Video Evidence Indexing: Learning Where to Look from Video Previews for Token-Budgeted Long-Video Question Answering
cs.CV
Submitted: 2026-09-30
Updated: 2026-09-30
Terminology
Sources
- On-Policy Distillation of Language Models: Learning from Self-Generated Mistakes
- LLaVA-OneVision-2: Towards Next-Generation Perceptual Intelligence
- Qwen3-VL Technical Report
- Qwen2.5-VL Technical Report
- Scaling Video Understanding via Compact Latent Multi-Agent Collaboration
- One Ranking, Any Budget: Matryoshka Evidence-to-Context Frame Selection for Long-Video Understanding
- Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling
- Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities
- Unified Spatiotemporal Token Compression for Video-LLMs at Ultra-Low Retention
- GridProbe: Posterior-Probing for Adaptive Test-Time Compute in Long-Video VLMs
- Small Vision-Language Models are Smart Compressors for Long Video Understanding
- Video-MME: The First-Ever Comprehensive Evaluation Benchmark of Multi-modal LLMs in Video Analysis
- AdaCodec: A Predictive Visual Code for Video MLLMs
- Reinforcement Learning via Self-Distillation
- LLaVA-OneVision: Easy Visual Task Transfer
- When and Where to Look: Adaptive Visual Evidence Scheduling for Efficient Long Video Understanding
- NVILA: Efficient Frontier Visual Language Models
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