相关论文: McSc: Motion-Corrective Preference Alignment for V…

Streaming autoregressive (AR) video generators combined with few-step distillation achieve low-latency, high-quality synthesis, yet remain difficult to align via reinforcement learning from human feedback (RLHF). Existing SDE-based GRPO…

Precisely evaluating semantic alignment between text prompts and generated videos remains a challenge in Text-to-Video (T2V) Generation. Existing text-to-video alignment metrics like CLIPScore only generate coarse-grained scores without…

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…

Despite notable advancements in Multimodal Large Language Models (MLLMs), most state-of-the-art models have not undergone thorough alignment with human preferences. This gap exists because current alignment research has primarily achieved…

Multimodal large language models (MLLMs) have shown remarkable capabilities, yet their performance is often capped by the coarse nature of existing alignment techniques. A critical bottleneck remains the lack of effective reward models…

Reward modeling is a key step in building safe foundation models when applying reinforcement learning from human feedback (RLHF) to align Large Language Models (LLMs). However, reward modeling based on the Bradley-Terry (BT) model assumes a…

Text-to-video (T2V) synthesis has advanced rapidly, yet current evaluation metrics primarily capture visual quality and temporal consistency, offering limited insight into how synthetic videos perform in downstream tasks such as…

A key challenge in music generation models is their lack of direct alignment with human preferences, as music evaluation is inherently subjective and varies widely across individuals. We introduce MR-FlowDPO, a novel approach that enhances…

Recent advances in human preference alignment have significantly improved multimodal generation and understanding. A key approach is to train reward models that provide supervision signals for preference optimization. However, existing…

Text-to-video (T2V) generation aims to synthesize videos with high visual quality and temporal consistency that are semantically aligned with input text. Reward-based post-training has emerged as a promising direction to improve the quality…

Users often possess a clear visual intent but struggle to articulate it precisely in language. This intention-expression gap makes aligning generated images with latent visual preferences a fundamental challenge in text-to-image diffusion…

Human motion generation is a critical task with a wide range of applications. Achieving high realism in generated motions requires naturalness, smoothness, and plausibility. Despite rapid advancements in the field, current generation…

Video generation has advanced rapidly, improving evaluation methods, yet assessing video's motion remains a major challenge. Specifically, there are two key issues: 1) current motion metrics do not fully align with human perceptions; 2) the…

Human motion generation is essential for fields such as animation, robotics, and virtual reality, requiring models that effectively capture motion dynamics from text descriptions. Existing approaches often rely on Contrastive Language-Image…

This paper focuses on self-supervised video representation learning. Most existing approaches follow the contrastive learning pipeline to construct positive and negative pairs by sampling different clips. However, this formulation tends to…

Aligning language models with human preferences through reinforcement learning from human feedback is crucial for their safe and effective deployment. The human preference is typically represented through comparison where one response is…

Large vision-language models (LVLMs) often fail to align with human preferences, leading to issues like generating misleading content without proper visual context (also known as hallucination). A promising solution to this problem is using…

Contrastive Learning (CL) performances as a rising approach to address the challenge of sparse and noisy recommendation data. Although having achieved promising results, most existing CL methods only perform either hand-crafted data or…

Test-time scaling has proven effective in further enhancing the performance of pretrained Large Language Models (LLMs). However, mainstream post-training methods (i.e., reinforcement learning (RL) with chain-of-thought (CoT) reasoning)…

Conventional video compression (VC) methods are based on motion compensated transform coding, and the steps of motion estimation, mode and quantization parameter selection, and entropy coding are optimized individually due to the…