AI Paper Atlas

Research map / Video / Video generation

Diverse Video Generation with Determinantal Point Process-Guided Policy Optimization

Tahira Kazimi, Connor Dunlop, Pinar Yanardag

CVPR 2026 · Video › Video generation · approach: Efficient video diffusion models · 4 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add DPP-GRPO prompt policy to Wan2.1Wan2.1 · VBench prompts (Wan2.1)TCE: 19.76 -> 31.95Improved
add DPP-GRPO prompt policy to Wan2.1Wan2.1 · VBench prompts (Wan2.1)TIE: 39.7 -> 49.09Improved
add DPP-GRPO prompt policy to CogVideoXCogVideoX · VBench prompts (CogVideoX)TCE: 22.21 -> 27.59Improved
add DPP-GRPO prompt policy to CogVideoXCogVideoX · VBench prompts (CogVideoX)CLIP: 0.292 -> 0.310Improved
rewrite prompts with GPT-5 instead of original promptsWan2.1 · VBench prompts (Wan2.1)TCE: 19.76 -> 16.71Hurt
rewrite prompts with Prompt-A-VideoWan2.1 · VBench prompts (Wan2.1)TIE: 39.7 -> 24.10Hurt
add the DPP diversity term to the relevance-only reward (ablation)DPP-GRPO · VBench prompts (Wan2.1, reward ablation)TCE: 20.06 -> 31.95Improved
add the relevance term to the DPP-only reward (ablation)DPP-GRPO · VBench prompts (Wan2.1, reward ablation)CLIP: 0.255 -> 0.311Improved
add the relevance term to the DPP-only reward (ablation)DPP-GRPO · VBench prompts (Wan2.1, reward ablation)TCE: 27.05 -> 31.95Improved
add GRPO training after supervised fine-tuning (ablation)DPP-GRPO · VBench prompts (Wan2.1, reward ablation)TCE: 14.05 -> 31.95Improved
increase reference set size from 5 to 10 (ablation)DPP-GRPO · Reference set size (supplement)TCE: 16.570 -> 15.546Hurt
raise diversity weight from 0.1 to 0.9 with relevance weight 0.9 to 0.1 (ablation)DPP-GRPO · Reward weight (supplement)CLIP: 0.305 -> 0.285Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy