1

Imaginative Perception Tokens Enhance Spatial Reasoning in Multimodal Language Models
Imaginative Perception Tokens enhance spatial reasoning in multimodal language models - ECCV 2026
Mahtab Bigverdi, Linjie Li, Weikai Huang, Yiming Liu, Jaemin Cho, Jieyu Zhang, Tuhin Kundu, Chris Dongjoo Kim, Zelun Luo, Ranjay Krishna, Linda Shapiro
Preprint Cite
AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
Camera-controllable video generation with retrieved local geometric memories instead of a single global 3D reconstruction
Zun Wang, Han Lin, Jaehong Yoon, Jaemin Cho, Yue Zhang, Mohit Bansal
Preprint Cite
V-Co: A Closer Look at Visual Representation Alignment via Co-Denoising
A systematic study of visual co-denoising for representation-aligned pixel-space diffusion
Han Lin, Xichen Pan, Zun Wang, Yue Zhang, Chu Wang, Jaemin Cho, Mohit Bansal
Preprint Cite Code
Physics Question Scene Graph: Fine-grained Evaluation of Physical Plausibility in Text-to-Video Generation
A hierarchical question-based pipeline (PQSG) for fine-grained evaluation of physical plausibility in text-to-video generation
Atin Pothiraj, Jaemin Cho, Yue Zhang, Elias Stengel-Eskin, Mohit Bansal
Cite
EPiC: Efficient Video Camera Control Learning with Precise Anchor-Video Guidance
Efficient and precise camera control learning for video diffusion models with anchor-video guidance — ICML 2026
Zun Wang, Jaemin Cho, Jialu Li, Han Lin, Jaehong Yoon, Yue Zhang, Mohit Bansal
Preprint Cite Project
VideoRepair: Improving Text-to-Video Generation via Misalignment Detection and Localized Refinement
A new automatic refinement framework for T2V generation based on fine-grained text-video misalignment detection and localized refinement
Daeun Lee, Jaehong Yoon, Jaemin Cho, Mohit Bansal
Preprint Cite Code Project
VideoRepair: Improving Text-to-Video Generation via Misalignment Detection and Localized Refinement
One Life to Learn: Inferring Symbolic World Models for Stochastic Environments from Unguided Exploration
OneLife learns symbolic programmatic world models from a single episode of unguided exploration in stochastic environments
Zaid Khan, Archiki Prasad, Elias Stengel-Eskin, Jaemin Cho, Mohit Bansal
Preprint Cite Project
One Life to Learn: Inferring Symbolic World Models for Stochastic Environments from Unguided Exploration
RotBench: Evaluating Multimodal Large Language Models on Identifying Image Rotation
a benchmark evaluating MLLMs’ ability to identify image rotation
Tianyi Niu, Jaemin Cho, Elias Stengel-Eskin, Mohit Bansal
Preprint Cite Code
RotBench: Evaluating Multimodal Large Language Models on Identifying Image Rotation
Bifrost-1: Bridging Multimodal LLMs and Diffusion Models with Patch-level CLIP Latents
a unified framework that bridges multimodal LLMs and diffusion models with patch-level CLIP latents
Han Lin, Jaemin Cho, Amir Zadeh, Chuan Li, Mohit Bansal
Preprint Cite Code Project
Bifrost-1: Bridging Multimodal LLMs and Diffusion Models with Patch-level CLIP Latents
Video-Skill-CoT: Skill-based Chain-of-Thoughts for Domain-Adaptive Video Reasoning
a framework that automatically constructs and leverages skill-aware CoT supervisions for domain-adaptive video reasoning
Daeun Lee*, Jaehong Yoon*, Jaemin Cho, Mohit Bansal
Preprint Cite Code Project
Video-Skill-CoT: Skill-based Chain-of-Thoughts for Domain-Adaptive Video Reasoning