Search Results for author:
Found 27 papers, 16 papers with code
CombiBench: Benchmarking LLM Capability for Combinatorial Mathematics
CombiBench is suitable for testing IMO solving capabilities since it includes all IMO combinatorial problems since 2000 (except IMO 2004 P3 as its statement contain an images).
Kimina-Prover Preview: Towards Large Formal Reasoning Models with Reinforcement Learning
We introduce Kimina-Prover Preview, a large language model that pioneers a novel reasoning-driven exploration paradigm for formal theorem proving, as showcased in this preview release.
Ranked #1 on
Automated Theorem Proving
on miniF2F-test
(using extra training data)
FormalAlign: Automated Alignment Evaluation for Autoformalization
To address this, we introduce \textsc{FormalAlign}, the first automated framework designed for evaluating the alignment between natural and formal languages in autoformalization.
ToolACE: Winning the Points of LLM Function Calling
Function calling significantly extends the application boundary of large language models, where high-quality and diverse training data is critical for unlocking this capability.
FVEL: Interactive Formal Verification Environment with Large Language Models via Theorem Proving
In this paper, we propose FVEL, an interactive Formal Verification Environment with LLMs.
Process-Driven Autoformalization in Lean 4
Autoformalization, the conversion of natural language mathematics into formal languages, offers significant potential for advancing mathematical reasoning.
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.
ATG: Benchmarking Automated Theorem Generation for Generative Language Models
We conduct extensive experiments to investigate whether current LMs can generate theorems in the library and benefit the problem theorems proving.
MUSTARD: Mastering Uniform Synthesis of Theorem and Proof Data
Recent large language models (LLMs) have witnessed significant advancement in various tasks, including mathematical reasoning and theorem proving.
A Survey of Reasoning with Foundation Models
Reasoning, a crucial ability for complex problem-solving, plays a pivotal role in various real-world settings such as negotiation, medical diagnosis, and criminal investigation.
Large Language Models as Automated Aligners for benchmarking Vision-Language Models
In this work, we address the limitations via Auto-Bench, which delves into exploring LLMs as proficient aligners, measuring the alignment between VLMs and human intelligence and value through automatic data curation and assessment.
Gaining Wisdom from Setbacks: Aligning Large Language Models via Mistake Analysis
The rapid development of large language models (LLMs) has not only provided numerous opportunities but also presented significant challenges.
TRIGO: Benchmarking Formal Mathematical Proof Reduction for Generative Language Models
Automated theorem proving (ATP) has become an appealing domain for exploring the reasoning ability of the recent successful generative language models.
LEGO-Prover: Neural Theorem Proving with Growing Libraries
Our ablation study indicates that these newly added skills are indeed helpful for proving theorems, resulting in an improvement from a success rate of 47. 1% to 50. 4%.
Ranked #1 on
Automated Theorem Proving
on miniF2F-valid
(Pass@100 metric)
Lyra: Orchestrating Dual Correction in Automated Theorem Proving
In addition, we introduce Conjecture Correction, an error feedback mechanism designed to interact with prover to refine formal proof conjectures with prover error messages.
Ranked #2 on
Automated Theorem Proving
on miniF2F-valid
(Pass@100 metric)
MetaMath: Bootstrap Your Own Mathematical Questions for Large Language Models
Our MetaMath-7B model achieves 66. 4% on GSM8K and 19. 4% on MATH, exceeding the state-of-the-art models of the same size by 11. 5% and 8. 7%.
Ranked #60 on
Arithmetic Reasoning
on GSM8K
(using extra training data)
FIMO: A Challenge Formal Dataset for Automated Theorem Proving
We present FIMO, an innovative dataset comprising formal mathematical problem statements sourced from the International Mathematical Olympiad (IMO) Shortlisted Problems.
Forward-Backward Reasoning in Large Language Models for Mathematical Verification
Instead of using forward or backward reasoning alone, we propose FOBAR to combine FOrward and BAckward Reasoning for verification.
Progressive-Hint Prompting Improves Reasoning in Large Language Models
The performance of Large Language Models (LLMs) in reasoning tasks depends heavily on prompt design, with Chain-of-Thought (CoT) and self-consistency being critical methods that enhance this ability.
Ranked #4 on
Math Word Problem Solving
on SVAMP
Learning to Prove Trigonometric Identities
We define the normalized form of trigonometric identities, design a set of rules for the proof and put forward a method which can generate theoretically infinite trigonometric identities.
Lessons learned from the NeurIPS 2021 MetaDL challenge: Backbone fine-tuning without episodic meta-learning dominates for few-shot learning image classification
Although deep neural networks are capable of achieving performance superior to humans on various tasks, they are notorious for requiring large amounts of data and computing resources, restricting their success to domains where such resources are available.
Advances in MetaDL: AAAI 2021 challenge and workshop
Winning methods featured various classifiers trained on top of the second last layer of popular CNN backbones, fined-tuned on the meta-training data (not necessarily in an episodic manner), then trained on the labeled support and tested on the unlabeled query sets of the meta-test data.
Winning solutions and post-challenge analyses of the ChaLearn AutoDL challenge 2019
Code submissions were executed on hidden tasks, with limited time and computational resources, pushing solutions that get results quickly.
Deep Statistical Solvers
This paper introduces Deep Statistical Solvers (DSS), a new class of trainable solvers for optimization problems, arising e. g., from system simulations.
AgEBO-Tabular: Joint Neural Architecture and Hyperparameter Search with Autotuned Data-Parallel Training for Tabular Data
Neural architecture search (NAS) is an AutoML approach that generates and evaluates multiple neural network architectures concurrently and improves the accuracy of the generated models iteratively.
LEAP nets for power grid perturbations
We propose a novel neural network embedding approach to model power transmission grids, in which high voltage lines are disconnected and reconnected with one-another from time to time, either accidentally or willfully.
Analysis of the AutoML Challenge Series 2015–2018
The solutions of the winners are systematically benchmarked over all datasets of all rounds and compared with canonical machine learning algorithms available in scikit-learn.
Ranked #1 on
AutoML
on Chalearn-AutoML-1
