arXiv AI
On-Policy Visual Evidence Distillation
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv AI
Sep 16
OPD-Aha: From Linguistic Momentum to Visual Reflection in Multimodal On-Policy Distillation
OPD‑Aha is a privileged on‑policy distillation method that improves multimodal reasoning by reconstructing the distillation target from the teacher’s isolated visual preference instead of relying on fragile teacher‑student discrepancies. It suppresses continuations that contradict the image, encouraging students to interrupt flawed reasoning with reflection tokens such as "wait" and "actually." This approach leads to consistent improvements across fine‑grained perception and complex multimodal reasoning benchmarks.
arXiv Machine Learning
Jun 5
ViCuR: Visual Cues as Recoverable Privilege for Multimodal On-Policy Distillation
arXiv:2606. 05718v1 Announce Type: cross Abstract: On-policy distillation (OPD) improves reasoning by training a student on trajectories sampled from its own policy under supervision from a teacher.
Hugging Face Trending Papers
Sep 15
OPD-Aha: From Linguistic Momentum to Visual Reflection in Multimodal On-Policy Distillation
Privileged on-policy distillation improves multimodal reasoning by allowing a teacher to evaluate student trajectories using rich, training-only visual evidence. Both models score these trajectories w...
Hugging Face Trending Papers
Aug 9
OpenVisTool: An Open Recipe for Synthesizing Instructive Visual Tool-Use Trajectories
Visual tool use has emerged as a fundamental capability for multimodal agents to actively acquire evidence beyond a fixed image encoding. The prevailing recipe learns this capability from teacher-generated trajectories filtered for answer correctness, implicitly assuming that every successful demonstration provides effective supervision.
arXiv Machine Learning
Aug 11
OpenVisTool: An Open Recipe for Synthesizing Instructive Visual Tool-Use Trajectories
arXiv:2608. 08557v1 Announce Type: cross Abstract: Visual tool use has emerged as a fundamental capability for multimodal agents to actively acquire evidence beyond a fixed image encoding.
arXiv Computer Vision
Sep 3
CA-OPD: Confidence-Aware On-Policy Distillation for Structured Visual Prediction
CA-OPD is a confidence‑aware on‑policy distillation framework that improves structured visual prediction by using teacher confidence to selectively correct unreliable student transitions and gradually transfer rollout control to the student. The method aligns supervision with intervention decisions, providing direct cross‑entropy loss for corrected tokens and full predictive distribution for retained tokens. In a multi‑teacher setting for GUI grounding and OCR, CA‑OPD significantly outperforms the Qwen3.5‑0.8B baseline, achieving large gains on benchmarks such as ScreenSpot‑Pro and OCRBench‑v2 English.