REVIEW 12 cited by
VideoDPO: Omni-Preference Alignment for Video Diffusion Generation
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
Recent progress in generative diffusion models has greatly advanced text-to-video generation. While text-to-video models trained on large-scale, diverse datasets can produce varied outputs, these generations often deviate from user preferences, highlighting the need for preference alignment on pre-trained models. Although Direct Preference Optimization (DPO) has demonstrated significant improvements in language and image generation, we pioneer its adaptation to video diffusion models and propose a VideoDPO pipeline by making several key adjustments. Unlike previous image alignment methods that focus solely on either (i) visual quality or (ii) semantic alignment between text and videos, we comprehensively consider both dimensions and construct a preference score accordingly, which we term the OmniScore. We design a pipeline to automatically collect preference pair data based on the proposed OmniScore and discover that re-weighting these pairs based on the score significantly impacts overall preference alignment. Our experiments demonstrate substantial improvements in both visual quality and semantic alignment, ensuring that no preference aspect is neglected. Code and data will be shared at https://videodpo.github.io/.
Forward citations
Cited by 12 Pith papers
-
VideoCoCo: Code-as-CoT for Physically-Consistent Video Generation via an Agentic Dual-Engine System
Using executable Blender code as an intermediate simulation draft improves physical consistency in text-to-video generation, lifting OmniWeaving from 0.475 to 0.558 on PhyGenBench and from 52.18% to 77.88% on VBench-2.0.
-
Fake it till You Make it: Reward Modeling as Discriminative Prediction
GAN-RM trains a CLIP-based discriminator to distinguish a few hundred preference proxy images from model outputs, then uses it for Best-of-N selection, SFT, and DPO.
-
Scaling Image and Video Generation via Test-Time Evolutionary Search
Evolutionary search over denoising trajectories improves image and video generation quality and diversity as test-time compute increases, without retraining the generative model.
-
ExeSQL: Self-Taught Text-to-SQL Models with Execution-Driven Bootstrapping for SQL Dialects
Execution-driven bootstrapping, where a model generates SQL, executes it, and keeps only queries that run, lets a 7B model outperform GPT-4o on PostgreSQL, MySQL, and Oracle text-to-SQL benchmarks.
-
Investigating and Enhancing the Robustness of Large Multimodal Models Against Temporal Inconsistency
Large multimodal models are shown to rely on prior knowledge and text cues rather than video order under temporal inconsistency, and a benchmark plus preference-optimization method partially correct this.
-
A Survey on Evaluating Quality and Trustworthiness in LLM-Generated Data
A metric-oriented survey that classifies intrinsic quality and trustworthiness metrics for LLM-generated data across six modalities and documents systematic evaluation gaps in the current literature.
-
From Black Box to Transparency: Enhancing Automated Interpreting Assessment with Explainable AI in College Classrooms
An explainable model using BLEURT, CometKiwi, pause features, and Chinese phraseological diversity predicts human-rated quality dimensions in English-Chinese consecutive interpreting, with SHAP identifying the stronge...
-
GigaVideo-1: Advancing Video Generation via Automatic Feedback with 4 GPU-Hours Fine-Tuning
GigaVideo-1 fine-tunes Wan2.1 on synthetic weakness-targeted prompts with VLM reward reweighting and reports ~4% average VBench-2.0 gains per dimension at 4 GPU-hours each, though joint training gains less.
-
AlignHuman: Improving Motion and Fidelity via Timestep-Segment Preference Optimization for Audio-Driven Human Animation
Timestep-segment preference optimization with separate motion and fidelity LoRAs improves audio-driven human animation quality and allows a 3.3x inference speedup.
-
$I^2G$: Generating Instructional Illustrations via Text-Conditioned Diffusion
A pairwise-conditioned diffusion model generates instructional illustrations from procedural text and is finetuned with a text-image alignment reward.
-
Hierarchical Fine-grained Preference Optimization for Physically Plausible Video Generation
A hierarchical direct preference optimization with four alignment levels plus automated data selection improves physical plausibility of text-to-video models.
-
Robust Single-Stage Fully Sparse 3D Object Detection via Detachable Latent Diffusion
The submitted manuscript's abstract and full text are mismatched; the claimed 3D detection method is not present in the body.
Discussion (0). Sign in to comment.