arXiv Computer Vision
Learning from Next-Frame Prediction: Towards Unified and Scalable Visual Representation Learning
Read the original on arXiv Computer Vision →The Flow has not summarised this story yet — read it at arXiv Computer Vision.
Related stories
arXiv Computer Vision
Sep 28
Learning from Next-Frame Prediction: Autoregressive Video Modeling Encodes Effective Representations
arXiv:2512.21004v2 Announce Type: replace Abstract: Recent advances in pretraining general foundation models have significantly improved performance across diverse downstream tasks. While autoregress...
arXiv AI
Jul 15
The TIME Machine: On The Power of Motion for Efficient Perception
arXiv:2605. 23045v2 Announce Type: replace-cross Abstract: Video representation learning has seen tremendous progress in recent years.
arXiv AI
Jun 16
Momentum-Guided Semantic Forecasting (MoFore) for Self-Supervised Video Representation Learning
arXiv:2606. 14765v1 Announce Type: cross Abstract: Self-supervised video representation learning has recently advanced through contrastive learning, masked reconstruction, and predictive representation learning.
arXiv Computer Vision
Oct 2
Latent-Foresight: End-to-End Learning Predictable Representations for Latent World Models
arXiv:2610.01942v1 Announce Type: new Abstract: Predicting the future evolution of a scene is a fundamental capability for world modeling. Recent work has shown that operating in the feature space of...
arXiv AI
Aug 18
Beyond Visual CoT: Internalized Visual Thinking for Proactive Video Reasoning
arXiv:2608. 15869v1 Announce Type: cross Abstract: Multimodal large language models increasingly use visual chain-of-thought (Visual CoT) to reason about spatial, temporal, and embodied environments.
arXiv Computer Vision
Oct 16
Imagine Before You Predict: Interleaved Latent Visual Reasoning for Video Event Prediction
The paper introduces Future‑L1, an interleaved latent visual reasoning framework that alternates between language tokens and continuous latent visual spans during autoregressive decoding for video event prediction. By training on a curated dataset (Future‑L1‑50K) and optimizing latent trajectories with a latent‑aware RL objective (LA‑DAPO), Future‑L1 achieves state‑of‑the‑art results on FutureBench and TwiFF‑Bench, outperforming prior models by significant margins. The work demonstrates that preserving intermediate visual semantics in latent space, rather than verbalizing every reasoning step, leads to more accurate and visually grounded future predictions.