Trendoday

VideoNexus: Video Perception Beyond the Reasoning Context

Understanding long videos requires locating evidence, resolving visual details, and integrating observations into an answer. Even when relevant evidence is present, performing these operations within

  • Upvotes16
–Rank now
#4Peak rank
2Days on list
244Score · 7d
Nov 18, 2026First seen
Rank · 7 days

About this paper

VideoNexus separates detailed video perception from evidence-driven planning and reasoning, using perception sub-agents to return compact temporally grounded evidence and achieving higher accuracy at lower cost on long-video benchmarks.

Understanding long videos requires locating evidence, resolving visual details, and integrating observations into an answer. Even when relevant evidence is present, performing these operations within long, dense visual sequences burdens both perception and reasoning. Video agents enable selective inspection, but returning frames to the planner still accumulates visual information in its reasoning context. Delegating perception reduces this burden, yet sparse sampling can miss decisive details, and per-frame descriptions can preserve context growth. We introduce VideoNexus, a training-free framework that separates detailed video perception from evidence-driven planning and reasoning. The…

training-free frameworkvideo agentsplannerperception sub-agentsnative audio-videoindependent contextstemporally grounded evidenceiterative search and verificationstatic ingestionbuilt-in agentic processing
Upvotes
16
Authors
7
Published
Nov 16, 2026

Summary and abstract excerpt via Hugging Face Papers ↗ · arXiv.

Trending history

VideoNexus: Video Perception Beyond the Reasoning Context was first seen on Hugging Face · Daily papers on Nov 18, 2026. Since then it has appeared in 12 checks on 2 different days. Its best position was #4 of 30, reached on Nov 19, 07:29 UTC. It dropped off the list after Nov 19, 07:29 UTC.

Rank history

Position on Hugging Face · Daily papers at every check (lower is better).

#1#11#20#30 09:2814:5820:2901:5907:29 Nov 18, 09:28 UTC · #14Nov 18, 11:28 UTC · #14Nov 18, 13:28 UTC · #14Nov 18, 15:28 UTC · #13Nov 18, 17:28 UTC · #13Nov 18, 19:28 UTC · #13Nov 18, 21:28 UTC · #12Nov 18, 23:28 UTC · #12Nov 19, 01:28 UTC · #12Nov 19, 03:28 UTC · #12Nov 19, 05:28 UTC · #7Nov 19, 07:29 UTC · #4

Last 14 days

Best rank per day (UTC).

Nov 9today

Metric history

Platform metric as reported by Hugging Face.

071320 09:2814:5820:2901:5907:29 Nov 18, 09:28 UTC · 16Nov 18, 11:28 UTC · 18Nov 18, 13:28 UTC · 17Nov 18, 15:28 UTC · 17Nov 18, 17:28 UTC · 18Nov 18, 19:28 UTC · 18Nov 18, 21:28 UTC · 19Nov 18, 23:28 UTC · 19Nov 19, 01:28 UTC · 19Nov 19, 03:28 UTC · 20Nov 19, 05:28 UTC · 20Nov 19, 07:29 UTC · 20

Questions

Is VideoNexus: Video Perception Beyond the Reasoning Context trending on HF Daily Papers right now?

Not at the moment. It was last on the list on Nov 19, 07:29 UTC, after 2 days of trending.

What is the highest rank VideoNexus: Video Perception Beyond the Reasoning Context reached?

#4 on Hugging Face · Daily papers, on Nov 19, 07:29 UTC. Trendoday checks this list every 120 minutes.

How long has VideoNexus: Video Perception Beyond the Reasoning Context been trending?

It was first seen on Nov 18, 2026 and has been on the list on 2 days (12 checks) since.