Lie Routing Vision Language Models for View-Robust 3D Understanding
cs.CV, cs.LG
Submitted: 2026-11-01
Updated: 2026-11-01
Code: https://github.com/fudan-zvg/spar
Terminology
Sources
- Qwen2.5-VL Technical Report
- Vid-LLM: A Compact Video-based 3D Multimodal LLM with Reconstruction-Reasoning Synergy
- Grounded 3D-LLM with Referent Tokens
- Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling
- VLM-3R: Vision-Language Models Augmented with Instruction-Aligned 3D Reconstruction
- G$^2$VLM: Geometry Grounded Vision Language Model with Unified 3D Reconstruction and Spatial Reasoning
- Chat-Scene: Bridging 3D Scene and Large Language Models with Object Identifiers
- An Embodied Generalist Agent in 3D World
- 3DRS: MLLMs Need 3D-Aware Representation Supervision for Scene Understanding
- LLaVA-OneVision: Easy Visual Task Transfer
- SAT: Dynamic Spatial Aptitude Training for Multimodal Language Models
- On the Generalization Capacities of MLLMs for Spatial Intelligence
- SpaceMind: Camera-Guided Modality Fusion for Spatial Reasoning in Vision-Language Models
- Learning from Videos for 3D World: Enhancing MLLMs with 3D Vision Geometry Priors
- LLaVA-3D: A Simple yet Effective Pathway to Empowering LMMs with 3D-awareness
Related papers
- TEA: Text Encoder Alignment for Robust Concept Erasure in Text-to-Image Models
- Do Egocentric Video-Language Models Capture Both Hand- and Object-Centric Cues?
- Aura: Consistent Multi-Subject Video Generation via VLM-Grounded Semantic Alignment
- PVRF: All-in-one Adverse Weather Removal via Prior-modulated and Velocity-constrained Rectified Flow
- DLWM: Diverse Latent World Models for Efficient Multimodal Reasoning
- Out of Sight, Still in Mind: Token Compression for Omni-LLMs