Related papers: A Systematic Post-Train Framework for Video Genera…

Reinforcement fine-tuning (RFT) has shown great promise in achieving humanlevel reasoning capabilities of Large Language Models (LLMs), and has recently been extended to MLLMs. Nevertheless, reasoning about videos, which is a fundamental…

Text-to-video generation aims to produce a video based on a given prompt. Recently, several commercial video models have been able to generate plausible videos with minimal noise, excellent details, and high aesthetic scores. However, these…

Online reinforcement learning is becoming increasingly important for aligning diffusion models with non-differentiable objectives. However, existing methods still face limitations in assigning fine-grained credit along denoising…

Scaling video generation from seconds to minutes faces a critical bottleneck: while short-video data is abundant and high-fidelity, coherent long-form data is scarce and limited to narrow domains. To address this, we propose a training…

Recent advancements in diffusion models (DMs) have been propelled by alignment methods that post-train models to better conform to human preferences. However, these approaches typically require computation-intensive training of a base model…

The post-training pipeline for diffusion models currently has two stages: supervised fine-tuning (SFT) on curated data and reinforcement learning (RL) with reward models. A fundamental gap separates them. SFT optimizes the denoiser only on…

Pre-trained Large Language Model (LLM) exhibits broad capabilities, yet, for specific tasks or domains their attainment of higher accuracy and more reliable reasoning generally depends on post-training through Supervised Fine-Tuning (SFT)…

Diffusion models have emerged as the de facto paradigm for video generation. However, their reliance on web-scale data of varied quality often yields results that are visually unappealing and misaligned with the textual prompts. To tackle…

Large language models are classically trained in stages: pretraining on raw text followed by post-training for instruction following and reasoning. However, this separation creates a fundamental limitation: many desirable behaviors such as…

Reinforcement learning, particularly Group Relative Policy Optimization (GRPO), has emerged as an effective framework for post-training visual generative models with human preference signals. However, its effectiveness is fundamentally…

Post-training Large Vision-and-Language Models (LVLMs) typically involves Supervised Fine-Tuning (SFT) for knowledge injection or Reinforcement Learning with Verifiable Rewards (RLVR) for performance enhancement. However, SFT often leads to…

Generating videos predicting the future of a given sequence has been an area of active research in recent years. However, an essential problem remains unsolved: most of the methods require large computational cost and memory usage for…

Recent advances in Multimodal Large Language Models (MLLMs) have spurred significant progress in Chain-of-Thought (CoT) reasoning. Building on the success of Deepseek-R1, researchers extended multimodal reasoning to post-training paradigms…

Foundation models trained on web-scale data have revolutionized robotics, but their application to low-level control remains largely limited to behavioral cloning. Drawing inspiration from the success of the reinforcement learning stage in…

Recent advances in text-to-image (T2I) diffusion models have enabled impressive image generation capabilities guided by text prompts. However, extending these techniques to video generation remains challenging, with existing text-to-video…

Video generation has made remarkable progress in recent years, especially since the advent of the video diffusion models. Many video generation models can produce plausible synthetic videos, e.g., Stable Video Diffusion (SVD). However, most…

In an era where visual content generation is increasingly driven by machine learning, the integration of human feedback into generative models presents significant opportunities for enhancing user experience and output quality. This study…

Post training via GRPO has demonstrated remarkable effectiveness in improving the generation quality of flow-matching models. However, GRPO suffers from inherently low sample efficiency due to its on-policy training paradigm. To address…

Supervised Fine-Tuning (SFT) and Reinforcement Learning (RL) dominate the post-training landscape for mathematical reasoning, yet differ fundamentally in their reliance on expert trajectories. To understand the optimal way to harness these…

Human video generation remains challenging due to the difficulty of jointly modeling human appearance, motion, and camera viewpoint under limited multi-view data. Existing methods often address these factors separately, resulting in limited…