CLiViS: Unleashing Cognitive Map through Linguistic-Visual Synergy for Embodied Visual Reasoning

arXiv:2506.17629 · cs.CV, cs.AI, cs.CL · Submitted 2025-06-21 · Read on arXiv

cs.CV, cs.AI, cs.CL

Submitted: 2025-06-21

Updated: 2026-05-25

Journal ref: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2026, pp. 5134-5143

Code: https://github.com/Teacher-Tom/CLiViS

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Benchmark — 20× in this paper · explained in 2 episodes
• Accuracy — 16× in this paper · explained in 1 episode
• Embodied Visual Reasoning — 9× in this paper
• Foundation Model — 6× in this paper · explained in 3 episodes
• Training-Free Framework — 6× in this paper · explained in 2 episodes
• Embodied Question Answering — 5× in this paper
• Foundation Models — 5× in this paper · explained in 7 episodes
• Core — 4× in this paper · explained in 2 episodes
• Interpretability — 4× in this paper · explained in 15 episodes
• Model-Agnostic — 4× in this paper · explained in 2 episodes
• Semantic Understanding — 4× in this paper · explained in 2 episodes
• Ablation — 3× in this paper · explained in 1 episode
• Ablation Studies — 3× in this paper · explained in 1 episode
• Fine-Tuning — 3× in this paper · explained in 5 episodes
• Large Language Models (LLMs) — 3× in this paper · explained in 6 episodes
• Action Sequences — 2× in this paper
• Consistency — 2× in this paper · explained in 3 episodes
• Embodied AI — 2× in this paper · explained in 2 episodes
• Grounding — 2× in this paper · explained in 3 episodes
• Latent Space — 2× in this paper · explained in 7 episodes
• Spatial Relations — 2× in this paper
• Structured Reasoning — 2× in this paper · explained in 3 episodes
• Task Planning — 2× in this paper · explained in 2 episodes
• Temporal Reasoning — 2× in this paper · explained in 2 episodes
• Trace — 2× in this paper · explained in 2 episodes
• Verification — 2× in this paper · explained in 2 episodes
• Vision-Language Models (VLMs) — 2× in this paper · explained in 6 episodes
• Action-Specific Objects — 1× in this paper
• Adaptation — 1× in this paper · explained in 1 episode
• Benchmarking — 1× in this paper · explained in 3 episodes
• Elias — 1× in this paper · explained in 2 episodes
• Generalizability — 1× in this paper · explained in 6 episodes
• Graph Construction — 1× in this paper · explained in 3 episodes
• Instruction Tuning — 1× in this paper · explained in 2 episodes
• Locating Objects — 1× in this paper
• Meta-learning — 1× in this paper · explained in 2 episodes
• Multimodal Fusion — 1× in this paper · explained in 3 episodes
• Multimodal Reasoning — 1× in this paper · explained in 5 episodes
• Parameter-Efficient Fine-Tuning — 1× in this paper · explained in 2 episodes
• Reinforcement Learning — 1× in this paper · explained in 4 episodes
• Robustness — 1× in this paper · explained in 5 episodes
• Task Decomposition — 1× in this paper · explained in 2 episodes
• Temporal Events — 1× in this paper
• Unified Framework — 1× in this paper · explained in 5 episodes

Sources

• ChatDB: Augmenting LLMs with Databases as Their Symbolic Memory
• DeepSeek-V3 Technical Report
• A Survey on Vision-Language-Action Models for Embodied AI
• Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond
• Qwen2.5-VL Technical Report
• Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling
• Video-R1: Reinforcing Video Reasoning in MLLMs
• LLaMA: Open and Efficient Foundation Language Models
• OCRA: Object-Centric Learning with 3D and Tactile Priors for Human-to-Robot Action Transfer
• Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution
• Qwen2.5 Technical Report
• VideoLLaMA 3: Frontier Multimodal Foundation Models for Image and Video Understanding
• InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models
• MemGPT: Towards LLMs as Operating Systems
• Position: Episodic Memory is the Missing Piece for Long-Term LLM Agents

Related papers

• Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
• AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
• Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
• MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
• TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
• A Survey on Efficient Vision-Language-Action Models