Counterfactual Attention Policy Distillation for Temporal Video Grounding

arXiv:2609.34581 · cs.CV · Submitted 2026-09-28 · Read on arXiv

cs.CV

Submitted: 2026-09-28

Updated: 2026-09-29

Terminology

• Distillation — 43× in this paper · explained in 2 episodes
• Grounding — 37× in this paper · explained in 3 episodes
• Benchmark — 19× in this paper · explained in 2 episodes
• On-Policy Distillation — 12× in this paper · explained in 3 episodes
• Calibration — 8× in this paper · explained in 7 episodes
• GRPO — 5× in this paper · explained in 6 episodes
• Counterfactual Attention Policy Distillation — 4× in this paper
• Knowledge Distillation — 4× in this paper · explained in 11 episodes
• Ablation — 3× in this paper · explained in 1 episode
• Core — 2× in this paper · explained in 2 episodes
• Instruction Tuning — 2× in this paper · explained in 2 episodes
• Temporal Reasoning — 2× in this paper · explained in 2 episodes
• Transformer — 2× in this paper · explained in 2 episodes
• Ablation study — 1× in this paper · explained in 1 episode
• Accuracy — 1× in this paper · explained in 1 episode
• Causal Inference — 1× in this paper · explained in 4 episodes
• Contrastive Learning — 1× in this paper · explained in 5 episodes
• Distribution Matching — 1× in this paper · explained in 2 episodes
• Fine-Tuning — 1× in this paper · explained in 5 episodes
• Multimodal Reasoning — 1× in this paper · explained in 5 episodes
• Reinforcement Learning — 1× in this paper · explained in 4 episodes
• Teacher-Student Distillation — 1× in this paper · explained in 2 episodes
• Verifiable Rewards — 1× in this paper · explained in 2 episodes

Sources

• Qwen2.5-VL Technical Report
• Qwen3-VL Technical Report
• Knowledge Distillation and Dataset Distillation of Large Language Models: Emerging Trends, Challenges, and Future Directions
• Reinforced Attention Learning
• VideoChat-R1: Enhancing Spatio-Temporal Perception via Reinforcement Fine-Tuning
• DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
• A Survey of On-Policy Distillation for Large Language Models
• HawkEye: Training Video-Text LLMs for Grounding Text in Videos
• MiMo-VL Technical Report
• TIP: Token Importance in On-Policy Distillation
• Survey on Knowledge Distillation for Large Language Models: Methods, Evaluation, and Application

Related papers

• Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
• AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
• Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
• MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
• TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
• A Survey on Efficient Vision-Language-Action Models