The paper introduces Temporal-Response Guidance (TRG), a method that enhances on‑policy distillation for video‑language models by aligning teacher corrections with the student’s temporal response space. TRG measures how representations change under local temporal perturbations, projects teacher corrections onto this space, and restores the original correction norm, thereby altering the supervision direction while preserving key loss properties. Experiments on TempCompass, Video‑MME, MVBench, and Video‑MMMU show that TRG boosts a 4B student’s macro accuracy by 2.86 percentage points over the baseline output‑only OPD approach.
arXiv:2609.34581v2 Announce Type: replace Abstract: Temporal video grounding is a key capability of advanced Multimodal Large Language Models (MLLMs) for the thorough understanding of video events, w...
arXiv:2609.40055v1 Announce Type: cross Abstract: On-policy distillation (OPD) provides dense supervision directly on student-generated trajectories, making it an effective post-training strategy for...
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.
arXiv:2610.20111v1 Announce Type: new Abstract: Distilling pretrained video diffusion models into few-step autoregressive (AR) generators typically combines student initialization with distribution m...
arXiv:2608. 16316v1 Announce Type: cross Abstract: Large Multimodal Models (LMMs) for video reasoning have long been hindered by the high computational cost of processing vast amounts of visual information.
arXiv:2609.09300v1 Announce Type: new Abstract: Video understanding demands a convergence of complementary capabilities across perception, temporal understanding, and complex reasoning, which are dif...
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.
arXiv:2608.22364v1 Announce Type: new Abstract: World action models (WAMs) couple visual future prediction with robot action generation, but accelerated students can lose task capabilities during dis...
arXiv:2610.14022v1 Announce Type: cross Abstract: On-policy distillation (OPD) improves language-model by supervising a student on prefixes sampled from its own policy, but its supervision remains co...
arXiv:2609.36995v1 Announce Type: cross Abstract: Few-step streaming audio--video generation requires both causal modeling and step distillation, yet standard training recipes face two context-relate...
arXiv:2609.38282v1 Announce Type: new Abstract: Vision-language models may rewrite anomalous text in images into linguistically plausible expressions, compromising OCR transcription faithfulness. Seq...
arXiv:2606. 08432v1 Announce Type: new Abstract: On-policy distillation (OPD) has become a central post-training tool for large language models (LLMs), providing dense per-token teacher supervision along the student's own rollouts.