Think in 360: Benchmarking and Bootstrapping Panoramic Video Reasoning
cs.CV
Submitted: 2026-10-30
Updated: 2026-10-30
Code: https://github.com/OpenBMB/MiniCPM-V
Project page: https://think-in-360.github.io
Terminology
Sources
- TemporalBench: Benchmarking Fine-grained Temporal Understanding for Multimodal Video Models
- One Flight Over the Gap: A Survey from Perspective to Panoramic Vision
- Nemotron 3 Nano Omni: Efficient and Open Multimodal Intelligence
- VCR-Bench: A Comprehensive Evaluation Framework for Video Chain-of-Thought Reasoning
- GLM-4.5V and GLM-4.1V-Thinking: Towards Versatile Multimodal Reasoning with Scalable Reinforcement Learning
- PanoWorld: Towards Spatial Supersensing in 360$^\circ$ Panorama World
- InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency
- PLLaVA : Parameter-free LLaVA Extension from Images to Videos for Video Dense Captioning
- MiniCPM-V: A GPT-4V Level MLLM on Your Phone
- Vision-OPD: Learning to See Fine Details for Multimodal LLMs via On-Policy Self-Distillation
- Listen, See and Track: Spatio-Temporal Audio-Visual Sound Event Reasoning for Omni-Modal Language Models
- Towards Omnidirectional Reasoning with 360-R1: A Dataset, Benchmark, and GRPO-based Method
- PANORAMA: The Rise of Omnidirectional Vision in the Embodied AI Era
- Dense360: Dense Understanding from Omnidirectional Panoramas
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