A Minimalist Approach to LLM Reasoning: from Rejection Sampling to Reinforce

Authors: Xiong, Wei, Yao, Jiarui, Xu, Yuhui, Pang, Bo, Wang, Lei, Sahoo, Doyen, Li, Junnan, Jiang, Nan, Zhang, Tong, Xiong, Caiming, Dong, Hanze

Subject Terms: Computer Science - Machine Learning, Computer Science - Artificial Intelligence, Computer Science - Computation and Language, Statistics - Machine Learning

Access URL: http://arxiv.org/abs/2504.11343

Empowering Time Series Analysis with Synthetic Data: A Survey and Outlook in the Era of Foundation Models

Authors: Liu, Xu, Aksu, Taha, Liu, Juncheng, Wen, Qingsong, Liang, Yuxuan, Xiong, Caiming, Savarese, Silvio, Sahoo, Doyen, Li, Junnan, Liu, Chenghao

Subject Terms: Computer Science - Machine Learning

Access URL: http://arxiv.org/abs/2503.11411

Generative Frame Sampler for Long Video Understanding

Authors: Yao, Linli, Wu, Haoning, Ouyang, Kun, Zhang, Yuanxing, Xiong, Caiming, Chen, Bei, Sun, Xu, Li, Junnan

Subject Terms: Computer Science - Computer Vision and Pattern Recognition, Computer Science - Multimedia

Access URL: http://arxiv.org/abs/2503.09146

ProBench: Judging Multimodal Foundation Models on Open-ended Multi-domain Expert Tasks

Authors: Yang, Yan, Li, Dongxu, Wu, Haoning, Chen, Bei, Liu, Liu, Pan, Liyuan, Li, Junnan

Subject Terms: Computer Science - Computer Vision and Pattern Recognition

Access URL: http://arxiv.org/abs/2503.06885

Air Conditioning Load Monitoring in NILM Using Low Frequency Power Data

Authors: Li, Junnan, Tian, Minzhe, Ma, Mingjie, Zhou, Guanyu, Wang, Guohui, Guo, Lufang

Source: 2024 3rd Asian Conference on Frontiers of Power and Energy (ACFPE) Frontiers of Power and Energy (ACFPE), 2024 3rd Asian Conference on. :404-408 Oct, 2024

Relation: 2024 3rd Asian Conference on Frontiers of Power and Energy (ACFPE)

Object Augmentation Algorithm: Computing virtual object motion and object induced interaction wrench from optical markers

Authors: Herneth, Christopher, Li, Junnan, Fatoni, Muhammad Hilman, Ganguly, Amartya, Haddadin, Sami

Source: 2024 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) Intelligent Robots and Systems (IROS), 2024 IEEE/RSJ International Conference on. :13502-13509 Oct, 2024

Relation: 2024 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

Identification and validation of the dynamic model of a tendon-driven anthropomorphic finger

Authors: Li, Junnan, Chen, Lingyun, Ringwald, Johannes, Fortunic, Edmundo Pozo, Ganguly, Amartya, Haddadin, Sami

Source: 2024 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) Intelligent Robots and Systems (IROS), 2024 IEEE/RSJ International Conference on. :8330-8337 Oct, 2024

Relation: 2024 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

Optimizing Interaction Space: Enlarging the Capture Volume for Multiple Portable Motion Capture Devices

Authors: Fatoni, Muhammad Hilman, Herneth, Christopher, Li, Junnan, Budiman, Fajar, Ganguly, Amartya, Haddadin, Sami

Source: 2024 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) Intelligent Robots and Systems (IROS), 2024 IEEE/RSJ International Conference on. :5680-5687 Oct, 2024

Relation: 2024 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

Reward Models Identify Consistency, Not Causality

Authors: Xu, Yuhui, Dong, Hanze, Wang, Lei, Xiong, Caiming, Li, Junnan

Subject Terms: Computer Science - Machine Learning, Computer Science - Artificial Intelligence, Computer Science - Computation and Language

Access URL: http://arxiv.org/abs/2502.14619

Reward-Guided Speculative Decoding for Efficient LLM Reasoning

Authors: Liao, Baohao, Xu, Yuhui, Dong, Hanze, Li, Junnan, Monz, Christof, Savarese, Silvio, Sahoo, Doyen, Xiong, Caiming

Subject Terms: Computer Science - Computation and Language, Computer Science - Artificial Intelligence

Access URL: http://arxiv.org/abs/2501.19324

Aria-UI: Visual Grounding for GUI Instructions

Authors: Yang, Yuhao, Wang, Yue, Li, Dongxu, Luo, Ziyang, Chen, Bei, Huang, Chao, Li, Junnan

Subject Terms: Computer Science - Human-Computer Interaction, Computer Science - Artificial Intelligence

Access URL: http://arxiv.org/abs/2412.16256

OFTSR: One-Step Flow for Image Super-Resolution with Tunable Fidelity-Realism Trade-offs

Authors: Zhu, Yuanzhi, Wang, Ruiqing, Lu, Shilin, Li, Junnan, Yan, Hanshu, Zhang, Kai

Subject Terms: Computer Science - Computer Vision and Pattern Recognition

Access URL: http://arxiv.org/abs/2412.09465

Accelerating Video Diffusion Models via Distribution Matching

Authors: Zhu, Yuanzhi, Yan, Hanshu, Yang, Huan, Zhang, Kai, Li, Junnan

Subject Terms: Computer Science - Computer Vision and Pattern Recognition

Access URL: http://arxiv.org/abs/2412.05899

ULIP-2: Towards Scalable Multimodal Pre-Training for 3D Understanding

Authors: Xue, Le, Yu, Ning, Zhang, Shu, Panagopoulou, Artemis, Li, Junnan, Martin-Martin, Roberto, Wu, Jiajun, Xiong, Caiming, Xu, Ran, Niebles, Juan Carlos, Savarese, Silvio

Source: 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) CVPR Computer Vision and Pattern Recognition (CVPR), 2024 IEEE/CVF Conference on. :27081-27091 Jun, 2024

Relation: 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

Research on Overhead Power Gantry Based on Muti-sensor Fusion Method to Prevent External Force Damage of Mechanical Vehicles

Authors: Hong, Siyuan, Li, Junnan, Ai, Chuan, Zheng, Anwu

Source: 2024 5th International Conference on Artificial Intelligence and Electromechanical Automation (AIEA) Artificial Intelligence and Electromechanical Automation (AIEA), 2024 5th International Conference on. :847-851 Jun, 2024

Relation: 2024 5th International Conference on Artificial Intelligence and Electromechanical Automation (AIEA)

An Efficient Method for Safety Monitoring of Substation Workers Using Fusion of Point Cloud and Image Data

Authors: Li, Junnan, Hong, Siyuan, Ai, Chuan

Source: 2024 5th International Conference on Electronic Communication and Artificial Intelligence (ICECAI) Electronic Communication and Artificial Intelligence (ICECAI), 2024 5th International Conference on. :353-356 May, 2024

Relation: 2024 5th International Conference on Electronic Communication and Artificial Intelligence (ICECAI)

VideoAutoArena: An Automated Arena for Evaluating Large Multimodal Models in Video Analysis through User Simulation

Authors: Luo, Ziyang, Wu, Haoning, Li, Dongxu, Ma, Jing, Kankanhalli, Mohan, Li, Junnan

Subject Terms: Computer Science - Computer Vision and Pattern Recognition, Computer Science - Artificial Intelligence, Computer Science - Computation and Language, Computer Science - Multimedia

Access URL: http://arxiv.org/abs/2411.13281

Aria: An Open Multimodal Native Mixture-of-Experts Model

Authors: Li, Dongxu, Liu, Yudong, Wu, Haoning, Wang, Yue, Shen, Zhiqi, Qu, Bowen, Niu, Xinyao, Zhou, Fan, Huang, Chengen, Li, Yanpeng, Zhu, Chongyan, Ren, Xiaoyi, Li, Chao, Ye, Yifan, Liu, Peng, Zhang, Lihuan, Yan, Hanshu, Wang, Guoyin, Chen, Bei, Li, Junnan

Subject Terms: Computer Science - Computer Vision and Pattern Recognition

Access URL: http://arxiv.org/abs/2410.05993

LongVideoBench: A Benchmark for Long-context Interleaved Video-Language Understanding

Authors: Wu, Haoning, Li, Dongxu, Chen, Bei, Li, Junnan

Subject Terms: Computer Science - Computer Vision and Pattern Recognition, Computer Science - Computation and Language, Computer Science - Machine Learning

Access URL: http://arxiv.org/abs/2407.15754

Transmission Line Fittings Defect Recognition Method Based on Knowledge Enhancement

Authors: Hong, Siyuan, Li, Junnan, Chen, Xiying, Ai, Chuan, Fan, Liang, Ke, Yanping, Wang, Linna

Source: 2023 3rd International Conference on Digital Society and Intelligent Systems (DSInS) Digital Society and Intelligent Systems (DSInS), 2023 3rd International Conference on. :424-428 Nov, 2023

Relation: 2023 3rd International Conference on Digital Society and Intelligent Systems (DSInS)