The paper studies classifier‑free guidance (CFG) in Flow Matching, showing that strong guidance can distort the generated distribution by shifting the mean and concentrating trajectories. By interpreting Flow Matching as a time‑varying gradient flow, the authors explain how CFG reshapes the underlying potential and propose a training‑free method, Posterior‑Mean‑Capped CFG (PMC‑CFG), that adaptively limits guidance to the strongest feasible level. Experiments on synthetic and large‑scale image‑generation tasks demonstrate that PMC‑CFG reduces distortion and concentration while improving the alignment–diversity trade‑off, especially when nominal guidance is large.
By Jishen Peng, Zheng Ma
arXiv:2602. 20360v2 Announce Type: replace Abstract: Flow-based generative methods offer a simple and effective framework for high-fidelity generation, yet pretrained flow models are rarely used in their vanilla conditional form: in image generation, samples without guidance often appear diffuse and lack fine-grained detail.
By Runlong Liao, Jian Yu, Baiyu Su, Chi Zhang, Lizhang Chen, Qiang Liu
The paper introduces Global Transport (GT), a class‑agnostic optimal‑transport coupling that can be computed without class labels. GT associates different conditions with distinct regions of the source noise, which degrades performance when used without guidance but consistently improves generation when combined with classifier‑free guidance across various domains, model scales, and sampling budgets. The authors argue that coupling design should be evaluated under guided flow conditions rather than unguided generation, and demonstrate GT’s benefits on both discrete class‑conditioned and continuous text‑conditioned image generation.
By Katarina Petrovi\'c, Zander W. Blasingame, Danyal Rehman, \.Ismail \.Ilkan Ceylan, Michael Bronstein, Stephen Y. Zhang, Lazar Atanackovic, Alexander Tong
arXiv:2610.20604v1 Announce Type: new
Abstract: World-action models aim to turn visual anticipation into driving decisions, yet typically train action experts on trajectory representations defined in...
By Ao Liang, Youquan Liu, Mingxiao Li, Wei Chow, Lingdong Kong, Yue Liao, Dongyue Lu, Yu Yang, Wei Yin, Runnan Chen
arXiv:2609.33167v2 Announce Type: replace
Abstract: We present FloodDiffusion 2 (FD2), an efficient and controllable framework that builds upon FloodDiffusion (FD1), a state-of-the-art streaming moti...
By Yiyi Cai, Yuhan Wu, Kunhang Li, Tu Fangyuan, Xiangyue Zhang, Qiaoge Li, Zhixiang Wang, Kaipeng Zhang, Haiyang Liu
VideoAWR introduces a decoupled-timestep advantage‑weighted rectification framework for video flow models, separating guided rollouts from the optimization anchor to avoid geometric guidance blow‑up and cold‑start collapse. The method uses an EMA reference policy for guided rollouts while rectifying against an unguided conditional anchor, proving that the centered advantage cancels the anchor in expectation and retains only reward‑correlated covariance. Experiments on Wan2.1‑1.3B and 14B models show stable training and improved visual and motion quality in both CFG‑free and CFG‑enabled settings.
By Zheming Fu, Wenbin Ning, Ruizhe He, Wei Shang, Xiaoxiao Ma, Lianrui Mu, Chang Liu, Lei Wang, Siming Fu
arXiv:2608.29107v1 Announce Type: new
Abstract: While modern generative models excel at modeling complex data, precise inference-time control in conditional generation remains a critical challenge. C...
By Avishag Nevo, Tamir Hazan
LongLive‑Plug is a once‑for‑all distillation framework that learns reusable LoRA adapters on a base video diffusion model, enabling training‑free, plug‑and‑play deployment to a wide range of downstream models. These adapters provide single‑pass classifier‑free guidance, few‑step sampling, and long‑context error correction for autoregressive generation, and remain effective even when downstream models add conditioning branches or expand output channels. The authors demonstrate that the approach works on 54 downstream models across three backbone families and eight task categories, including world modeling, robotics, editing, and multimodal generation.
By Shuai Yang, Luozhou Wang, Wei Huang, ZhiFei Chen, Bohan Zhang, Xiao Fu, Qianli Ma, Chen-Hsuan Lin, Weian Mao, Bryan Chu, Song Han, Yukang Chen
arXiv:2608.29904v1 Announce Type: new
Abstract: Modern video generators routinely fail at physical dynamics: objects float, trajectories violate gravity, contacts vanish. Standard denoising and flow-...
By Hai Nguyen-Truong, Tuan-Anh Vu, Dang Huynh
arXiv:2608. 15284v1 Announce Type: cross Abstract: Navigation instruction generation from ego-centric RGB video in continuous environments is an important yet challenging task for human-robot interaction and scalable dataset construction.
By Haolin Yang, Yuxing Long, Zihan Yang, Hao Dong
MoCAR (Motion-code Coordinate-aware AutoRegression) is a decoder‑only framework that treats continuous trajectory forecasting as next‑code prediction in a coordinate‑aware latent space. It learns a continuous motion‑code space from endpoint‑normalized trajectory segments, using historical codes as a teacher‑forced prefix and generating future codes autoregressively while updating local scene context. The method achieves top‑tier performance on Argoverse benchmarks, transfers well from AV2 to AV1 in zero‑shot evaluation, and improves on turn‑heavy scenarios without requiring trajectory‑space re‑tokenization or proposal‑and‑refinement pipelines.
The paper introduces Latent-Centroid Steering (LCS), a single-pass classifier-free guidance method for vision‑language autonomous driving models. LCS replaces instance‑level residuals with class‑level latent shifts, projecting conditional representations toward precomputed command‑specific centroids to enhance command adherence. Experiments on Bench2Drive and nuScenes show that LCS cuts inference latency by about 50% while improving driving performance.
By Meibo Hu, Jiamian Wang, Pichao Wang, Zhiqiang Tao