Related papers: Improving Video Generation with Human Feedback
Recent studies have demonstrated the effectiveness of directly aligning diffusion models with human preferences using differentiable reward. However, they exhibit two primary challenges: (1) they rely on multistep denoising with gradient…
Recent flow matching models for text-to-image generation have achieved remarkable quality, yet their integration with reinforcement learning for human preference alignment remains suboptimal, hindering fine-grained reward-based…
We introduce RewardFlow, an inversion-free framework that steers pretrained diffusion and flow-matching models at inference time through multi-reward Langevin dynamics. RewardFlow unifies complementary differentiable rewards for semantic…
We introduce MotionRL, the first approach to utilize Multi-Reward Reinforcement Learning (RL) for optimizing text-to-motion generation tasks and aligning them with human preferences. Previous works focused on improving numerical performance…
Flow-based generative models have shown remarkable success in text-to-image generation, yet fine-tuning them with intermediate feedback remains challenging, especially for continuous-time flow matching models. Most existing approaches…
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…
Video generation models produce visually coherent content but struggle with tasks requiring spatial reasoning and multi-step planning. Reinforcement learning (RL) offers a path to improve generalization, but its effectiveness in video…
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…
Video diffusion models have made rapid progress in perceptual realism and temporal coherence, but they remain primarily optimized for plausible generation rather than verifiable reasoning. This limitation is especially pronounced in tasks…
Current mainstream methods of aligning diffusion models with human preferences typically employ VLM-based reward models. However, these reward models, pre-trained for semantic alignment, struggle to capture the essential perceptual…
Recent advancements in flow-matching have enabled high-quality text-to-image generation. However, the deterministic nature of flow-matching models makes them poorly suited for reinforcement learning, a key tool for improving image quality…
We have made significant progress towards building foundational video diffusion models. As these models are trained using large-scale unsupervised data, it has become crucial to adapt these models to specific downstream tasks. Adapting…
Generative speech enhancement offers a promising alternative to traditional discriminative methods by modeling the distribution of clean speech conditioned on noisy inputs. Post-training alignment via reinforcement learning (RL) effectively…
Text-to-video models have made remarkable advancements through optimization on high-quality text-video pairs, where the textual prompts play a pivotal role in determining quality of output videos. However, achieving the desired output often…
Camera-controlled video generation has achieved remarkable progress in recent years. However, existing video-to-video re-rendering methods primarily rely on Supervised Fine-Tuning using synthetic datasets. At present, there is an extreme…
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…
Recent advancements in multimodal reward models (RMs) have significantly propelled the development of visual generation. Existing frameworks typically adopt Bradley-Terry-style preference modeling or leverage generative VLMs as judges, and…
The correct specification of reward models is a well-known challenge in reinforcement learning. Hand-crafted reward functions often lead to inefficient or suboptimal policies and may not be aligned with user values. Reinforcement learning…
We present an approach to robot learning from egocentric human videos by modeling human preferences in a reward function and optimizing robot behavior to maximize this reward. Prior work on reward learning from human videos attempts to…
Aligning human preference and value is an important requirement for building contemporary foundation models and embodied AI. However, popular approaches such as reinforcement learning with human feedback (RLHF) break down the task into…