arXiv Computer Vision
VidHarness: Evolving Agent Harnesses for Cost-Efficient Long Video Understanding
Read the original on arXiv Computer Vision →The Flow has not summarised this story yet — read it at arXiv Computer Vision.
Related stories
Hugging Face Trending Papers
Aug 5
MetaVideoAgent: Automated Video-Agent Evolution for Long-Form Video Understanding
Long-form video understanding requires locating sparse, question-relevant evidence in long, multimodal videos. Real-world video distributions differ in modality-specific information density, content structure, and evidence patterns, causing fixed video-agent designs to incur redundant processing or fail when mismatched.
arXiv AI
2d ago
Video-RSI: Recursive Self-Improvement of Video Understanding Agents via Harness Evolution
arXiv:2609.37950v1 Announce Type: new Abstract: Video understanding agents acquire evidence through an executable harness that controls what they observe and how they use those observations. However,...
arXiv Computer Vision
Sep 14
Online Video Agent Harness for Long Video Understanding
arXiv:2609.12818v1 Announce Type: new Abstract: Long video understanding often behaves like a visual needle-in-a-haystack problem: query-relevant evidence is sparsely distributed across long temporal...
arXiv AI
Aug 17
MedClaw: Heuristic Agent Harness for Long-Horizon Surgical Video Reasoning
arXiv:2608. 14015v1 Announce Type: cross Abstract: Understanding tens-of-minutes surgical videos requires long-horizon temporal reasoning, answering what happens before, after, or across stages of a procedure by grounding the question in visual evidence spread across time.
arXiv AI
Aug 26
VideoHarness-RSI: Recursive Harness Self-Improvement for Long-Video Understanding with Frozen Vision-Language Models
VideoHarness‑RSI explores how improving the executable context‑construction program alone can enhance long‑video understanding with frozen vision‑language models. By recursively searching for better harnesses—programs that select and structure video segments—using an outer‑loop proposer that learns from prior programs and execution traces, the method consistently outperforms weaker hand‑crafted baselines and further improves upon stronger ones. The resulting harnesses transfer to other long‑video benchmarks without additional search, demonstrating that executable context construction is a distinct, reusable optimization layer.
Hugging Face Trending Papers
Aug 12
Beyond Trial-and-Error: Agentic Optimization for Image-to-Video Adherence
Modern black-box Image-to-Video (I2V) models offer powerful capabilities in automated content creation, yet their lack of fine-grained control and reliability presents significant challenges in professional workflows. Their inherent stochasticity causes minor variations in textual prompts or hyperparameters to yield drastically different outputs often necessitating inefficient, brute-force trial-and-error processes.