StreamOPD: A Post-Training Recipe with Spatio-Temporal Cue Gating for Streaming Video Understanding

• URL: http://arxiv.org/abs/2608.16320v1
• Date: Mon, 17 Aug 2026 09:25:36 GMT
• Title: StreamOPD: A Post-Training Recipe with Spatio-Temporal Cue Gating for Streaming Video Understanding
• Abstract summary: Reinforcement learning with verifiable rewards fits this regime poorly, encouraging long think-then-answer'' generations.<n>On-policy distillation supplies dense token-level teacher supervision on student trajectories but is stable only when both models train in thinking mode.<n>We provide a transparent and reproducible reference for open-source streaming-video research.
• Score: 16.629848186775718
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Streaming video understanding demands direct responses from the causally observed prefix of an unfolding video. Existing systems add inference-time memory, retrieval, and compression, yet a training-free sliding-window baseline already matches them. We therefore fix a memory-free recent-window protocol and ask how far post-training alone can go. Reinforcement learning with verifiable rewards fits this regime poorly, encouraging long ``think-then-answer'' generations, while on-policy distillation (OPD) supplies dense token-level teacher supervision on student trajectories but is stable only when both models train in thinking mode. These observations lead to \textsc{StreamOPD}, a recipe combining verifiable streaming-video data, thinking-mode OPD, and instruct-mode deployment. It raises StreamingBench from $77.9\%$ to $83.9\%$---within $0.3$ points of the 9B teacher---and improves OVO-Bench excluding its hallucination-detection subtask (HLD) by $9.1$ points under unchanged inference. As a teacher-privilege extension, \emph{Spatio-Temporal CueGate (ST-CueGate)} aggregates cue-versus-no-cue teacher likelihood ratios into a group-relative response score that reweights OPD. It reaches $71.9\%$ on OVO-Bench (excluding HLD) and $64.9\%$ on Video-MME, and is the only variant that stays above the base model on all four benchmarks. Replacing the teacher with a frozen copy of the student's initial policy---on-policy self-distillation---retains most of these gains and lifts HLD to $57.0\%$, above both the untrained student and the 9B teacher, so abstention loss is not intrinsic to the recipe. We provide a transparent and reproducible reference for open-source streaming-video research.

Related papers

• Temporal Self-Distillation: Learning Visual State Tracking in Videos Without Supervision [22.058460912910125]
  S$3$T (Self-Supervised Self-Distillation over Time) is the first fully self-contained framework for continuous video state tracking.<n>On LLaVA-OneVision-2-8B, S$3$T improves VSTAT accuracy by $+1.74$ as a single model, $+2.38$ with souping, and $+2.70$ with additional vision-encoder adaptation.<n>The capability learned from unlabeled synthetic clips transfers to real videos, improving performance by $+7.95$ on VSTAT-YouTube state-tracking questions and $+4.50
  arXiv  Detail & Related papers  (2026-09-03T17:59:55Z)
• Video-OPSD: Exploiting Privileged Visual Evidence for On-Policy Self-Distillation in Video Large Language Models [58.45264308304815]
  On-policy self-distillation (OPSD) has recently emerged as an effective post-training paradigm that improves policy optimization through dense token-level supervision from a privileged self-teacher.<n>We present $textbfVideo-OPSD$, an OPSD framework that exploits privileged visual evidence for both self-teacher construction and knowledge transfer.
  arXiv  Detail & Related papers  (2026-08-27T12:51:32Z)
• ReOrder-OPD:Reliability-Aware Prompt Ordering for On-Policy Distillation [25.69241346799495]
  We define prompt-level teacher continuation reliability $R$ as the teacher's probability of reaching a correct answer from a student prefix.<n>We show that high-$R$ prompts yield larger OPD gains and that descending-$R$ training outperforms random and ascending orders.
  arXiv  Detail & Related papers  (2026-08-11T13:27:56Z)
• Visual Contrastive Self-Distillation [61.298159957622886]
  We propose Visual Contrastive Self-Distillation, which converts image-content removal into an on-policy self-distillation signal.<n>We use this contrast to sharpen the teacher's original-image distribution within its plausible support, and distill the resulting full-distribution target into the student.
  arXiv  Detail & Related papers  (2026-07-23T17:37:37Z)
• H$^2$SD: Hybrid Hindsight Self-Distillation [61.71131241473028]
  Reinforcement learning with verifiable rewards (RLVR) provides reliable outcome supervision for language model reasoning.<n>Existing self-distillation methods add a privileged teacher but typically assign it a fixed role.<n>We introduce Hybrid Hindsight Self-Distillation ($mathrmH2mathrmSD$), which jointly adapts teacher context and update strategy to trajectory correctness.
  arXiv  Detail & Related papers  (2026-07-21T10:47:27Z)
• OPSD-V: On-Policy Self-Distillation for Post-Training Few-Step Autoregressive Video Generators [68.69611976783243]
  OPSD-V is an on-policy self-distillation paradigm for post-training few-step autoregressive (AR) video diffusion models.<n>Key idea is to introduce real long-video data as temporal context during training and use it to provide dense trajectory-level supervision.<n>Experiments show consistent improvements in visual quality, motion dynamics, and VBenchLong scores.
  arXiv  Detail & Related papers  (2026-07-09T17:59:11Z)
• Visual-OPSD: Cross-Modal On-Policy Self-Distillation for Efficient Unified Multimodal Reasoning [30.851590309402436]
  Unified multimodal models (UMMs) interleave generated ''visual thoughts'' (VTs) with text reasoning to improve spatial tasks.<n>This incurs roughly an order-of-magnitude inference cost from multi-step diffusion.<n>We propose Visual On-Policy Self-Distillation(Visual-OPSD) to solve this problem.
  arXiv  Detail & Related papers  (2026-06-17T11:59:15Z)
• ViCuR: Visual Cues as Recoverable Privilege for Multimodal On-Policy Distillation [5.131753844398592]
  ViCuR is a visually grounded privileged-teacher distillation framework.<n>It replaces answer-side privilege with visual cues.<n>It consistently improves over answer-based on-policy self-distillation.
  arXiv  Detail & Related papers  (2026-06-04T05:18:13Z)
• Your Teacher Can't Help You Here: Combating Supervision Fidelity Decay in On-Policy Distillation [81.10000755917712]
  On-policy distillation transfers reasoning capabilities by training a student model on its own generated trajectories using token-level feedback from a teacher.<n>As student-generated prefixes lengthen, the teacher's next-token distribution becomes less confident and less discriminative.<n>To mitigate SFD, we introduce textbfLookahead Group Reward (ours).
  arXiv  Detail & Related papers  (2026-05-29T04:39:20Z)
• On-Policy Distillation with Best-of-N Teacher Rollout Selection [54.91780727674628]
  We propose BRTS, a Best-of-N Rollout Teacher Selection framework for on-policy distillation.<n>BRTS augments standard student-context OPD with a teacher-context supervision branch constructed from the teacher trajectory.<n>BRTS improves over standard OPD on challenging reasoning benchmarks, with the largest gains on harder datasets.
  arXiv  Detail & Related papers  (2026-05-10T19:49:00Z)
• Prune-OPD: Efficient and Reliable On-Policy Distillation for Long-Horizon Reasoning [66.52232008796294]
  Prune-OPD dynamically aligns training budgets with supervision quality.<n>It reduces training time by 37.6%--68.0% while preserving, and often improving, performance on challenging benchmarks.
  arXiv  Detail & Related papers  (2026-05-08T14:38:53Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.