu et al.2018 · 7 citationsarXiv
Career total: 49 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.