VAD: Attributing Visual Evidence for Target Reconstruction in Multimodal On-Policy Distillation

• URL: http://arxiv.org/abs/2607.28590v1
• Date: Thu, 30 Jul 2026 17:43:46 GMT
• Title: VAD: Attributing Visual Evidence for Target Reconstruction in Multimodal On-Policy Distillation
• Abstract summary: Multimodal on-policy distillation transfers fine-grained visual knowledge by supervising student-generated trajectories with a privileged-view teacher.<n>Key challenge is to estimate which corrections are supported by visual evidence, not merely where or how strongly to distill.<n>We introduce Visual Attribution Distillation (VAD), a counterfactual target-reconstruction algorithm that estimates the visually attributable part of a teacher correction.
• Score: 46.347555076026964
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Multimodal on-policy distillation (OPD) transfers fine-grained visual knowledge by supervising student-generated trajectories with a privileged-view teacher. Yet its next-token corrections are source-mixed, combining visual signals with linguistic priors and teacher-specific effects. The key challenge is to estimate which corrections are supported by visual evidence, not merely where or how strongly to distill. We introduce Visual Attribution Distillation (VAD), a counterfactual target-reconstruction algorithm that estimates the visually attributable part of a teacher correction. At each student-generated prefix, VAD evaluates the same fixed teacher with the relevant evidence present and removed. The corresponding change in centered log-probabilities defines ut, a signed proxy for the visual evidence direction that estimates how revealing the evidence supports or refutes candidate tokens. VAD projects the original correction onto this proxy to obtain an intervention-aligned component and a proxy-unexplained residual, then reconstructs a student-anchored target from the former. During training, this reconstructed target supplies the primary supervision signal, while the privileged teacher contributes a weak regularizer. Across six fine-grained visual benchmarks at 4B and 9B scales, VAD outperforms direct privileged-view distillation and visual-advantage weighting. Token- level and controlled-target analyses show that the proxy-aligned component is enriched in task-relevant visual corrections and yields stronger target shifts, especially when evidence refutes a mistaken answer. These results support counterfactual target reconstruction as an effective alternative to source-mixed supervision.

Related papers

• OPD-Aha: From Linguistic Momentum to Visual Reflection in Multimodal On-Policy Distillation [15.986808086256792]
  Privileged on-policy distillation improves multimodal reasoning by allowing a teacher to evaluate student trajectories using rich, training-only visual evidence.<n>We find that the teacher's visual corrective preference is not lost under this misleading agreement.<n>We introduce OPD-Aha, which reconstructs the distillation target directly from this isolated visual preference.
  arXiv  Detail & Related papers  (2026-09-15T00:25:28Z)
• CA-OPD: Confidence-Aware On-Policy Distillation for Structured Visual Prediction [12.346416465825627]
  Confidence-Aware On-Policy Distillation (CA-OPD) is a framework that couples reliable rollout construction with adaptive supervision.<n> Evaluated in a multi-teacher setting for GUI grounding and optical character recognition, CA-OPD substantially improves the Qwen3.5-0.8B baseline.
  arXiv  Detail & Related papers  (2026-09-02T10:11:59Z)
• 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)
• Purified OPSD: On-Policy Self-Distillation Without Losing How to Think [52.879387744920415]
  We find that on-policy self-distillation (OPSD) consistently fails on long chain-of-thought (long-CoT) reasoning models.<n>We propose a two-step solution: first, we construct a reference-only teacher to isolate the non-transferable component of the supervision signal.<n>Second, we use pointwise mutual information (PMI) as the mechanism to transform this residual into a well-formed PMI target distribution.
  arXiv  Detail & Related papers  (2026-07-02T14:33:07Z)
• Token-level Response-visual Attention Guidance for Multimodal LLMs Knowledge Distillation [36.9736177938003]
  We introduce Token-level Response-visual Attention Guidance (TRAG)<n>TRAG shifts the focus to response-to-vision signals and employs token-specific objectives.<n>Extensive experimental results on multiple benchmarks demonstrate that TRAG significantly outperforms prior distillation baselines.
  arXiv  Detail & Related papers  (2026-07-01T08:03:30Z)
• HERO: Hindsight-Enhanced Reflection from Environment Observations for Agentic Self-Distillation [50.53459634301361]
  HERO is a hindsight-enhanced self-distillation framework that uses next environment observations as locally aligned feedback.<n> HERO improves task success and reduces unnecessary turns over environment-feedback-only self-distillation and GRPO.
  arXiv  Detail & Related papers  (2026-06-10T01:35:34Z)
• Trajectory-Refined Distillation [25.346810464266497]
  Trajectory-Refined Distillation (TRD) is a trajectory-level correction method that revises the student's rollout under the teacher guidance while within on-policy support.<n> TRD can also be applied to on-policy self-distillation (OPSD), a parameter-sharing variant that uses the student model conditioned on privileged informations as the teacher.
  arXiv  Detail & Related papers  (2026-06-07T03:17:25Z)
• AVSD: Adaptive-View Self-Distillation by Balancing Consensus and Teacher-Specific Privileged Signals [65.71225905458182]
  Self-distillation enables language models to learn on-policy from their own trajectories by using the same model as both student and teacher.<n>This setup provides dense token-level feedback without relying on a separate external model.<n>We introduce AVSD, a novel method of self-distillation with multiple privileged-information views.
  arXiv  Detail & Related papers  (2026-05-20T03:06:36Z)
• Molecular Identifier Visual Prompt and Verifiable Reinforcement Learning for Chemical Reaction Diagram Parsing [52.825281124618535]
  Reaction diagram parsing (RxnDP) is critical for extracting chemical synthesis information from literature.<n>Recent Vision-Language Models (VLMs) have emerged as a promising paradigm to automate this complex visual reasoning task.<n>This work enhances VLM-based RxnDP from two complementary perspectives: prompting representation and learning paradigms.
  arXiv  Detail & Related papers  (2026-03-16T09:17:05Z)
• Look As You Think: Unifying Reasoning and Visual Evidence Attribution for Verifiable Document RAG via Reinforcement Learning [55.232400251303794]
  Look As You Think (LAT) is a reinforcement learning framework that trains models to produce verifiable reasoning paths with consistent attribution.<n>LAT consistently improves the vanilla model in both single- and multi-image settings, yielding average gains of 8.23% in soft exact match (EM) and 47.0% in IoU@0.5.
  arXiv  Detail & Related papers  (2025-11-15T02:50:23Z)

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.