arXiv:2609.22947v1 Announce Type: new Abstract: Reinforcement learning (RL) is vital for optimizing video generation models, with a robust reward model (RM) serving as the cornerstone. However, exist...
Reinforcement learning (RL) is vital for optimizing video generation models, with a robust reward model (RM) serving as the cornerstone. However, existing video reward models often produce unstable sc...
arXiv:2608. 18607v2 Announce Type: replace Abstract: Using reinforcement learning to post-train joint video-audio generation models requires a reward signal.
arXiv:2610.32222v1 Announce Type: new Abstract: Reinforcement learning has gained attention for improving action-conditioned world models (ACWMs), as it enables reward-driven optimization of visual q...
VGIQA is a new image quality assessment model that provides both local and global quality evaluations. It uses a two-stage training process—initial cold-start followed by reinforcement learning—with local quality reward functions. The model outperforms existing large multimodal language models on the newly introduced VGSR-2K dataset and improves performance on degradation perception tasks.
arXiv:2608.21425v1 Announce Type: cross Abstract: Video generation is central to AI-powered content creation. Aligning generated videos with human preferences is a key criterion for evaluating genera...
AI video generation has advanced rapidly and entered widespread commercial use. As a result, quality differences among videos produced by state-of-the-art AI video generation models~(AIVGMs) have become increasingly difficult to discern using conventional evaluation criteria, such as visual fidelity and semantic instruction following.
PreResQ‑R1 introduces a Preference‑Response Disentangled Reinforcement Learning framework for Visual Quality Assessment that jointly optimizes absolute score regression and relative ranking consistency. It employs a dual‑branch reward system—modeling intra‑sample response coherence and inter‑sample preference alignment—trained with Group Relative Policy Optimization. The method extends to video quality assessment via a global‑temporal and local‑spatial data flow strategy, achieving state‑of‑the‑art results on 10 IQA and 5 VQA benchmarks with only 6K images and 28K videos, and provides human‑aligned reasoning traces.
VGIQA is a new image quality assessment model that provides both local and global quality evaluations. It uses a two‑stage training process—starting with a cold‑start phase and then reinforcement learning guided by local quality reward functions. The model demonstrates superior performance on the newly introduced VGSR‑2K dataset, outperforming existing open‑source multi‑modal large language models such as Qwen2.5‑VL‑72B‑Instruct and Qwen3‑VL‑32B‑Instruct, and it also improves degradation perception tasks.
VGA‑BenchV2 is an expanded, human‑aligned benchmark and optimization framework that jointly evaluates video generation quality and aesthetic value. It builds on the original VGA‑Bench taxonomy, adding 52 sub‑dimensions and 1,016 curated prompts to generate over 60,000 videos from 12 mainstream models. The benchmark significantly enlarges human supervision with 36,000 task‑level annotations and introduces a hybrid evaluator (VAQA‑Net, VTag‑Net, VGQA‑Net) that aligns well with human judgments and can be used as a reward model for reinforcement‑learning fine‑tuning.
arXiv:2608. 09111v1 Announce Type: new Abstract: AI video generation has advanced rapidly and entered widespread commercial use.
WorldReward introduces a vision‑language model–based reward system for camera‑conditioned world models, combining action consistency and visual quality evaluation. It processes paired videos by splitting them into action‑aligned chunks, structuring visual evidence, and aggregating decisions through voting. The model is trained on a large, reasoning‑augmented preference dataset and outperforms GPT‑5.5 on a human‑annotated benchmark, improving both action execution and visual quality when applied to RL post‑training.