SangEun
Publications Projects Posts CV
Home Publications Projects Posts CV

spatial-reasoning 5

  • World2VLM: Distilling World Model Imagination into VLMs for Dynamic Spatial Reasoning May 4, 2026
  • SpatialRGPT: Grounded Spatial Reasoning in Vision-Language Models Apr 29, 2026
  • When and How Much to Imagine: Adaptive Test-Time Scaling with World Models for Visual Spatial Reasoning Apr 29, 2026
  • MindJourney: Test-Time Scaling with World Models for Spatial Reasoning Apr 28, 2026
  • SpatialVLM: Endowing Vision-Language Models with Spatial Reasoning Capabilities Apr 27, 2026

Recently Updated

  • GenRecon: Bridging Generative Priors for Multi-View 3D Scene Reconstruction
  • EmoVIT: Revolutionizing Emotion Insights with Visual Instruction Tuning
  • LLaVA: Large Language and Vision Assistant
  • Why We Feel: Breaking Boundaries in Emotional Reasoning with Multimodal Large Language Models
  • Hunyuan3D 2.1: From Images to High-Fidelity 3D Assets with Production-Ready PBR Material

Trending Tags

long mllm vision-language 3d 3d-generation short emotion-mllm

© 2026 SangEun Lee. Some rights reserved.

Using the Chirpy theme for Jekyll.

Trending Tags

long mllm vision-language 3d 3d-generation short emotion-mllm

A new version of content is available.