Scholar

Filippos Kokkinos

Google Scholar ID: uuXQjUIAAAAJ

Research Scientist, Meta Superintelligence Lab

Generative AIvLLMs3D reconstructionDiffusion Models

Homepage↗Google Scholar↗

Citations & Impact

All-time

Citations

11,860

H-index

17

i10-index

22

Publications

20

Co-authors

0

Contact

No contact links provided.

Publications

7 items

Towards Physics of Multimodal Pretraining: Knowledge Flow, Modality Synergy, Early Unification, and Recipes

2026

Cited

0

From Pixels to Feelings: Aligning MLLMs with Human Cognitive Perception of Images

2025

Cited

0

Learning to See Before Seeing: Demystifying LLM Visual Priors from Language Pre-training

2025

Cited

0

WildCAT3D: Appearance-Aware Multi-View Diffusion in the Wild

2025

Cited

0

Gen3DEval: Using vLLMs for Automatic Evaluation of Generated 3D Objects

2025

Cited

0

VGRP-Bench: Visual Grid Reasoning Puzzle Benchmark for Large Vision-Language Models

2025

Cited

0

Flex3D: Feed-Forward 3D Generation With Flexible Reconstruction Model And Input View Curation

arXiv.org · 2024

Cited

4

Resume (English only)

Co-authors

0 total

Co-authors: 0 (list not available)