Sanjeev Arora
Princeton CS professor; director of Princeton Language and Intelligence; theoretical foundations of ML and LLMs.
- Role
- professor
- Currently at
- Princeton NLP Group
- Scholar
- scholar.google.com/citations
- Papers
- 20
Cite
Notes
Only stored in your browser.
Authored papers
20LiveCodeBench Pro: How Do Olympiad Medalists Judge LLMs in Competitive Programming?
arXiv 2025
Goedel-Prover: A Frontier Model for Open-Source Automated Theorem Proving
arXiv 2025
AdaptMI: Adaptive Skill-based In-context Math Instruction for Small Language Models
arXiv 2025
Goedel-Prover-V2: Scaling Formal Theorem Proving with Scaffolded Data Synthesis and Self-Correction
arXiv 2025
Ineq-Comp: Benchmarking Human-Intuitive Compositional Reasoning in Automated Theorem Proving on Inequalities
arXiv 2025
Generalizing from SIMPLE to HARD Visual Reasoning: Can We Mitigate Modality Imbalance in VLMs?
arXiv 2025
What Makes a Reward Model a Good Teacher? An Optimization Perspective
arXiv 2025
CharXiv: Charting Gaps in Realistic Chart Understanding in Multimodal LLMs
arXiv 2024
LESS: Selecting Influential Data for Targeted Instruction Tuning
arXiv 2024
Keeping LLMs Aligned After Fine-tuning: The Crucial Role of Prompt Templates
arXiv 2024
Instruct-SkillMix: A Powerful Pipeline for LLM Instruction Tuning
arXiv 2024
Language Models as Science Tutors
arXiv 2024
Unintentional Unalignment: Likelihood Displacement in Direct Preference Optimization
arXiv 2024
AI-Assisted Generation of Difficult Math Questions
arXiv 2024
Fine-Tuning Language Models with Just Forward Passes
fine-tuning-language-models-with-just-forward
Task-Specific Skill Localization in Fine-tuned Language Models
arXiv 2023
A Quadratic Synchronization Rule for Distributed Deep Learning
arXiv 2023
On the SDEs and Scaling Rules for Adaptive Gradient Algorithms
arXiv 2022
A Kernel-Based View of Language Model Fine-Tuning
arXiv 2022
A Latent Variable Model Approach to PMI-based Word Embeddings
a-latent-variable-model-approach-to-pmi-based
Affiliations
Frequent co-authors
10from 20 papers