Video-Zero: Self-Evolution Video Understanding

• URL: http://arxiv.org/abs/2605.14733v1
• Date: Thu, 14 May 2026 11:56:14 GMT
• Title: Video-Zero: Self-Evolution Video Understanding
• Abstract summary: We argue that the key bottleneck of video self-evolution is not difficulty alone, but grounding.<n>We propose Video-Zero, an annotation-free Questioner-answerr co-evolution framework that centers self-evolution on temporally localized evidence.<n>Video-Zero consistently improves multiple video VLM backbones, demonstrating the effectiveness and transferability of evidence-centered self-evolution.
• Score: 54.992296368077085
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Self-evolution offers a promising path for improving reasoning models without relying on intensive human annotation. However, extending this paradigm to video understanding remains underexplored and challenging: videos are long, dynamic, and redundant, while the evidence needed for reasoning is often sparse and temporally localized. Naively generating difficult question-answer pairs from full videos can therefore produce supervision that appears challenging but is weakly grounded, relying on static cues or language priors rather than temporal evidence. In this work, we argue that the key bottleneck of video self-evolution is not difficulty alone, but grounding. We propose Video-Zero, an annotation-free Questioner--Solver co-evolution framework that centers self-evolution on temporally localized evidence. The Questioner discovers informative evidence segments and generates evidence-grounded questions, while the Solver learns to answer and align its predictions with the supporting evidence. This closes an iterative loop of evidence discovery, grounded supervision, and evidence-aligned learning. Across 13 benchmarks spanning temporal grounding, long-video understanding, and video reasoning, Video-Zero consistently improves multiple video VLM backbones, demonstrating the effectiveness and transferability of evidence-centered self-evolution.

Related papers

• Video-OPSD: Exploiting Privileged Visual Evidence for On-Policy Self-Distillation in Video Large Language Models [58.45264308304815]
  On-policy self-distillation (OPSD) has recently emerged as an effective post-training paradigm that improves policy optimization through dense token-level supervision from a privileged self-teacher.<n>We present $textbfVideo-OPSD$, an OPSD framework that exploits privileged visual evidence for both self-teacher construction and knowledge transfer.
  arXiv  Detail & Related papers  (2026-08-27T12:51:32Z)
• TimeThink: Reasoning with Time for Video LLMs [28.549802513886046]
  We propose TimeThink, a reinforcement learning framework that guides temporal evidence discovery in Video-LLMs.<n>Our key idea is to treat temporal clue steps as the fundamental optimization primitive of video reasoning.<n>To enable scalable training, we construct TimeThink-RFT-20K, a dataset with automatically derived temporal evidence segments.
  arXiv  Detail & Related papers  (2026-07-06T13:50:15Z)
• EvoVid: Temporal-Centric Self-Evolution for Video Large Language Models [44.97714162696323]
  Video Large Language Models (Video-LLMs) have demonstrated strong capabilities in video reasoning through reinforcement learning (RL)<n>We propose a temporal-centric self-evolving framework that enables Video-LLMs to improve directly from raw, unannotated videos.
  arXiv  Detail & Related papers  (2026-05-21T03:00:35Z)
• Towards Temporal Compositional Reasoning in Long-Form Sports Videos [5.5825182710791275]
  Chain-of-Time Reasoning (CoTR) treats reasoning as a process of temporally grounded evidence composition.<n>CoTR consistently improves temporal compositional reasoning and step-wise grounding quality over strong MLLM baselines.
  arXiv  Detail & Related papers  (2026-04-24T05:02:03Z)
• VideoZeroBench: Probing the Limits of Video MLLMs with Spatio-Temporal Evidence Verification [73.02304272829785]
  VideoBench is a hierarchical benchmark for long-video answering that rigorously verifies evidence.<n>It comprises 500 manually annotated questions across 13 domains, paired with temporal intervals and spatial bounding boxes as evidence.<n>Experiments show that even GeminiPro-3-Pro correctly answers fewer than 17% of questions under the standard end-to-end QA setting.<n>Results expose a significant gap between surface-level answer correctness and genuine evidence-based reasoning.
  arXiv  Detail & Related papers  (2026-04-02T03:29:43Z)
• VisionCoach: Reinforcing Grounded Video Reasoning via Visual-Perception Prompting [58.508924874097715]
  VisonCoach consists of two components: (1) Visual Prompt Selector, which predicts appropriate prompt types conditioned on the video and question, and (2) Spatio-Reasoner, optimized with RL under visual prompt guidance and object grounding rewards.<n>Our results show that visual prompting during training improves grounded video reasoning, while distract-distillationSense enables the model to this ability without requiring prompts at inference time.
  arXiv  Detail & Related papers  (2026-03-15T23:32:02Z)
• Think, Then Verify: A Hypothesis-Verification Multi-Agent Framework for Long Video Understanding [25.82963105515627]
  VideoHV-Agent is a framework that reformulates video question answering as a structured hypothesis-verification process.<n>We show that VideoHV-Agent achieves state-of-the-art accuracy while providing enhanced interpretability, improved logical soundness, and lower computational cost.
  arXiv  Detail & Related papers  (2026-03-05T09:16:07Z)
• Process-of-Thought Reasoning for Videos [33.74677144833003]
  Process-of-Thought (PoT) Reasoning for Videos is a framework that makes the reasoning process explicit by structuring video inference into a sequence of lightweight, verifiable steps.<n>PoT interleaves (i) temporal evidence selection, (ii) step-wise state updates, and (iii) constrained answer synthesis, enabling the model to progressively refine hypotheses while maintaining traceability to video evidence.
  arXiv  Detail & Related papers  (2026-02-07T20:25:46Z)
• Video-CoM: Interactive Video Reasoning via Chain of Manipulations [78.64256470920166]
  We introduce Interactive Video Reasoning, enabling models to "think with videos"<n>Our model, Video CoM, reasons through a Chain of Manipulations (CoM), performing iterative visual actions to gather and refine evidence.<n>Video CoM achieves strong results across nine video reasoning benchmarks, improving average performance by 3.6 percent over recent state of art models.
  arXiv  Detail & Related papers  (2025-11-28T18:59:57Z)
• When Thinking Drifts: Evidential Grounding for Robust Video Reasoning [68.75730050161219]
  Chain-of-Thought (CoT) mechanism has enhanced reasoning in text-based tasks.<n>CoT often degrades performance in video reasoning, generating verbose but misleading internal monologues.<n>Visual Evidence Reward (VER) is a reinforcement learning framework that explicitly rewards the generation of reasoning traces that are verifiably grounded in visual evidence.
  arXiv  Detail & Related papers  (2025-10-07T16:03:33Z)
• VITED: Video Temporal Evidence Distillation [49.38292490256531]
  We investigate complex video question answering via chain-of-evidence reasoning.<n>Models struggle with multi-step reasoning as they uniformly sample a fixed number of frames.<n>We propose a framework to enhance existing VideoQA datasets with evidence reasoning chains.
  arXiv  Detail & Related papers  (2025-03-17T06:30:02Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.