Sanjeev Arora
~Sanjeev_Arora1
18
论文总数
9.0
年均投稿
平均评分
接收情况14/18
会议分布
ICLR
9
NeurIPS
4
ICML
3
COLM
2
发表论文 (18 篇)
202511 篇
4
On the Power of Context-Enhanced Learning in LLMs
ICML 2025Spotlight
4
Provable unlearning in topic modeling and downstream tasks
ICLR 2025Poster
5
AdaptMI: Adaptive Skill-based In-context Math Instructions for Small Language Models
COLM 2025Poster
3
Instruct-SkillMix: A Powerful Pipeline for LLM Instruction Tuning
ICLR 2025Poster
4
Weak-to-Strong Generalization Even in Random Feature Networks, Provably
ICML 2025Poster
4
Unintentional Unalignment: Likelihood Displacement in Direct Preference Optimization
ICLR 2025Poster
4
Generalizing from SIMPLE to HARD Visual Reasoning: Can We Mitigate Modality Imbalance in VLMs?
ICML 2025Poster
5
What Makes a Reward Model a Good Teacher? An Optimization Perspective
NeurIPS 2025Spotlight
4
Low Compute Unlearning via Sparse Representations
ICLR 2025Rejected
4
AI-Assisted Generation of Difficult Math Questions
ICLR 2025Rejected
4
Goedel-Prover: A Frontier Model for Open-Source Automated Theorem Proving
COLM 2025Poster
20247 篇
4
A Quadratic Synchronization Rule for Distributed Deep Learning
ICLR 2024Poster
4
Trainable Transformer in Transformer
ICLR 2024Rejected
4
Can Models Learn Skill Composition from Examples?
NeurIPS 2024Poster
3
SKILL-MIX: a Flexible and Expandable Family of Evaluations for AI Models
ICLR 2024Poster
4
Unlearning via Sparse Representations
ICLR 2024Rejected
4
Keeping LLMs Aligned After Fine-tuning: The Crucial Role of Prompt Templates
NeurIPS 2024Poster
4
Metacognitive Capabilities of LLMs: An Exploration in Mathematical Problem Solving
NeurIPS 2024Poster