3

CAPTURe: Evaluating Spatial Reasoning in Vision Language Models via Occluded Object Counting
a VLM benchmark testing spatial reasoning by making the models count objects under occlusion
Atin Pothiraj, Elias Stengel-Eskin, Jaemin Cho, Mohit Bansal
Preprint Cite Code
CAPTURe: Evaluating Spatial Reasoning in Vision Language Models via Occluded Object Counting
Executable Functional Abstractions: Inferring Generative Programs for Advanced Math Problems
EFA is a new way to generate diverse math problems for LLMs, by inferring generative programs from seed problems
Zaid Khan, Elias Stengel-Eskin, Archiki Prasad, Jaemin Cho, Mohit Bansal
Preprint Cite Dataset Project
Executable Functional Abstractions: Inferring Generative Programs for Advanced Math Problems
Training-free Guidance in Text-to-Video Generation via Multimodal Planning and Structured Noise Initialization
Video sketch as a new training-free guidance method for T2V diffusion models
Jialu Li*, Shoubin Yu*, Han Lin*, Jaemin Cho, Jaehong Yoon, Mohit Bansal
Preprint Cite Code Project
Training-free Guidance in Text-to-Video Generation via Multimodal Planning and Structured Noise Initialization
VideoRepair: Improving Text-to-Video Generation via Misalignment Evaluation and Localized Refinement
A new automatic refinement framework for T2V generation based on fine-grained text-video misalignment evaluation and localized refinement
Daeun Lee, Jaehong Yoon, Jaemin Cho, Mohit Bansal
Preprint Cite Code Project
VideoRepair: Improving Text-to-Video Generation via Misalignment Evaluation and Localized Refinement
M3DocRAG: Multi-modal Retrieval is What You Need for Multi-page Multi-document Understanding
Multi-modal RAG framework and dataset for multi-page multi-document understanding
Jaemin Cho, Debanjan Mahata, Ozan İrsoy, Yujie He, Mohit Bansal
Preprint Cite Code Project
M3DocRAG: Multi-modal Retrieval is What You Need for Multi-page Multi-document Understanding