Search Results for author: Simon Park

Found 3 papers, 2 papers with code

Generalizing from SIMPLE to HARD Visual Reasoning: Can We Mitigate Modality Imbalance in VLMs?

1 code implementation5 Jan 2025 Simon Park, Abhishek Panigrahi, Yun Cheng, Dingli Yu, Anirudh Goyal, Sanjeev Arora

We seek strategies for training on the SIMPLE version of the tasks that improve performance on the corresponding HARD task, i. e., S2H generalization.

Image Captioning Image to text +3

Instruct-SkillMix: A Powerful Pipeline for LLM Instruction Tuning

no code implementations27 Aug 2024 Simran Kaur, Simon Park, Anirudh Goyal, Sanjeev Arora

Vanilla SFT (i. e., no PPO, DPO, or RL methods) on data generated from Instruct-SkillMix leads to strong gains on instruction following benchmarks such as AlpacaEval 2. 0, MT-Bench, and WildBench.

Instruction Following

AI-Assisted Generation of Difficult Math Questions

1 code implementation30 Jul 2024 Vedant Shah, Dingli Yu, Kaifeng Lyu, Simon Park, Jiatong Yu, Yinghui He, Nan Rosemary Ke, Michael Mozer, Yoshua Bengio, Sanjeev Arora, Anirudh Goyal

We present a design framework that combines the strengths of LLMs with a human-in-the-loop approach to generate a diverse array of challenging math questions.

Math Mathematical Reasoning

Cannot find the paper you are looking for? You can Submit a new open access paper.