Less from More: Reinforcing Sparse Video Reasoning from Dense References

arXiv:2610.10893 · cs.CV · Submitted 2026-10-07 · Read on arXiv

cs.CV

Submitted: 2026-10-07

Updated: 2026-10-07

Terminology

• Grounding — 93× in this paper · explained in 3 episodes
• Benchmark — 44× in this paper · explained in 2 episodes
• Accuracy — 13× in this paper · explained in 1 episode
• Alignment — 9× in this paper · explained in 1 episode
• Robustness — 5× in this paper · explained in 5 episodes
• Ablation — 4× in this paper · explained in 1 episode
• Distillation — 4× in this paper · explained in 2 episodes
• Adaptive Selection — 3× in this paper · explained in 1 episode
• Pruning — 3× in this paper · explained in 4 episodes
• Pseudo-labels — 3× in this paper · explained in 2 episodes
• Reinforcement Learning — 3× in this paper · explained in 4 episodes
• Adaptation — 2× in this paper · explained in 1 episode
• Minimal Video Pairs — 2× in this paper
• Self-distillation — 2× in this paper · explained in 6 episodes
• Calibration — 1× in this paper · explained in 7 episodes
• Core — 1× in this paper · explained in 2 episodes
• Failure Modes — 1× in this paper · explained in 3 episodes
• Feature Extraction — 1× in this paper · explained in 2 episodes
• Fine-Tuning — 1× in this paper · explained in 5 episodes
• Foundation Model — 1× in this paper · explained in 3 episodes
• Foundation Models — 1× in this paper · explained in 7 episodes
• Generative AI — 1× in this paper · explained in 2 episodes
• Instruction Tuning — 1× in this paper · explained in 2 episodes
• KL Regularization — 1× in this paper · explained in 2 episodes
• Reasoning Traces — 1× in this paper · explained in 3 episodes
• Redundancy — 1× in this paper · explained in 2 episodes
• Regularization — 1× in this paper · explained in 3 episodes
• Scaffolding — 1× in this paper · explained in 3 episodes
• Sparsity — 1× in this paper · explained in 4 episodes
• Temporal Reasoning — 1× in this paper · explained in 2 episodes
• Test-time Scaling — 1× in this paper · explained in 2 episodes
• Trace — 1× in this paper · explained in 2 episodes
• Verification — 1× in this paper · explained in 2 episodes
• Verifier — 1× in this paper · explained in 2 episodes

Sources

• Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond
• Qwen3-VL Technical Report
• Qwen2.5-VL Technical Report
• Scaling RL to Long Videos
• Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling
• LOVE-R1: Advancing Long Video Understanding with an Adaptive Zoom-in Mechanism via Multi-Step Reasoning
• Chain-of-Frames: Advancing Video Understanding in Multimodal LLMs via Frame-Aware Reasoning
• Reinforcing Video Reasoning Segmentation to Think Before It Segments
• Video-MMMU: Evaluating Knowledge Acquisition from Multi-Discipline Professional Videos
• A Shortcut-aware Video-QA Benchmark for Physical Understanding via Minimal Video Pairs
• LLaVA-OneVision: Easy Visual Task Transfer
• Reinforcement Learning Tuning for VideoLLMs: Reward Design and Data Efficiency
• VideoChat-R1: Enhancing Spatio-Temporal Perception via Reinforcement Fine-Tuning
• VerIPO: Cultivating Long Reasoning in Video-LLMs via Verifier-Gudied Iterative Policy Optimization
• VideoAuto-R1: Video Auto Reasoning via Thinking Once, Answering Twice
• Time-R1: Post-Training Large Vision Language Model for Temporal Video Grounding
• MARC: Memory-Augmented RL Token Compression for Efficient Video Understanding
• LMMs-Eval: Reality Check on the Evaluation of Large Multimodal Models
• VideoBrain: Learning Adaptive Frame Sampling for Long Video Understanding

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