Hugging Face Trending Papers October 13, 2026

FlowCred: Hierarchical Credit Assignment and Functional Coordination for Joint Text-to-Video Post-Training

Read the original on Hugging Face Trending Papers →

FlowCred is a two-level framework designed to jointly post-train text-to-video models by separating prompt-level credit from generator residuals and coordinating prompt optimization with generator updates. It uses hierarchical credit assignment with matched prompt-seed rollout grids and functional coordination that probes alternative prompts during actual generation trajectories. Across multiple benchmarks, FlowCred consistently outperforms joint-training baselines, improving performance on T2V-CompBench and StoryEval without increasing decoding or reward-model call budgets.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at Hugging Face Trending Papers.

arXiv Computer Vision

2d ago

Generator-Aligned Reward Modeling with Target-Aware Bounded Optimization for Visual Generation

The paper introduces a post‑training framework for visual generative models that enhances specific attributes while preserving overall quality. It combines Generator‑Aligned Reward Modeling (GARM) to align reward signals with the generator’s distribution and reduce content confounding, with Target‑Aware Bounded Optimization (TABO) that caps reward values using real target examples. The authors also present TA‑GRPO, a flow‑based video optimization variant that further improves attribute enhancement and mitigates unintended attribute leakage.

By Ziqiao Weng, Yuanzhi Liang, Haibing Huang, Weidong Cai, Xuelong Li

reinforcement-learning

arXiv Computer Vision

Sep 7

Learning to Credit the Right Steps: Objective-aware Process Optimization for Visual Generation

The paper introduces Objective-aware Trajectory Credit Assignment (OTCA), a framework that refines reinforcement learning for diffusion-based visual generation. OTCA decomposes credit across denoising steps and allocates multiple reward signals adaptively, addressing the coarse, uniform reward assignment of existing GRPO pipelines. Experiments demonstrate that OTCA consistently enhances image and video generation quality across various metrics.

By Rui Li, Ke Hao, Yuanzhi Liang, Haibin Huang, Chi Zhang, Yun Gu, Xuelong Li

diffusion reinforcement-learning safety

arXiv Computer Vision

Sep 1

NoisEasier: Test-Time Noise Optimization for Text-to-Video Generation

arXiv:2608.30194v1 Announce Type: new Abstract: Diffusion models have recently advanced text-to-video (T2V) generation, yet they still struggle with fine-grained compositional alignment, such as attr...

By Yujiang Pu, Yu Kong

diffusion fine-tuning safety

arXiv Computer Vision

Oct 2

Token-Level Video Reinforcement Learning

arXiv:2610.01973v1 Announce Type: new Abstract: Reinforcement learning (RL) for video generation usually assigns one scalar reward to an entire sampled video. Yet a video is not uniformly flawed: som...

By Yifan Wang, Gordon Guocheng Qian, Yanyu Li, Anil Kag, Yun Fu

llms diffusion reinforcement-learning multimodal

arXiv Computer Vision

Oct 5

OuroReward: Sequential Reward Scheduling for Reinforcement Learning in Text-to-3D Generation

arXiv:2610.03423v1 Announce Type: new Abstract: Reinforcement learning (RL) for Text-to-3D (T23D) generation requires optimization across multiple quality dimensions such as semantic alignment and te...

By Bingyang Cui, Yujie Zhang, Yiling Xu, Yunfeng Guan

reinforcement-learning safety

arXiv AI

Oct 15

REEL: Learning to Retrieve, Evaluate, and Evolve Visual Memory for Any Long-Horizon Multi-Shot Video Generation

arXiv:2610.16632v1 Announce Type: cross Abstract: Memory-based long-video generation aims to combine user control with long-range visual consistency. We organize this process into three functional co...

By Hang Xu, Guohui Zhang, Xiaoxiao Ma, Hu Yu, Jie Huang, Jiayin Xiao, Lin Song, Haoyang Huang, Nan Duan, Feng Zhao

agents diffusion reinforcement-learning fine-tuning

One email a morning, machine-written

Related stories

Generator-Aligned Reward Modeling with Target-Aware Bounded Optimization for Visual Generation

Learning to Credit the Right Steps: Objective-aware Process Optimization for Visual Generation

NoisEasier: Test-Time Noise Optimization for Text-to-Video Generation

Token-Level Video Reinforcement Learning

OuroReward: Sequential Reward Scheduling for Reinforcement Learning in Text-to-3D Generation

REEL: Learning to Retrieve, Evaluate, and Evolve Visual Memory for Any Long-Horizon Multi-Shot Video Generation