Congcong Wang

ORCID: 0009-0006-5330-4691
Publications
Citations
Views
---
Saved
---
About
Contact & Profiles
Research Areas
  • Regulation of Appetite and Obesity
  • Machine Learning and Algorithms
  • Robot Manipulation and Learning
  • Adipose Tissue and Metabolism
  • Blockchain Technology Applications and Security
  • Smart Grid Security and Resilience
  • Sleep and Wakefulness Research
  • IoT and Edge/Fog Computing
  • Cryptography and Data Security
  • Neuroendocrine regulation and behavior
  • Machine Learning and Data Classification
  • Neurobiology and Insect Physiology Research

Center for Excellence in Brain Science and Intelligence Technology
2023-2025

Chinese Academy of Sciences
2023-2025

Nanjing University of Information Science and Technology
2023-2025

Language model pretraining with next token prediction has proved effective for scaling compute but is limited to the amount of available training data. Scaling reinforcement learning (RL) unlocks a new axis continued improvement artificial intelligence, promise that large language models (LLMs) can scale their data by explore rewards. However, prior published work not produced competitive results. In light this, we report on practice Kimi k1.5, our latest multi-modal LLM trained RL,...

10.48550/arxiv.2501.12599 preprint EN arXiv (Cornell University) 2025-01-21

Abstract The hypothalamus plays a vital role in coordinating essential neuroendocrine, autonomic, and somatomotor responses for survival reproduction. While previous studies have explored population-level projections of hypothalamic neurons, the specific innervation patterns individual axons remain unclear. To understand organization axon projections, we conducted comprehensive reconstruction single-cell projectomes from 7,180 mouse neurons expressing neuropeptides. Our analysis identified...

10.1101/2023.05.25.542241 preprint EN cc-by-nc-nd bioRxiv (Cold Spring Harbor Laboratory) 2023-05-25

With the rapid development of smart grid technology, a new challenge has been brought about by massive data generated from distributed devices. Data aggregation technology plays crucial role in schemes, terms energy statistics and resource allocation. However, achieving fast error-checking improving device fault-tolerance are still open issues aggregation. To address these issues, this paper proposes an error-tolerant scheme integrated with mechanisms. The tree-based structure, facilitating...

10.1109/dasc/picom/cbdcom/cy59711.2023.10360506 article EN 2021 IEEE Intl Conf on Dependable, Autonomic and Secure Computing, Intl Conf on Pervasive Intelligence and Computing, Intl Conf on Cloud and Big Data Computing, Intl Conf on Cyber Science and Technology Congress (DASC/PiCom/CBDCom/CyberSciTech) 2023-11-14
Coming Soon ...