Finding the Right Evidence: Factor-Guided Coarse-to-Fine Reasoning for Long Videos

arXiv:2608.26355 · cs.CV, cs.LG · Submitted 2026-08-26 · Read on arXiv

cs.CV, cs.LG

Submitted: 2026-08-26

Updated: 2026-08-26

Code: https://github.com/HKUST-KnowComp/PACE

Terminology

• Accuracy — 35× in this paper · explained in 1 episode
• Verification — 30× in this paper · explained in 2 episodes
• Benchmark — 27× in this paper · explained in 2 episodes
• Trace — 17× in this paper · explained in 2 episodes
• Ablation — 7× in this paper · explained in 1 episode
• Foundation Model — 7× in this paper · explained in 3 episodes
• Foundation Models — 7× in this paper · explained in 7 episodes
• Agentic Framework — 5× in this paper · explained in 6 episodes
• Ablation study — 3× in this paper · explained in 1 episode
• Adam — 3× in this paper · explained in 2 episodes
• Agentic System — 3× in this paper · explained in 2 episodes
• Redundancy — 3× in this paper · explained in 2 episodes
• Robustness — 3× in this paper · explained in 5 episodes
• Hallucination — 2× in this paper · explained in 3 episodes
• Introspection — 2× in this paper · explained in 2 episodes
• Pruning — 2× in this paper · explained in 4 episodes
• Ablation Studies — 1× in this paper · explained in 1 episode
• Abundance — 1× in this paper · explained in 1 episode
• Action Space — 1× in this paper · explained in 1 episode
• Agentic Search — 1× in this paper · explained in 1 episode
• Aggregation — 1× in this paper · explained in 1 episode
• Alignment — 1× in this paper · explained in 1 episode
• Benchmarking — 1× in this paper · explained in 3 episodes
• Consistency — 1× in this paper · explained in 3 episodes
• Cosine Similarity — 1× in this paper · explained in 3 episodes
• Distillation — 1× in this paper · explained in 2 episodes
• Elias — 1× in this paper · explained in 2 episodes
• Embeddings — 1× in this paper · explained in 2 episodes
• Generalization — 1× in this paper · explained in 13 episodes
• Generative Model — 1× in this paper · explained in 2 episodes
• Grounding — 1× in this paper · explained in 3 episodes
• Instruction Tuning — 1× in this paper · explained in 2 episodes
• Regret — 1× in this paper · explained in 3 episodes
• Test-time Scaling — 1× in this paper · explained in 2 episodes
• Two-Stage Framework — 1× in this paper · explained in 2 episodes
• Visual Grounding — 1× in this paper · explained in 2 episodes

Sources

• Qwen3-VL Technical Report
• Qwen2.5-VL Technical Report
• TimeMarker: A Versatile Video-LLM for Long and Short Video Understanding with Superior Temporal Localization Ability
• Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling
• InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks
• CogVLM2: Visual Language Models for Image and Video Understanding
• GPT-4o System Card
• VideoChat-Flash: Hierarchical Compression for Long-Context Video Modeling
• MR. Video: "MapReduce" is the Principle for Long Video Understanding
• Gemini: A Family of Highly Capable Multimodal Models
• Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities
• Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution
• LVBench: An Extreme Long Video Understanding Benchmark
• ReTaKe: Reducing Temporal and Knowledge Redundancy for Long Video Understanding
• InternVideo2.5: Empowering Video MLLMs with Long and Rich Context Modeling
• Training Long-Context Vision-Language Models Effectively with Generalization Beyond 128K Context
• Video2GUI: Synthesizing Large-Scale Interaction Trajectories for Generalized GUI Agent Pretraining
• Towards Multi-Agent Reasoning Systems for Collaborative Expertise Delegation: An Exploratory Design Study
• The Cognitive Bandwidth Bottleneck: Shifting Long-Horizon Agent from Planning with Actions to Planning with Schemas
• VCA: Video Curious Agent 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