MMCoT cubed: Empowering 3D Scene Understanding with 3D-Text Interleaved Multi-Modal Chain-of-Thought Reasoning
cs.CV
Submitted: 2026-11-01
Updated: 2026-11-01
Terminology
Sources
- CoT3DRef: Chain-of-Thoughts Data-Efficient 3D Visual Grounding
- A Multitask, Multilingual, Multimodal Evaluation of ChatGPT on Reasoning, Hallucination, and Interactivity
- DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
- Point-Bind & Point-LLM: Aligning Point Cloud with Multi-modality for 3D Understanding, Generation, and Instruction Following
- LoRA: Low-Rank Adaptation of Large Language Models
- An Embodied Generalist Agent in 3D World
- OpenAI o1 System Card
- DeepSeek-VL: Towards Real-World Vision-Language Understanding
- Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks
- Self-Consistency Improves Chain of Thought Reasoning in Language Models
- AffordBot: 3D Fine-grained Embodied Reasoning via Multimodal Large Language Models
- Chat-3D: Data-efficiently Tuning Large Language Model for Universal Dialogue of 3D Scenes
- SPARTUN3D: Situated Spatial Understanding of 3D World in Large Language Models
- Multimodal Chain-of-Thought Reasoning in Language Models
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