SOTAVerified

Math

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 501–550 of 1596 papers

TitleStatusHype
Template-Driven LLM-Paraphrased Framework for Tabular Math Word Problem GenerationCode0
Offline Reinforcement Learning for LLM Multi-Step ReasoningCode2
Formal Mathematical Reasoning: A New Frontier in AI—0
Qwen2.5 Technical ReportCode13
Data for Mathematical Copilots: Better Ways of Presenting Proofs for Machine Learning—0
Conceptual In-Context Learning and Chain of Concepts: Solving Complex Conceptual Problems Using Large Language Models—0
AceMath: Advancing Frontier Math Reasoning with Post-Training and Reward Modeling—0
Critical-Questions-of-Thought: Steering LLM reasoning with Argumentative QueryingCode0
Inference-Aware Fine-Tuning for Best-of-N Sampling in Large Language Models—0
Strictly monotone mean-variance preferences with applications to portfolio selection—0
LinguaLIFT: An Effective Two-stage Instruction Tuning Framework for Low-Resource Language Tasks—0
CoinMath: Harnessing the Power of Coding Instruction for Math LLMsCode0
A Survey of Mathematical Reasoning in the Era of Multimodal Large Language Model: Benchmark, Method & Challenges—0
Combining Large Language Models with Tutoring System Intelligence: A Case Study in Caregiver Homework SupportCode0
Entropy-Regularized Process Reward ModelCode1
Dipper: Diversity in Prompts for Producing Large Language Model Ensembles in Reasoning tasks—0
Geo-LLaVA: A Large Multi-Modal Model for Solving Geometry Math Problems with Meta In-Context Learning—0
A Graph-Based Synthetic Data Pipeline for Scaling High-Quality Reasoning Instructions—0
Learning to Solve Domain-Specific Calculation Problems with Knowledge-Intensive Programs Generator—0
A Context-Enhanced Framework for Sequential Graph ReasoningCode0
Greek2MathTex: A Greek Speech-to-Text Framework for LaTeX Equations GenerationCode0
HARP: A challenging human-annotated math reasoning benchmarkCode1
MNIST-Fraction: Enhancing Math Education with AI-Driven Fraction Detection and Analysis—0
LLM-as-an-Interviewer: Beyond Static Testing Through Dynamic LLM EvaluationCode0
Mining Math Conjectures from LLMs: A Pruning Approach—0
ProcessBench: Identifying Process Errors in Mathematical ReasoningCode2
When Dimensionality Reduction Meets Graph (Drawing) Theory: Introducing a Common Framework, Challenges and Opportunities—0
Chimera: Improving Generalist Model with Domain-Specific Experts—0
Neuro-Symbolic Data Generation for Math Reasoning—0
Hard Math -- Easy UVM: Pragmatic solutions for verifying hardware algorithms using UVM—0
Enhancing Mathematical Reasoning in LLMs with Background Operators—0
Automated LaTeX Code Generation from Handwritten Math Expressions Using Vision Transformer—0
RedStone: Curating General, Code, Math, and QA Data for Large Language Models—0
U-MATH: A University-Level Benchmark for Evaluating Mathematical Skills in LLMsCode1
Unsupervised learning-based calibration scheme for Rough Bergomi modelCode0
Free Process Rewards without Process LabelsCode5
MALT: Improving Reasoning with Multi-Agent LLM Training—0
Yi-Lightning Technical Report—0
Critical Tokens Matter: Token-Level Contrastive Estimation Enhances LLM's Reasoning CapabilityCode1
Reverse Thinking Makes LLMs Stronger Reasoners—0
A Lean Dataset for International Math Olympiad: Small Steps towards Writing Math Proofs for Hard Problems—0
Mars-PO: Multi-Agent Reasoning System Preference Optimization—0
Embracing AI in Education: Understanding the Surge in Large Language Model Use by Secondary Students—0
Beyond Examples: High-level Automated Reasoning Paradigm in In-Context Learning via MCTSCode0
Training and Evaluating Language Models with Template-based Data GenerationCode1
Preference Optimization for Reasoning with Pseudo FeedbackCode2
Unraveling Arithmetic in Large Language Models: The Role of Algebraic Structures—0
Learning by Analogy: Enhancing Few-Shot Prompting for Math Word Problem Solving with Computational Graph-Based Retrieval—0
LLaMA-MoE v2: Exploring Sparsity of LLaMA from Perspective of Mixture-of-Experts with Post-TrainingCode2
Velocitune: A Velocity-based Dynamic Domain Reweighting Method for Continual Pre-training—0
Show:102550
← PrevPage 11 of 32Next →

No leaderboard results yet.