Search Results for author: Peiyang Song

Found 9 papers, 5 papers with code

LeanProgress: Guiding Search for Neural Theorem Proving via Proof Progress Prediction

no code implementations25 Feb 2025 Suozhi Huang, Peiyang Song, Robert Joseph George, Anima Anandkumar

Our experiments show that LeanProgress achieves an overall prediction accuracy of 75. 1\% in predicting the amount of progress and, hence, the remaining number of steps.

Automated Theorem Proving Mathematical Reasoning

LeanAgent: Lifelong Learning for Formal Theorem Proving

1 code implementation8 Oct 2024 Adarsh Kumarappan, Mo Tiwari, Peiyang Song, Robert Joseph George, Chaowei Xiao, Anima Anandkumar

We present LeanAgent, a novel lifelong learning framework for formal theorem proving that continuously generalizes to and improves on ever-expanding mathematical knowledge without forgetting previously learned knowledge.

Abstract Algebra Automated Theorem Proving +1

Creative and Context-Aware Translation of East Asian Idioms with GPT-4

1 code implementation1 Oct 2024 Kenan Tang, Peiyang Song, Yao Qin, Xifeng Yan

As a type of figurative language, an East Asian idiom condenses rich cultural background into only a few characters.

Translation

In-Context Learning May Not Elicit Trustworthy Reasoning: A-Not-B Errors in Pretrained Language Models

1 code implementation23 Sep 2024 Pengrui Han, Peiyang Song, Haofei Yu, Jiaxuan You

Recent advancements in artificial intelligence have led to the creation of highly capable large language models (LLMs) that can perform tasks in a human-like manner.

In-Context Learning

Lean Copilot: Large Language Models as Copilots for Theorem Proving in Lean

2 code implementations18 Apr 2024 Peiyang Song, Kaiyu Yang, Anima Anandkumar

Neural theorem proving combines large language models (LLMs) with proof assistants such as Lean, where the correctness of formal proofs can be rigorously verified, leaving no room for hallucination.

Automated Theorem Proving Hallucination

LeanDojo: Theorem Proving with Retrieval-Augmented Language Models

3 code implementations NeurIPS 2023 Kaiyu Yang, Aidan M. Swope, Alex Gu, Rahul Chalamala, Peiyang Song, Shixing Yu, Saad Godil, Ryan Prenger, Anima Anandkumar

Using this data, we develop ReProver (Retrieval-Augmented Prover): an LLM-based prover augmented with retrieval for selecting premises from a vast math library.

Automated Theorem Proving Math +1

User Pairing and Power Allocation for FTN-based SC-NOMA and MIMO-NOMA Systems Considering User Fairness

no code implementations6 Jul 2022 Peiyang Song

As far as we know, this paper is the first solution to the issue of user pairing and power allocation in FTN-based NOMA, which proves the great advantage of the combination of these two state-of-the-art technologies.

Fairness

For Intelligent and Higher Spectrum Efficiency: A Variable Packing Ratio Transmission System Based on Faster-than-Nyquist and Deep Learning

no code implementations1 Aug 2020 Peiyang Song, Nan Zhang, Lin Cai, Guo Li, Fengkui Gong

With the rapid development of various services in wireless communications, spectrum resource has become increasingly valuable.

Receiver Design for Faster-than-Nyquist Signaling: Deep-learning-based Architectures

no code implementations7 Nov 2018 Peiyang Song, Fengkui Gong, Qiang Li, Guo Li, Haiyang Ding

Additionally, we propose a DL-based joint signal detection and decoding for FTN signaling to replace the complete baseband part in traditional FTN receivers.

Cannot find the paper you are looking for? You can Submit a new open access paper.