Search Results for author:
Found 27 papers, 13 papers with code
APE-Bench I: Towards File-level Automated Proof Engineering of Formal Math Libraries
Recent progress in large language models (LLMs) has shown promise in formal theorem proving, yet existing benchmarks remain limited to isolated, static proof tasks, failing to capture the iterative, engineering-intensive workflows of real-world formal mathematics libraries.
Theorem Prover as a Judge for Synthetic Data Generation
Building upon that, we introduce Theorem Prover as a Judge (TP-as-a-Judge), a method that employs theorem prover formalisation to rigorously assess LLM intermediate reasoning, effectively integrating autoformalisation with synthetic data generation.
Formal Mathematical Reasoning: A New Frontier in AI
AI for Mathematics (AI4Math) is not only intriguing intellectually but also crucial for AI-driven discovery in science, engineering, and beyond.
End-to-End Ontology Learning with Large Language Models
Ontologies are useful for automatic machine processing of domain knowledge as they represent it in a structured format.
Shallow Diffuse: Robust and Invisible Watermarking through Low-Dimensional Subspaces in Diffusion Models
This method ensures that a substantial portion of the watermark lies in the null space of this subspace, effectively separating it from the image generation process.
Learning a Mini-batch Graph Transformer via Two-stage Interaction Augmentation
Mini-batch Graph Transformer (MGT), as an emerging graph learning model, has demonstrated significant advantages in semi-supervised node prediction tasks with improved computational efficiency and enhanced model robustness.
Proving Theorems Recursively
This approach allows the theorem to be tackled incrementally by outlining the overall theorem at the first level and then solving the intermediate conjectures at deeper levels.
DeepSeek-Prover: Advancing Theorem Proving in LLMs through Large-Scale Synthetic Data
Proof assistants like Lean have revolutionized mathematical proof verification, ensuring high accuracy and reliability.
Ranked #5 on
Automated Theorem Proving
on miniF2F-test
(using extra training data)
Don't Trust: Verify -- Grounding LLM Quantitative Reasoning with Autoformalization
Large language models (LLM), such as Google's Minerva and OpenAI's GPT families, are becoming increasingly capable of solving mathematical quantitative reasoning problems.
Multilingual Mathematical Autoformalization
In this work, we create $\texttt{MMA}$, a large, flexible, multilingual, and multi-domain dataset of informal-formal pairs, by using a language model to translate in the reverse direction, that is, from formal mathematical statements into corresponding informal ones.
Message-passing selection: Towards interpretable GNNs for graph classification
In this paper, we strive to develop an interpretable GNNs' inference paradigm, termed MSInterpreter, which can serve as a plug-and-play scheme readily applicable to various GNNs' baselines.
Evaluating Language Models for Mathematics through Interactions
There is much excitement about the opportunity to harness the power of large language models (LLMs) when building problem-solving assistants.
Decomposing the Enigma: Subgoal-based Demonstration Learning for Formal Theorem Proving
Large language models~(LLMs) present an intriguing avenue of exploration in the domain of formal theorem proving.
Ranked #8 on
Automated Theorem Proving
on miniF2F-test
A large-scale multimodal dataset of human speech recognition
The dataset has been validated and has potential for the research of lip reading and multimodal speech recognition.
Draft, Sketch, and Prove: Guiding Formal Theorem Provers with Informal Proofs
In this work, we introduce Draft, Sketch, and Prove (DSP), a method that maps informal proofs to formal proof sketches, and uses the sketches to guide an automated prover by directing its search to easier sub-problems.
Ranked #3 on
Automated Theorem Proving
on miniF2F-valid
(Pass@100 metric)
Autoformalization with Large Language Models
Autoformalization is the process of automatically translating from natural language mathematics to formal specifications and proofs.
Thor: Wielding Hammers to Integrate Language Models and Automated Theorem Provers
Thor increases a language model's success rate on the PISA dataset from $39\%$ to $57\%$, while solving $8. 2\%$ of problems neither language models nor automated theorem provers are able to solve on their own.
Ranked #17 on
Automated Theorem Proving
on miniF2F-test
MDPose: Human Skeletal Motion Reconstruction Using WiFi Micro-Doppler Signatures
It provides an effective solution to track human activities by reconstructing a skeleton model with 17 key points, which can assist with the interpretation of conventional RF sensing outputs in a more understandable way.
OPERAnet: A Multimodal Activity Recognition Dataset Acquired from Radio Frequency and Vision-based Sensors
This dataset can be exploited to advance WiFi and vision-based HAR, for example, using pattern recognition, skeletal representation, deep learning algorithms or other novel approaches to accurately recognize human activities.
Neural Style Transfer Enhanced Training Support For Human Activity Recognition
Further, we benchmark the data augmentation performance of the style transferred signatures with three other synthetic datasets -- clean simulated spectrograms (no environmental effects), simulated data with added AWGN noise, and simulated data with GAN generated noise.
FMNet: Latent Feature-wise Mapping Network for Cleaning up Noisy Micro-Doppler Spectrogram
On the other hand, we also propose a novel idea which trains a classifier with only simulated data and predicts new measured samples after cleaning them up with the FMNet.
Unsupervised Doppler Radar-Based Activity Recognition for e-Healthcare
This study proposes two unsupervised feature extraction methods for the purpose of human activity monitoring using Doppler-streams.
SimHumalator: An Open Source WiFi Based Passive Radar Human Simulator For Activity Recognition
We integrate WiFi transmission signals with the human animation data to generate the micro-Doppler features that incorporate the diversity of human motion characteristics, and the sensor parameters.
Learning from Natural Noise to Denoise Micro-Doppler Spectrogram
However, noisy time-frequency spectrograms can significantly affect the performance of the classifier and must be tackled using appropriate denoising algorithms.
LIME: Learning Inductive Bias for Primitives of Mathematical Reasoning
While designing inductive bias in neural architectures has been widely studied, we hypothesize that transformer networks are flexible enough to learn inductive bias from suitable generic tasks.
IsarStep: a Benchmark for High-level Mathematical Reasoning
In this paper, we present a benchmark for high-level mathematical reasoning and study the reasoning capabilities of neural sequence-to-sequence models.
