Summarize Before Grounding: Query-Guided Chunk Condensation for Long-Video Temporal Grounding

arXiv:2609.34598 · cs.CV, cs.AI · Submitted 2026-09-28 · Read on arXiv

cs.CV, cs.AI

Submitted: 2026-09-28

Updated: 2026-09-28

Terminology

• Grounding — 98× in this paper · explained in 3 episodes
• Benchmark — 36× in this paper · explained in 2 episodes
• GRPO — 9× in this paper · explained in 6 episodes
• Ablation — 6× in this paper · explained in 1 episode
• Accuracy — 6× in this paper · explained in 1 episode
• KV cache — 6× in this paper · explained in 3 episodes
• Regularization — 5× in this paper · explained in 3 episodes
• GRPO Objective — 4× in this paper · explained in 2 episodes
• KL Regularization — 4× in this paper · explained in 2 episodes
• Temporal Reasoning — 3× in this paper · explained in 2 episodes
• Transformer — 3× in this paper · explained in 2 episodes
• Verifiable Rewards — 3× in this paper · explained in 2 episodes
• Fine-Tuning — 2× in this paper · explained in 5 episodes
• Reinforcement Learning — 2× in this paper · explained in 4 episodes
• Ablation study — 1× in this paper · explained in 1 episode
• Action Space — 1× in this paper · explained in 1 episode
• Adaptation — 1× in this paper · explained in 1 episode
• Aggregation — 1× in this paper · explained in 1 episode
• Embeddings — 1× in this paper · explained in 2 episodes
• Failure Modes — 1× in this paper · explained in 3 episodes
• Group Relative Policy Optimization (GRPO) — 1× in this paper · explained in 5 episodes
• Latent Representation — 1× in this paper · explained in 2 episodes
• RAG — 1× in this paper · explained in 3 episodes
• RLVR with Group Relative Policy Optimization — 1× in this paper
• Transferability — 1× in this paper · explained in 4 episodes
• Vision-language models — 1× in this paper · explained in 2 episodes
• Visual Grounding — 1× in this paper · explained in 2 episodes

Sources

• Universal Video Temporal Grounding with Generative Multi-modal Large Language Models
• REFRAG: Rethinking RAG based Decoding
• Momentor: Advancing Video Large Language Model with Fine-Grained Temporal Reasoning
• DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
• LongVU: Spatiotemporal Adaptive Compression for Long Video-Language Understanding
• HawkEye: Training Video-Text LLMs for Grounding Text in Videos
• Time-R1: Post-Training Large Vision Language Model for Temporal Video Grounding
• DATE: Dynamic Absolute Time Enhancement for Long Video Understanding
• TimeSuite: Improving MLLMs for Long Video Understanding via Grounded Tuning
• TimeLens: Rethinking Video Temporal Grounding with Multimodal LLMs

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