arXiv Computer Vision By Shravan Venkatraman, Wenshuai Zhao, Mohammad Hassan Vali, Arno Solin

Temporal Self-Distillation: Learning Visual State Tracking in Videos Without Supervision

Read the original on arXiv Computer Vision →

The paper introduces S$^3$T, a fully self‑contained framework for continuous video state tracking that uses temporal self‑distillation. It treats denser temporal sampling as privileged information, letting a dense‑view teacher guide a sparse‑view student to match its next‑token distribution without external labels or reward signals. Experiments on LLaVA-OneVision-2-8B show significant accuracy gains on VSTAT and MVBench benchmarks, and the learned capability transfers from synthetic to real videos.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computer Vision.

arXiv Computer Vision
Aug 28

Video-OPSD: Exploiting Privileged Visual Evidence for On-Policy Self-Distillation in Video Large Language Models

Video-OPSD introduces a post‑training framework for Video Large Language Models that leverages privileged visual evidence to enhance on‑policy self‑distillation. The method constructs a self‑teacher conditioned only on annotated evidence frames, while the student processes the full video, allowing the teacher to provide more focused supervision. Additionally, an evidence‑guided token optimization scheme weights distillation based on each token’s reliance on privileged evidence, improving perceptually grounded reasoning. Experiments demonstrate consistent gains over standard OPSD and comparable performance to GRPO with less training time.

By Ziyue Wang, Shiqi Huang, Weiwen Xu, Bihan Wen, Xudong Jiang
arXiv AI
Aug 28

LeVJEPA: Efficient & Scalable Video Pretraining without the Heuristics

LeVJEPA is a video encoder that eliminates the need for architectural asymmetries, exponential-moving-average target encoders, stop-gradients, and capacity-limited predictors used in prior self‑supervised methods. It trains a single encoder with an invariance loss over global and local views, regularized by SIGReg to prevent collapse, and achieves strong performance with far less pretraining compute. The approach also allows block‑causal attention, making temporal ordering a property of the encoder itself, and matches or surpasses state‑of‑the‑art baselines on both appearance‑centric and motion‑centric benchmarks.

By Lukas Kuhn, Lucas Maes, Giuseppe Serra, Quentin Le Lidec, Yann LeCun, Randall Balestriero, Florian Buettner
arXiv Computer Vision
Sep 3

Learning to Track from Privileged Target Appearances

The paper introduces Privileged Appearance Transfer for Tracking (PATT), a teacher‑student framework that leverages exact target crops from past, current, and future frames during training to improve visual tracking. By weighting the teacher’s guidance with its localization advantage and accuracy, PATT transfers privileged appearance information to a deployable tracker that only uses past‑frame templates at inference. Experiments on seven benchmarks show consistent performance gains across both long‑ and short‑term tracking protocols.

By Xin Chen, Jiao Xu, Dong Wang, Huchuan Lu, Kede Ma