CAVE: Competence-Aware Visual Boundary Evidence Alignment for Video Temporal Grounding

arXiv:2608.02078 · cs.CL, cs.CV · Submitted 2026-08-10 · Read on arXiv

Wei Jia, Zhicong Lu, Yu Chen, Xiang Wang, Shuai Li, Wenqian Lv, Jiayue Cao, Huaxing Liu

cs.CL, cs.CV

Submitted: 2026-08-10

Updated: 2026-08-11

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Grounding — 21× in this paper · explained in 3 episodes
• Benchmark — 18× in this paper · explained in 2 episodes
• Alignment — 17× in this paper · explained in 1 episode
• Video Temporal Grounding — 10× in this paper
• GRPO — 7× in this paper · explained in 6 episodes
• Visual Boundary Evidence Alignment Reward — 7× in this paper
• Reinforcement Learning — 6× in this paper · explained in 4 episodes
• Accuracy — 5× in this paper · explained in 1 episode
• Ablation — 4× in this paper · explained in 1 episode
• Competence-Aware Visual Boundary Evidence Alignment — 4× in this paper
• Fine-Tuning — 3× in this paper · explained in 5 episodes
• Performance-Aware Gating for Evidence Supervision — 3× in this paper
• Reinforcement Learning (RL) — 3× in this paper · explained in 25 episodes
• Trace — 3× in this paper · explained in 2 episodes
• Verifiable Rewards — 3× in this paper · explained in 2 episodes
• Ablation study — 2× in this paper · explained in 1 episode
• Consistency — 2× in this paper · explained in 3 episodes
• Generalizability — 2× in this paper · explained in 6 episodes
• Temporal Reasoning — 2× in this paper · explained in 2 episodes
• Actor — 1× in this paper · explained in 3 episodes
• Adaptation — 1× in this paper · explained in 1 episode
• Aggregation — 1× in this paper · explained in 1 episode
• Conference on Computer Vision and Pattern Recognition — 1× in this paper
• GRPO Objective — 1× in this paper · explained in 2 episodes
• Group Relative Policy Optimization — 1× in this paper
• Group Relative Policy Optimization (GRPO) — 1× in this paper · explained in 5 episodes
• Multimodal Reasoning — 1× in this paper · explained in 5 episodes
• Visual Grounding — 1× in this paper · explained in 2 episodes

Sources

• Qwen2.5-VL Technical Report
• TAR: Temporal Anchor-Constrained Reasoning for Video Temporal Grounding
• Attend to Evidence: Evidence-Anchored Spatial Attention Supervision for Multimodal RLVR
• VideoChat-Flash: Hierarchical Compression for Long-Context Video Modeling
• VideoChat-R1: Enhancing Spatio-Temporal Perception via Reinforcement Fine-Tuning
• GPT-4o System Card
• OpenAI GPT-5 System Card
• DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
• Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities
• Qwen3-VL Technical Report
• MiMo-VL Technical Report

Related papers

• Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
• Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
• Subliminal Steering: Stronger Encoding of Hidden Signals
• MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
• The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
• Untangling the Mechanisms of Misleading Context in Medical Question Answering