Related papers: PhyGDPO: Physics-Aware Groupwise Direct Preference…

Customized text-to-video generation aims to generate high-quality videos guided by text prompts and subject references. Current approaches for personalizing text-to-video generation suffer from tackling multiple subjects, which is a more…

Generating realistic human motion is a central yet unsolved challenge in video generation. While reinforcement learning (RL)-based post-training has driven recent gains in general video quality, extending it to human motion remains…

Video generative models have made remarkable progress, yet they often yield visual artifacts that violate grounding in physical dynamics. Recent works such as PhysGen3D tackle single image-to-3D physics through mesh reconstruction and…

Recent advancements in reinforcement learning, particularly through Group Relative Policy Optimization (GRPO), have significantly improved multimodal large language models for complex reasoning tasks. However, two critical limitations…

Recent text-to-video (T2V) generation methods have seen significant advancements. However, the majority of these works focus on producing short video clips of a single event (i.e., single-scene videos). Meanwhile, recent large language…

Cinematic camera control relies on a tight feedback loop between director and cinematographer, where camera motion and framing are continuously reviewed and refined. Recent generative camera systems can produce diverse, text-conditioned…

Direct Preference Optimization (DPO) is broadly utilized for aligning Large Language Models (LLMs) with human values because of its flexibility. Despite its effectiveness, it has been observed that the capability of DPO to generate…

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.…

We present LongVPO, a novel two-stage Direct Preference Optimization framework that enables short-context vision-language models to robustly understand ultra-long videos without any long-video annotations. In Stage 1, we synthesize…

Text-to-video generative models have made significant strides in recent years, producing high-quality videos that excel in both aesthetic appeal and accurate instruction following, and have become central to digital art creation and user…

Recent advances in video generation have enabled thrilling experiences in producing realistic videos driven by scalable diffusion transformers. However, they usually fail to produce satisfactory outputs that are aligned to users' authentic…

Large-scale video diffusion models achieve impressive visual quality, yet often fail to preserve geometric consistency. Prior approaches improve consistency either by augmenting the generator with additional modules or applying…

Group Relative Policy Optimization has emerged as essential for aligning video diffusion models with human preferences, but faces a critical computational bottleneck: training a 14B parametered model typically demands hundreds of GPU days…

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…

Recent advances in diffusion-based and autoregressive video generation models have achieved remarkable visual realism. However, these models typically lack accurate physical alignment, failing to replicate real-world dynamics in object…

Generative multimodal content is increasingly prevalent in much of the content creation arena, as it has the potential to allow artists and media personnel to create pre-production mockups by quickly bringing their ideas to life. The…

Direct Preference Optimization (DPO) aligns language models using pairwise preference comparisons, offering a simple and effective alternative to Reinforcement Learning (RL) from human feedback. However, in many practical settings, training…

Prompt design plays a crucial role in text-to-video (T2V) generation, yet user-provided prompts are often short, unstructured, and misaligned with training data, limiting the generative potential of diffusion-based T2V models. We present…

Image-to-video generation, which aims to generate a video starting from a given reference image, has drawn great attention. Existing methods try to extend pre-trained text-guided image diffusion models to image-guided video generation…

Visual generative models have achieved remarkable progress in synthesizing photorealistic images and videos, yet aligning their outputs with human preferences across critical dimensions remains a persistent challenge. Though reinforcement…