VISD: Enhancing Video Reasoning via Structured Self-Distillation

• URL: http://arxiv.org/abs/2605.06094v3
• Date: Mon, 11 May 2026 02:55:14 GMT
• Title: VISD: Enhancing Video Reasoning via Structured Self-Distillation
• Abstract summary: Training VideoLLMs for complex reasoning remains challenging due to sequence of level level rewards and the lack of fine grained credit assignment over long, temporally grounded reasoning trajectories.<n>We propose VISD, a structured self distillation framework that introduces diagnostically meaningful privileged information for video reasoning.
• Score: 4.8876574457819855
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Training VideoLLMs for complex reasoning remains challenging due to sparse sequence level rewards and the lack of fine grained credit assignment over long, temporally grounded reasoning trajectories. While reinforcement learning with verifiable rewards (RLVR) provides reliable supervision, it fails to capture token level contributions, leading to inefficient learning. Conversely, existing self distillation methods offer dense supervision but lack structure and diagnostic specificity, and often interact unstably with reinforcement learning. In this work, we propose VISD, a structured self distillation framework that introduces diagnostically meaningful privileged information for video reasoning. VISD employs a video aware judge model to decompose reasoning quality into multiple dimensions, including answer correctness, logical consistency, and spatio-temporal grounding, and uses this structured feedback to guide a teacher policy for token level supervision. To stably integrate dense supervision with RL, we introduce a direction magnitude decoupling mechanism, where rollout level advantages computed from rewards determine update direction, while structured privileged signals modulate token level update magnitudes. This design enables semantically aligned and fine grained credit assignment, improving both reasoning faithfulness and training efficiency. Additionally, VISD incorporates curriculum scheduling and EMA based teacher stabilization to support robust optimization over long video sequences. Experiments on diverse benchmarks show that VISD consistently outperforms strong baselines, improving answer accuracy and spatio temporal grounding quality. Notably, VISD reaches these gains with nearly 2x faster convergence in optimization steps, highlighting the effectiveness of structured self supervision in improving both performance and sample efficiency for VideoLLMs.

Related papers

• CARE: Competence-Aware Reward Shaping for Adaptive Reasoning Length in Video-MLLMs [50.189987475377656]
  We propose CARE, a competence-aware reward shaping framework for adaptive reasoning length optimization in multimodal reasoning.<n> CARE maintains a smoothed competence estimate via an exponential moving average of pass rates, and uses it to route training into progressive stages.<n>Experiments on multiple video reasoning and general video understanding benchmarks demonstrate that CARE consistently improves reasoning accuracy, stabilizes reinforcement learning, and significantly enhances token efficiency.
  arXiv  Detail & Related papers  (2026-06-18T08:28:26Z)
• Dual-branch Distilled Transformer for Efficient Asymmetric UAV Tracking [34.13651852483772]
  EATrack is a teacher-guided dual-branch distillation strategy for UAV tracking.<n>It compensates for weakened representations by guiding the student to learn strong target representations.<n>Experiments on five UAV benchmarks demonstrate that EATrack achieves a favorable balance between accuracy and speed.
  arXiv  Detail & Related papers  (2026-05-27T06:20:13Z)
• TRIMMER: A New Paradigm for Video Summarization through Self-Supervised Reinforcement Learning [8.864968998286772]
  We propose a novel self-supervised reinforcement learning framework for video summarization.<n>We show it achieves state-of-the-art performance among unsupervised and self-supervised methods.<n>It remains competitive with leading supervised approaches, highlighting its effectiveness for scalable and general video summarization.
  arXiv  Detail & Related papers  (2026-05-03T00:55:02Z)
• STRIVE: Structured Spatiotemporal Exploration for Reinforcement Learning in Video Question Answering [28.670443420523796]
  STRIVE is a structured reinforcement learning framework for question answering.<n>It enriches reward signals and promotes more stable and informative policy updates.<n>It prioritizes frames most relevant to the input question while preserving temporal coverage.
  arXiv  Detail & Related papers  (2026-04-02T09:35:27Z)
• VisionCoach: Reinforcing Grounded Video Reasoning via Visual-Perception Prompting [58.508924874097715]
  VisonCoach consists of two components: (1) Visual Prompt Selector, which predicts appropriate prompt types conditioned on the video and question, and (2) Spatio-Reasoner, optimized with RL under visual prompt guidance and object grounding rewards.<n>Our results show that visual prompting during training improves grounded video reasoning, while distract-distillationSense enables the model to this ability without requiring prompts at inference time.
  arXiv  Detail & Related papers  (2026-03-15T23:32:02Z)
• PromptCD: Test-Time Behavior Enhancement via Polarity-Prompt Contrastive Decoding [85.22047087898311]
  We introduce Polarity-Prompt Contrastive Decoding (PromptCD), a test-time behavior control method that generalizes contrastive decoding to broader enhancement settings.<n>PromptCD constructs paired positive and negative guiding prompts for a target behavior and contrasts model responses to reinforce desirable outcomes.<n>Experiments on the "3H" alignment objectives demonstrate consistent and substantial improvements, indicating that post-trained models can achieve meaningful self-enhancement purely at test time.
  arXiv  Detail & Related papers  (2026-02-24T08:56:52Z)
• Sycophancy Mitigation Through Reinforcement Learning with Uncertainty-Aware Adaptive Reasoning Trajectories [58.988535279557546]
  We introduce textbf sycophancy Mitigation through Adaptive Reasoning Trajectories.<n>We show that SMART significantly reduces sycophantic behavior while preserving strong performance on out-of-distribution inputs.
  arXiv  Detail & Related papers  (2025-09-20T17:09:14Z)
• ViaRL: Adaptive Temporal Grounding via Visual Iterated Amplification Reinforcement Learning [68.76048244253582]
  We introduce ViaRL, the first framework to leverage rule-based reinforcement learning (RL) for optimizing frame selection in video understanding.<n>ViaRL utilizes the answer accuracy of a downstream model as a reward signal to train a frame selector through trial-and-error.<n>ViaRL consistently delivers superior temporal grounding performance and robust generalization across diverse video understanding tasks.
  arXiv  Detail & Related papers  (2025-05-21T12:29:40Z)
• StPR: Spatiotemporal Preservation and Routing for Exemplar-Free Video Class-Incremental Learning [79.44594332189018]
  Class-Incremental Learning (CIL) seeks to develop models that continuously learn new action categories over time without previously acquired knowledge.<n>Existing approaches either rely on forgetting, raising concerns over memory and privacy, or adapt static image-based methods that neglect temporal modeling.<n>We propose a unified and exemplar-free VCIL framework that explicitly disentangles and preserves information.
  arXiv  Detail & Related papers  (2025-05-20T06:46:51Z)
• Dataset Awareness is not Enough: Implementing Sample-level Tail Encouragement in Long-tailed Self-supervised Learning [16.110763554788445]
  We introduce pseudo-labels into self-supervised long-tailed learning, utilizing pseudo-label information to drive a dynamic temperature and re-weighting strategy. We analyze the lack of quantity awareness in the temperature parameter and use re-weighting to compensate for this deficiency, thereby achieving optimal training patterns at the sample level.
  arXiv  Detail & Related papers  (2024-10-30T10:25:22Z)

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.