paper-with-me

홈 › Papers

Dolphin: Closed-loop Open-ended Auto-research through Thinking, Practice, and Feedback

2025-01-07 · Jiakang Yuan, Xiangchao Yan, Botian Shi, Tao Chen, Wanli Ouyang, Bo Zhang, Lei Bai, Yu Qiao, BoWen Zhou

The scientific research paradigm is undergoing a profound transformation owing to the development of Artificial Intelligence (AI). Recent works demonstrate that various AI-assisted research methods can largely improve research efficiency by improving data analysis, accelerating computation, and fostering novel idea generation. To further move towards the ultimate goal (i.e., automatic scientific research), in this paper, we propose Dolphin, the first closed-loop open-ended auto-research framework to further build the entire process of human scientific research. Dolphin can generate research ideas, perform experiments, and get feedback from experimental results to generate higher-quality ideas. More specifically, Dolphin first generates novel ideas based on relevant papers which are ranked by the topic and task attributes. Then, the codes are automatically generated and debugged with the exception-traceback-guided local code structure. Finally, Dolphin automatically analyzes the results of each idea and feeds the results back to the next round of idea generation. Experiments are conducted on the benchmark datasets of different topics and results show that Dolphin can generate novel ideas continuously and complete the experiment in a loop. We highlight that Dolphin can automatically propose methods that are comparable to the state-of-the-art in some tasks such as 2D image classification and 3D point classification.

📄 PDF Abstract BibTeX arXiv:2501.03916

Code (0)

등록된 구현이 없습니다.

Tasks

image-classificationImage Classification

Similar Papers 제목 키워드 기반

Dolphin: A Large-Scale Automatic Speech Recognition Model for Eastern Languages

2025-03-26 · Yangyang Meng, Jinpeng Li, Guodong Lin, Yu Pu 외

This report introduces Dolphin, a large-scale multilingual automatic speech recognition (ASR) model that extends the Whisper architecture to support a wider range of languages. Our approach integrates in-house proprietar…

Automatic Speech RecognitionAutomatic Speech Recognition (ASR)speech-recognitionSpeech Recognition

Dolphins: Multimodal Language Model for Driving

2023-12-01 · Yingzi Ma, Yulong Cao, Jiachen Sun, Marco Pavone 외

The quest for fully autonomous vehicles (AVs) capable of navigating complex real-world scenarios with human-like understanding and responsiveness. In this paper, we introduce Dolphins, a novel vision-language model archi…

Autonomous VehiclesIn-Context LearningLanguage ModelingLanguage Modelling+1

Closed-Loop Open-Vocabulary Mobile Manipulation with GPT-4V

2024-04-16 · Peiyuan Zhi, Zhiyuan Zhang, Yu Zhao, Muzhi Han 외

Autonomous robot navigation and manipulation in open environments require reasoning and replanning with closed-loop feedback. In this work, we present COME-robot, the first closed-loop robotic system utilizing the GPT-4V…

Instruction FollowingMultimodal ReasoningRobot NavigationTask Planning

Hydra-NeXt: Robust Closed-Loop Driving with Open-Loop Training

2025-03-15 · Zhenxin Li, Shihao Wang, Shiyi Lan, Zhiding Yu 외

End-to-end autonomous driving research currently faces a critical challenge in bridging the gap between open-loop training and closed-loop deployment. Current approaches are trained to predict trajectories in an open-loo…

Autonomous DrivingBench2DriveNavSimTrajectory Prediction

Do Open-Loop Metrics Predict Closed-Loop Driving? A Cross-Benchmark Correlation Study of NAVSIM and Bench2Drive

2026-04-30 · Yiru Wang, Anqing Jiang, Shuo Wang, Yuwen Heng 외 arxiv

Open-loop evaluation offers fast, reproducible assessment of autonomous driving planners, but its ability to predict real closed-loop driving performance remains questionable. Prior work has shown that traditional open-l…

Autonomous Driving