arXiv AI
Less Data, Better Timing: Student-Curriculum Coupling for VLM On-Policy Distillation in Temporal Video Grounding
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv Computer Vision
Aug 28
Video-OPSD: Exploiting Privileged Visual Evidence for On-Policy Self-Distillation in Video Large Language Models
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 Computer Vision
4d ago
Counterfactual Attention Policy Distillation for Temporal Video Grounding
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 Computer Vision
Sep 10
Video-MOPD: Multi-Teacher On-Policy Distillation for Video Understanding
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...
arXiv AI
Aug 21
VISD: Enhancing Video Reasoning via Structured Self-Distillation
arXiv:2605. 06094v5 Announce Type: replace-cross 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.
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.
arXiv Computer Vision
Sep 3
TempoGround: State-Aware Streaming Visual Grounding with Vision-Language Models
TempoGround is a vision‑language model–native framework for streaming visual grounding that detects cross‑frame object correspondence and explicitly models object presence states. It uses a curriculum prediction mechanism to resolve 2D instance association, predict object entry, continuation, or exit, decode 2D boxes, and lift them to 3D camera‑frame boxes. The approach is further refined with Streaming Grounding Reinforcement, which optimizes grounding, identity, and consistency rewards, and achieves significant improvements on multiple streaming visual grounding benchmarks.