The paper compares diffusion and rectified flow objectives within the MotionGPT3 framework for text-driven motion generation. Experiments on HumanML3D show that rectified flow converges faster, achieves strong test performance earlier, and matches or exceeds diffusion quality while requiring fewer sampling steps. The study isolates the generative objective’s impact, demonstrating that rectified flow’s benefits transfer to continuous-latent motion generation.
By Jaymin Bhan, JiHong Jeon, SangYeop Jeong
Recent advances in generative video modeling have enabled diverse generation, reference-based synthesis, extension, and editing, but existing approaches often rely on fragmented task-specific models. A general model must distinguish heterogeneous target, source, and reference signals to determine what to generate, preserve, or use as guidance, while reducing interference among tasks.
arXiv:2604.09057v3 Announce Type: replace
Abstract: Audio-video (AV) generation has recently made strong progress in perceptual quality and multimodal coherence, yet generating content with plausible...
By Junchao Liao, Zhenghao Zhang, Xiangyu Meng, Litao Li, Ziying Zhang, Siyu Zhu, Long Qin, Weizhi Wang
arXiv:2608.24334v1 Announce Type: new
Abstract: Discrete motion representations have substantially advanced autoregressive text-to-motion generation. However, most motion tokenizers are optimized for...
By Tianlv Huang, Hetian Guo, Ziyi Cai, Song Wang, Yanping Zhang, Zipei Fan, Xuan Song, Guangming Wu, Xin Zheng
arXiv:2609.08032v1 Announce Type: cross
Abstract: We introduce FlexMoGen, a novel framework for flexible human motion synthesis conditioned on both natural language descriptions and motion style refe...
By Kai Weixian Lan, Bodie Criswell, Briana Fedkiw, Zhan Zhang, Joseph Teran, Daniel Holden
arXiv:2605. 29488v2 Announce Type: replace-cross Abstract: Conditional human motion generation remains a fundamental challenge in computer vision and robotics.
By Yiheng Li, Zhuo Li, Ruibing Hou, Yingjie Chen, Hong Chang, Hao Liu, Shiguang Shan
Instruction-driven editing of 3D human motion requires precise spatiotemporal localization, rich semantic grounding, and strict preservation of unmodified content. Existing methods either resort to training-free adaptation of generative models or rely solely on triplet supervision; however, adaptation often yields suboptimal control, and manually curated triplet datasets remain severely limited in scale and semantic diversity.
Understanding dynamic sound sources requires jointly determining what produces a sound, where the source is located, and how it moves over time. Yet existing audio-language models often represent clips as global acoustic events, while vision-language models lack the spatial audio cues needed to localize and track individual sources.
InteractGesture is a model‑agnostic, inference‑time method that enables fine‑grained spatial control of individual joints in continuous streaming co‑speech gesture generation. It guides diffusion sampler latent estimates through a differentiable RVQ‑VAE decoder, backpropagating spatial control gradients to adjust motion latents during sampling. To address chunk‑wise dependency issues in streaming generation, the method introduces Progressive Chunk Guidance, a chunk‑window strategy that keeps an active set of editable chunk latents with staggered delays, allowing spatial constraints to propagate gradients backward across chunk boundaries and reducing boundary inconsistencies.
By Ekkasit Pinyoanuntapong, Ajinkya Deogade, Paul Streli, Wenjing Zhang, Joanna Materzynska, Pu Wang, Vittorio Ferrari, Jie Shen
Diffusion-based text-to-motion models synthesize realistic human motions but often exhibit semantic drift from the input text. Motion is inherently temporal, especially in compositional and long-duration sequences that require semantic consistency across multiple action segments and smooth kinematic transitions throughout the trajectory.
Uni-HOI is a unified framework that learns the joint distribution among text, human motion, and object motion for 4D human‑object interaction (HOI). It uses large language models and two motion‑specific VQ‑VAEs to convert heterogeneous motion data into token sequences, enabling seamless integration of all three modalities. A two‑stage training strategy first captures correlations on a large‑scale HOI dataset and then fine‑tunes for specific tasks, achieving strong performance on text‑driven HOI generation, object‑motion‑driven human motion generation, and human‑motion‑driven object motion prediction.
By Mengfei Zhang, Jinlu Zhang, Zhigang Tu
arXiv:2608.23189v1 Announce Type: new
Abstract: We present EchoWM, an omnimodal world model for enterable generative media that responds to continuous navigation while jointly generating 720p video,...
By Songchun Zhang, Yaowei Li, Junhao Zhuang, Weiyang Jin, Haoyu Wang, Xin Lu, Yilang Sun, Shiyi Zhang, Haoran Li, Xiaoxiao Ma, Yuming Li, Yijun Liu, Yaofeng Su, Yanwen Ma, Haoyu Wu, Zihan Su, Yue Ma, Lvmin Zhang, Haoyang Huang, Zeyue Xue, Anyi Rao, Nan Duan