Related papers: Hierarchical Fine-grained Preference Optimization …
Recent advances in text-to-video (T2V) generation have achieved good visual quality, yet synthesizing videos that faithfully follow physical laws remains an open challenge. Existing methods mainly based on graphics or prompt extension…
Video generation techniques have achieved remarkable advancements in visual quality, yet faithfully reproducing real-world physics remains elusive. Preference-based model post-training may improve physical consistency, but requires costly…
Recent advances in text-to-video generation have achieved impressive perceptual quality, yet generated content often violates fundamental principles of physical plausibility - manifesting as implausible object dynamics, incoherent…
Modern video diffusion models excel at appearance synthesis but still struggle with physical consistency: objects drift, collisions lack realistic rebound, and material responses seldom match their underlying properties. We present PhyCo, a…
Video generative models have recently achieved notable advancements in synthesis quality. However, generating complex motions remains a critical challenge, as existing models often struggle to produce natural, smooth, and contextually…
Fine-grained video captioning aims to generate detailed, temporally coherent descriptions of video content. However, existing methods struggle to capture subtle video dynamics and rich detailed information. In this paper, we leverage…
Aligning text-to-video diffusion models with human preferences is crucial for generating high-quality videos. Existing Direct Preference Otimization (DPO) methods rely on multi-sample ranking and task-specific critic models, which is…
Large Video Models (LVMs) built upon Large Language Models (LLMs) have shown promise in video understanding but often suffer from misalignment with human intuition and video hallucination issues. To address these challenges, we introduce…
While large-scale video diffusion models have demonstrated impressive capabilities in generating high-resolution and semantically rich content, a significant gap remains between their pretraining performance and real-world deployment…
Efficiently aligning large-scale video diffusion models with human intent requires a scalable and trajectory-aware pathway that bridges the inherent discrepancy between training noise distributions and practical inference trajectories.…
Text-to-video (T2V) generation has achieved remarkable progress in producing high-quality videos aligned with textual prompts. However, aligning synthesized videos with nuanced human preference remains challenging due to the subjective and…
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…
Recent advances in video generation have shown remarkable potential for constructing world simulators. However, current models still struggle to produce physically consistent results, particularly when handling large-scale or complex…
Generating highly dynamic and photorealistic portrait animations driven by audio and skeletal motion remains challenging due to the need for precise lip synchronization, natural facial expressions, and high-fidelity body motion dynamics. We…
Recent progress in video generation has led to substantial improvements in visual fidelity, yet ensuring physically consistent motion remains a fundamental challenge. Intuitively, this limitation can be attributed to the fact that…
Direct Preference Optimization (DPO) has recently been applied as a post-training technique for text-to-video diffusion models. To obtain training data, annotators are asked to provide preferences between two videos generated from…
With the rapid development of AIGC technology, significant progress has been made in diffusion model-based technologies for text-to-image (T2I) and text-to-video (T2V). In recent years, a few studies have introduced the strategy of Direct…
While recent video generation models have achieved significant visual fidelity, they often suffer from the lack of explicit physical controllability and plausibility. To address this, some recent studies attempted to guide the video…
Reinforcement learning (RL) has become a powerful tool for post-training visual generative models, with Group Relative Policy Optimization (GRPO) increasingly used to align generators with human preferences. However, existing GRPO pipelines…
Video generation has achieved significant advances through rectified flow techniques, but issues like unsmooth motion and misalignment between videos and prompts persist. In this work, we develop a systematic pipeline that harnesses human…