avatar

Cheng DENG (Daven)

Research Fellow
Bayes Centre, CSE
University of Edinburgh
davendw49 (at) gmail.com
My Blog · All Talks

About Me

I develop efficient foundation models and agents that move from language to physical intelligence. My research spans natural language processing, foundation-model training, efficient model architecture and inference, and embodied AI, with a growing focus on VLA models, robotic agents, and hardware–model co-design for real-world deployment.

A central question across my work is how to build capable AI systems under real constraints on compute, memory, latency, energy, and interaction: from language models running on edge devices to embodied agents acting on robots and vehicles.

Currently, I am a Research Fellow at the Bayes Centre, University of Edinburgh, working in collaboration with Prof. Luo Mai, Prof. Jeff Pan, and Prof. Jun Wang. I also serve as a Visiting Research Fellow at Li Auto. Prior to joining the University of Edinburgh, I was a Research Assistant at the Hong Kong University of Science and Technology (Guangzhou), where I worked with Prof. Lei Chen and Prof. Lionel M. Ni. I obtained my Ph.D. at Shanghai Jiao Tong University, where I was fortunate to be supervised by Prof. Weinan Zhang, Prof. Luoyi Fu, and Prof. Xinbing Wang. During my early research career, I interned with the Data Team at TikTok and worked as an Applied Scientist Intern at Amazon Shanghai AI Lab. In 2021, I was selected for the Wenjun Wu Honored Ph.D. Class.

Research

My current research is organised around three connected directions:

  1. Efficient Physical AI & Robotics. VLA and world-action models, embodied agents, and hybrid learned/classical robot systems, with deployments across robotic manipulation, mobile robots, and intelligent vehicles.
  2. Efficient Foundation Models & Agents. Hardware-aware model architecture, scaling laws, efficient attention and inference, and long-context agent systems for resource-constrained deployment.
  3. NLP, Foundation Models & AI for Science. Pre-training, post-training, reasoning, agents, and structured knowledge for language and scientific domains.

My long-term goal is to understand how models, agents, robot skills, and hardware should be co-designed so that increasingly capable AI can operate reliably in the physical world.

Vision & Sensing Multimodal Perception NLP & LLMs Agentic Reasoning & Planning Robotics Manipulation & Navigation Physical AI Foundation Model

News

Selected Research Highlights

🤖 Efficient Physical AI & Robotics
Efficient VLA running on edge hardware

Efficient VLA CoRL 2026

A controlled, latency-aware study of modular VLA design. We identify where additional model capacity actually pays off, derive an efficient VLA recipe, and validate transfer from simulation to real robotic manipulation.

arXiv

PhysicalAgent operations console: map, camera, and lidar during a navigation task PhysicalAgent: the mobile robot navigating the same task

PhysicalAgent Banbu-supported

An embodied-agent testbed integrating VLA policies, SLAM/navigation, multimodal perception, and task-level agents on an untethered Jetson-powered mobile robot. We use it to study learned/classical skill composition, agent–executor feedback, and resource-aware autonomy in real environments.

Ongoing

Task-level Agent VLA Policy Vehicle / RobotPlatform Hardware co-design scaling law for on-device models

Efficient Embodied AI for Intelligent Vehicles and Robots Industry

VLA policies, agent–executor systems, and hardware-aware deployment for real-world vehicle and robot platforms through industry collaboration with Li Auto.

Scaling LawsEfficient VLAAdaptiveWAMLong-horizon VLAcoming soon

⚡ Efficient Foundation Models & Agents
PLM demo: interacting with objects in front of the device PLM demo: the on-device model's screen output

PLM Preprint & Hardware Co-Design Scaling Laws NeurIPS 2026

A 1.8B peripheral language model co-designed with edge hardware, Pareto-optimal scaling laws that choose architectures under latency, memory, and energy constraints (Dancing in Fetters), and RooflineBench for benchmarking on-device LLMs.

PLMCodeScaling LawsRooflineBench🤗 13k+ downloadsDAI 2026

ContextPilot system overview

ContextPilot MLSys 2026 & MemoryCraft Under review

Long-context agents, from inference to memory: ContextPilot cuts prefill cost through context reuse, ordering, and deduplication; MemoryCraft is a controlled platform for evaluating agent memory systems jointly with their retrieval regimes, backbones, and token cost.

ContextPilotMemoryCraft

GTA grouped-head latent attention compared with MHA, GQA, and MLA

GTA: Efficient Attention Preprint

Grouped-head latent attention: sharing attention maps across head groups and decoding values from a compact latent to cut attention FLOPs and KV-cache size at matched quality.

arXiv

💬 NLP, Agents & AI for Science
GAKG (CIKM 2021), K2 (WSDM 2024), and GeoGalactica (AI4X 2024)

GeoGalactica / K2 / GAKG WSDM · AI4X · CIKM

First-generation LLM foundation models for science, covering data acquisition, pre-training, SFT, and RL.

GeoGalacticaK2GAKG 314 stars🤗 2.9k downloads

DS-Agent case-based reasoning loop

DS-Agent ICML 2024

Automated data science with LLM agents: case-based reasoning as agent skills and memory in the era of 2024.

arXivCode

Uncertainty-based hallucination detection with keyword focus

Hallucination Detection EMNLP 2023

Uncertainty-based hallucination detection for LLMs with keyword focus and history-aware propagation, improving detection without extra supervision.

arXiv

Platforms. PhysicalAgent mobile base: a self-built wheeled home robot I lead the team on, NVIDIA Jetson Orin on board, lidar, camera, and microphones, ROS 2 navigation, pretrained VLA plus agent loop, running untethered in a real home. Also deployed on Raspberry Pi and consumer phones (PLM), and in-vehicle edge hardware (Li Auto).

Selected Publications [Google Citation]

  1. CoRL 2026 Robotics · VLA How to Build an Efficient VLA: A Design Space Study for Modular Vision-Language-Action Models
    Luoyang Sun, Guoyang Xia, Fengfa Li, Lei Ren, Xinyu Cui, Haifeng Zhang, Fangxiang Feng, Kaike Zhang, Kun Zhan, Xie Yan, Jun Wang, Cheng Deng*
    Conference on Robot Learning, 2026.
    PDF
  2. Under Review Agents · Systems MemoryCraft: How Retrieval Control Reshapes Agent Memory Performance and Cost
    Cheng Deng, Eve Sauvage, Danna Zheng, Wenyu Huang, Luo Mai, Mirella Lapata, Jeff Z. Pan
    Code
  3. Preprint Robotics · VLA π-StepNFT: Wider Space Needs Finer Steps in Online RL for Flow-based VLAs
    Siting Wang, Xiaofeng Wang, Zheng Zhu, Minnan Pei, Xinyu Cui, Cheng Deng, Jian Zhao, Guan Huang, Haifeng Zhang, Jun Wang
    PDF
  4. NeurIPS 2026 Efficient ML Dancing in Fetters: Pareto-Optimal On-Device LLMs under Hardware Constraints
    Luoyang Sun, Jiwen Jiang, Yifeng Ding, Fengfa Li, Yan Song, Haifeng Zhang, Jian Ying, Lei Ren, Kun Zhan, Wei Chen, Yan Xie, Cheng Deng*
    Conference on Neural Information Processing Systems, 2026.
    PDF
  5. MLSys 2026 Systems · Agents ContextPilot: Fast Long-Context Inference via Context Reuse
    Yinsicheng Jiang, Yeqi Huang, Liang Cheng, Cheng Deng, Xuan Sun, Luo Mai
    International Conference on Machine Learning Systems, 2026.
    PDF
  6. DAI 2026 Efficient ML · Systems RooflineBench: A Benchmarking Framework for On-Device LLMs via Roofline Analysis
    Zhen Bi, Xueshu Chen, Luoyang Sun, Yuhang Yao, Qing Shen, Jungang Lou, Cheng Deng*
    International Conference on Distributed Artificial Intelligence, 2026.
    PDF
  7. ICLR 2026 Multimodal SpatialViz-Bench: Automatically Generated Spatial Visualization Reasoning Tasks for MLLMs
    Siting Wang, Luoyang Sun, Cheng Deng*, Kun Shao, Minnan Pei, Zheng Tian, Haifeng Zhang, Jun Wang
    International Conference on Learning Representations, 2026.
    PDF
  8. Preprint Efficient ML GTA: Grouped-head latenT Attention
    Luoyang Sun, Cheng Deng, Jiwen Jiang, Xinjian Wu, Haifeng Zhang, Lei Chen, Lionel M. Ni, Jun Wang
    PDF
  9. Preprint Efficient ML PLM: Efficient Peripheral Language Models Hardware-Co-Designed for Ubiquitous Computing
    Cheng Deng*, Luoyang Sun, Jiwen Jiang, Yongcheng Zeng, Xinjian Wu, Wenxin Zhao, Qingfa Xiao, Jiachuan Wang, Haoyang Li, Lei Chen, Lionel M. Ni, Haifeng Zhang, Jun Wang
    PDF Code
  10. ICML2024 Agents · NLP DS-Agent: Automated Data Science by Empowering Large Language Models with Case-Based Reasoning
    Siyuan Guo, Cheng Deng, Ying Wen, Hechang Chen, Yi Chang, Jun Wang
    International Conference on Machine Learning
    PDF Code
  11. EMNLP2023 NLP Enhancing Uncertainty-Based Hallucination Detection with Stronger Focus
    Tianhang Zhang, Lin Qiu, Qipeng Guo, Cheng Deng, Yue Zhang, Zheng Zhang, Chenghu Zhou, Xinbing Wang, Luoyi Fu
    Conference on Empirical Methods in Natural Language Processing, 2023.
    PDF
  12. Preprint NLP · AI4Science GeoGalactica: A Scientific Large Language Model in Geoscience
    Zhouhan Lin, Cheng Deng, Le Zhou, Tianhang Zhang, Yi Xu, Luoyi Fu, Weinan Zhang, Junxian He, Chao Ma, Yunqiang Zhu, Xinbing Wang, Chenghu Zhou, et al.
    PDF Code
  13. WSDM2024 NLP · AI4Science K2: A Foundation Language Model for Geoscience Knowledge Understanding and Utilization
    Cheng Deng, Tianhang Zhang, Zhongmou He, Yi Xu, Qiyuan Chen, Yuanyuan Shi, Luoyi Fu, Weinan Zhang, Xinbing Wang, Chenghu Zhou, Zhouhan Lin, Junxian He
    WSDM, 2024
    PDF Code
  14. CIKM2021 AI4Science · Knowledge Graphs GAKG: A Multimodal GeoScience Academic Knowledge Graph
    Cheng Deng, Yuting Jia, Weinan Zhang, Luoyi Fu, Xinbing Wang, Chenghu Zhou, et al.
    CIKM, 2021
    PDF Code

* Corresponding author

Services

Funding

Selected Talks [All Talks]


Powered by Jekyll and Minimal Light theme.