Aviral Kumar

Artificial Intelligence · arXiv.org · 2024–2025

A researcher in the Science corpus: 3 papers; trusts 3 researchers and is trusted by 2 researchers here, as inferred from the citation graph.

Subfields

• Artificial Intelligence — 15 citations into it

Whom Aviral Kumar trusts overall

Their strongest outbound trust, strongest first, inferred from their citations.

1. Andrew Jones

Who trusts Aviral Kumar overall

1. Sam Dauncey
2. Adam Suma

Papers from Aviral Kumar's perspective

Ordered by how strongly the researchers Aviral Kumar trusts endorse each paper. Same corpus, a different order for every researcher.

1. Reinforcement Learning: An Introduction
2. Measuring Mathematical Problem Solving With the MATH Dataset
3. Chain of Thought Prompting Elicits Reasoning in Large Language Models (Neural Information Processing Systems)
4. Training Verifiers to Solve Math Word Problems
5. Bandit Based Monte-Carlo Planning
6. Tree of Thoughts: Deliberate Problem Solving with Large Language Models
7. Solving math word problems with process- and outcome-based feedback
8. Thinking fast and slow.
9. Scaling Relationship on Learning Mathematical Reasoning with Large Language Models
10. ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIs

Their papers

• Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context (2024) — 3,818 citations
• Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters (2024) — 1,973 citations
• Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities (2025) — 3,609 citations