# LAST: LeArning to Think in Space and Time for Generalist Vision-Language Models

arXiv: https://arxiv.org/abs/2511.19261 · HTML: https://mlsanity.com/paper/2511.19261/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Placed in Spatial and embodied reasoning, one of 17 directions in LLM reasoning.
- Builds on 24 of its 110 references that are in the map.
- First posted on arXiv 24 Nov 2025.

## Placed in

- LLM reasoning / [Spatial and embodied reasoning](https://mlsanity.com/lr/spatial-and-embodied-reasoning/)
- Multimodal LLMs / vision-language models / [Embodied and 3D vision-language models](https://mlsanity.com/mllm/embodied-and-3d-vision-language-models/)

## Builds on (most cited first, 24 of 24)

- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Qwen2.5-VL Technical Report](https://mlsanity.com/paper/2502.13923/) (2025)
- [GPT-4o System Card](https://mlsanity.com/paper/2410.21276/) (2024)
- [Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution](https://mlsanity.com/paper/2409.12191/) (2024)
- [Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities](https://mlsanity.com/paper/2507.06261/) (2025)
- [Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context](https://mlsanity.com/paper/2403.05530/) (2024)
- [InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models](https://mlsanity.com/paper/2504.10479/) (2025)
- [Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling](https://mlsanity.com/paper/2412.05271/) (2024)
- [SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features](https://mlsanity.com/paper/2502.14786/) (2025)
- [EVA-CLIP: Improved Training Techniques for CLIP at Scale](https://mlsanity.com/paper/2303.15389/) (2023)
- [Visual ChatGPT: Talking, Drawing and Editing with Visual Foundation Models](https://mlsanity.com/paper/2303.04671/) (2023)
- [GLM-4.5V and GLM-4.1V-Thinking: Towards Versatile Multimodal Reasoning with Scalable Reinforcement Learning](https://mlsanity.com/paper/2507.01006/) (2025)
- [Ring Attention with Blockwise Transformers for Near-Infinite Context](https://mlsanity.com/paper/2310.01889/) (2023)
- [DeepEyes: Incentivizing "Thinking with Images" via Reinforcement Learning](https://mlsanity.com/paper/2505.14362/) (2025)
- [PLLaVA : Parameter-free LLaVA Extension from Images to Videos for Video Dense Captioning](https://mlsanity.com/paper/2404.16994/) (2024)
- [Spatial-MLLM: Boosting MLLM Capabilities in Visual-based Spatial Intelligence](https://mlsanity.com/paper/2505.23747/) (2025)
- [Thinking with Images for Multimodal Reasoning: Foundations, Methods, and Future Frontiers](https://mlsanity.com/paper/2506.23918/) (2025)
- [LifelongMemory: Leveraging LLMs for Answering Queries in Long-form Egocentric Videos](https://mlsanity.com/paper/2312.05269/) (2023)
- [VideoAgent2: Enhancing the LLM-Based Agent System for Long-Form Video Understanding by Uncertainty-Aware CoT](https://mlsanity.com/paper/2504.04471/) (2025)
- [3D Aware Region Prompted Vision Language Model](https://mlsanity.com/paper/2509.13317/) (2025)
- [Temporal Chain of Thought: Long-Video Understanding by Thinking in Frames](https://mlsanity.com/paper/2507.02001/) (2025)
- [Athena: Enhancing Multimodal Reasoning with Data-efficient Process Reward Models](https://mlsanity.com/paper/2506.09532/) (2025)
- [CAViAR: Critic-Augmented Video Agentic Reasoning](https://mlsanity.com/paper/2509.07680/) (2025)

## Built on by (most cited first, 3 of 3)

- [FC-MIR: A Mobile Screen Awareness Framework for Intent-Aware Recommendation based on Frame-Compressed Multimodal Trajectory Reasoning](https://mlsanity.com/paper/2512.19107/) (2025)
- [Towards Camera-Robust 3D Localization: Equation-Anchored Tool-Use for MLLMs](https://mlsanity.com/paper/2605.19528/) (2026)
- [Devils in Question Relay: Source-Conditioned Relay Steering to Mitigate Hallucinations in Audio-visual Large Language Models](https://mlsanity.com/paper/2609.37568/) (2026)

## Abstract (arXiv)

Humans can perceive and understand 3D space and long videos from sequential visual observations. But do vision-language models (VLMs) can? Recent work demonstrates that even state-of-the-art VLMs still struggle to understand 3D space and long videos, although they are powerful in typical vision-language tasks. Current methods often rely on specialized architectural designs to improve performance for 3D tasks and video understanding tasks separately. In contrast, we propose LAST, short for LeArn to Think in Space and Time, to jointly improve 3D spatial and long video understanding for general VLMs with only a set of 2D images as inputs. LAST makes VLMs think in space and time rather than only with text before giving the final answer, building visual thinking trajectories in 3D space and temporal dimension. We demonstrate the effectiveness of LAST in two scenarios: 1) zero-shot, where we directly prompt proprietary models; and 2) fine-tuning general VLMs with data that include thinking trajectories in 3D space and time. We show that LAST brings substantial gains in various benchmarks, including 3 spatial understanding, 4 video understanding, and 3 image understanding tasks. Notably, 15.8% gains on EgoSchema with GPT-4o in a zero-shot manner and 8.3 gains on VSI-Bench compared with Qwen2.5-VL-7B.