Juan Carlos Niebles

Exploring Diffusion Transformer Designs via Grafting

Taming generative video models for zero-shot optical flow extraction

BLIP-3-Video: You Only Need 32 Tokens to Represent a Video Even in VLMs

Unifying Specialized Visual Encoders for Video Language Models

Why Is Spatial Reasoning Hard for VLMs? An Attention Mechanism Perspective on Focus Areas

Understanding Complexity in VideoQA via Visual Program Generation

Unifying Specialized Visual Encoders for Video Language Models

LAM Simulator: Advancing Large Action Model Training for Agent via Online Exploration and Feedback Simulation

Understanding Complexity in VideoQA via Visual Program Generation

AdaptVis: Spatial Understanding in Vision-Language Models Requires Adaptive Attention

Retroformer: Retrospective Large Language Agents with Policy Gradient Optimization

LayoutDETR: Detection Transformer Is a Good Multimodal Layout Designer

X-InstructBLIP: A Framework for aligning X-Modal instruction-aware representations to LLMs and Emergent Cross-modal Reasoning

REX: Rapid Exploration and eXploitation for AI agents