Compositional AI Beyond LLMs: System Implications of Neuro-Symbolic-Probabilistic Architectures
Open Access
- 11 December 2025
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 67-84
Abstract
No abstract availableThis publication has 19 references indexed in Scilit:
- RobotPerf: An Open-Source, Vendor-Agnostic, Benchmarking Suite for Evaluating Robotics Computing System Performance2024
- Solving olympiad geometry without human demonstrationsNature, 2024
- Mathematical discoveries from program search with large language modelsNature, 2023
- DreamCoder: growing generalizable, interpretable knowledge with wake–sleep Bayesian program learningPhilosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences, 2023
- The ThreeDWorld Transport Challenge: A Visually Guided Task-and-Motion Planning Benchmark Towards Physically Realistic Embodied AI2022
- An Energy-Efficient and Runtime-Reconfigurable FPGA-Based Accelerator for Robotic Localization Systems2022
- A comparison of vector symbolic architecturesArtificial Intelligence Review, 2021
- Gemmini: Enabling Systematic Deep-Learning Architecture Evaluation via Full-Stack Integration2021
- Heterogeneous Dataflow Accelerators for Multi-DNN Workloads2021
- SIGMA: A Sparse and Irregular GEMM Accelerator with Flexible Interconnects for DNN Training2020