# From Seeing to Predicting: A Vision-Language Framework for Trajectory Forecasting and Controlled Video Generation

arXiv: https://arxiv.org/abs/2510.00806 · HTML: https://mlsanity.com/paper/2510.00806/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 27 references that are in the map.
- First posted on arXiv 1 Oct 2025.

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

- [Improved Baselines with Visual Instruction Tuning](https://mlsanity.com/paper/2310.03744/) (2023)
- [InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning](https://mlsanity.com/paper/2305.06500/) (2023)
- [InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks](https://mlsanity.com/paper/2312.14238/) (2023)
- [Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond](https://mlsanity.com/paper/2308.12966/) (2023)
- [Make-A-Video: Text-to-Video Generation without Text-Video Data](https://mlsanity.com/paper/2209.14792/) (2022)
- [Align your Latents: High-Resolution Video Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2304.08818/) (2023)
- [SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features](https://mlsanity.com/paper/2502.14786/) (2025)
- [CogVideo: Large-scale Pretraining for Text-to-Video Generation via Transformers](https://mlsanity.com/paper/2205.15868/) (2022)
- [Shikra: Unleashing Multimodal LLM's Referential Dialogue Magic](https://mlsanity.com/paper/2306.15195/) (2023)
- [ModelScope Text-to-Video Technical Report](https://mlsanity.com/paper/2308.06571/) (2023)
- [Open-Sora: Democratizing Efficient Video Production for All](https://mlsanity.com/paper/2412.20404/) (2024)
- [Ferret: Refer and Ground Anything Anywhere at Any Granularity](https://mlsanity.com/paper/2310.07704/) (2023)
- [GOT-10k: A Large High-Diversity Benchmark for Generic Object Tracking in the Wild](https://mlsanity.com/paper/1810.11981/) (2018)
- [MagicVideo: Efficient Video Generation With Latent Diffusion Models](https://mlsanity.com/paper/2211.11018/) (2022)
- [CameraCtrl: Enabling Camera Control for Text-to-Video Generation](https://mlsanity.com/paper/2404.02101/) (2024)
- [Unifying Flow, Stereo and Depth Estimation](https://mlsanity.com/paper/2211.05783/) (2022)
- [LLM-grounded Diffusion: Enhancing Prompt Understanding of Text-to-Image Diffusion Models with Large Language Models](https://mlsanity.com/paper/2305.13655/) (2023)
- [Tora: Trajectory-oriented Diffusion Transformer for Video Generation](https://mlsanity.com/paper/2407.21705/) (2024)
- [DragAnything: Motion Control for Anything using Entity Representation](https://mlsanity.com/paper/2403.07420/) (2024)
- [Make Pixels Dance: High-Dynamic Video Generation](https://mlsanity.com/paper/2311.10982/) (2023)
- [LaSOT: A High-quality Large-scale Single Object Tracking Benchmark](https://mlsanity.com/paper/2009.03465/) (2020)
- [Towards More Flexible and Accurate Object Tracking with Natural Language: Algorithms and Benchmark](https://mlsanity.com/paper/2103.16746/) (2021)
- [LLM-grounded Video Diffusion Models](https://mlsanity.com/paper/2309.17444/) (2023)
- [Towards Unified Token Learning for Vision-Language Tracking](https://mlsanity.com/paper/2308.14103/) (2023)

## Built on by (most cited first, 1 of 1)

- [Kepler4D: Controllable Future Video Generation via 4D Scene State Evolution](https://mlsanity.com/paper/2610.04152/) (2026)

## Abstract (arXiv)

Current video generation models produce physically inconsistent motion that violates real-world dynamics. We propose TrajVLM-Gen, a two-stage framework for physics-aware image-to-video generation. First, we employ a Vision Language Model to predict coarse-grained motion trajectories that maintain consistency with real-world physics. Second, these trajectories guide video generation through attention-based mechanisms for fine-grained motion refinement. We build a trajectory prediction dataset based on video tracking data with realistic motion patterns. Experiments on UCF-101 and MSR-VTT demonstrate that TrajVLM-Gen outperforms existing methods, achieving competitive FVD scores of 545 on UCF-101 and 539 on MSR-VTT.