We present FlowAct-R2, a framework for interactive humanoid video generation that combines continuous multimodal control with proactive agent planning. Our method consists of two coupled components. First, a Streaming Multimodal Reference Diffusion Transformer adapts the pretrained Seedance 2.0 Mini reference-to-video backbone to accept rolling action prompts, streaming audio, and dynamically updated image, audio, and video references. Video-driven rotary positional embeddings align reference chunks with the generation timeline, while reference-plus-image conditioning and partially noised historical motion frames preserve appearance and avoid accumulated drift. Second, a Proactive Interaction Agent separates pre-online planning from online scheduling and response: it prepares a persona, a long-horizon agenda, and reusable multimodal skills in advance, then autonomously schedules behaviors, responds to audience input, and handles interruptions during a live session. FlowAct-R2 supports real-time 720p generation and hour-scale streaming across entertainment streaming, live shopping, video chatting, and live vlogging.
Figures & tables
Figure 1 : FlowAct-R2 couples proactive interaction with streaming multimodal reference generation. Our demonstrations cover entertainment streaming, live shopping, live vlogging, and video chatting.
Figure 2 : System overview. Offline planning organizes multimodal avatar assets into a persona, an agenda, and reusable skills. The online agent makes behavior and scheduling decisions using audience inputs and history. The resulting prompt, audio, and reference streams condition continuous video generation.
Figure 3 : Entertainment and live shopping results. (a) Selected poses and gestures during a dance performance. (b) A continuous presentation of one garment, including front-facing explanation, expressive gestures, and a rear-view demonstration. Each row contains eight full frames from one video in temporal order.
Figure 4 : Video chatting and live vlogging results. (a) Facial expressions and gestures during a conversation. (b) Viewpoint and scene changes during an outdoor vlog. Each row contains eight full frames in temporal order. Reference-image insets and audience text in the vlogging frames are retained from the source video.
Figure 5 : Behavior against Vidu-S1 during the same audience request and subsequent response. The first four columns show listening; the final four show speaking. FlowAct-R2 varies gaze, head pose, and facial response during listening, whereas Vidu-S1 maintains a nearly unchanged pose, smile, and hand gesture.
Figure 6 : Product-reference fidelity against Vidu-S2. Columns 1–3 follow successive product references in one paired shopping demonstration; column 4 shows a separate cylinder case. Reference images are copied from the source-video insets. Presenter crops expose differences in package graphics and shape.
Real-time embodied social interaction places two equally demanding requirements on an agent: continuously generating fluent multimodal interaction behavior, and proactively reasoning over accumulated dialogue and visual context to decide when to take initiative. These requirements must both be satisfied under a strict latency budget, making them difficult to meet simultaneously. We present ProAct, a dual-system framework that manages these time-critical requirements by integrating a low-latency Behavioral System for streaming multimodal interaction with a slower Cognitive System that performs long-horizon social reasoning and produces high-level proactive intentions. The Cognitive System incorporates an efficient memory mechanism and a user-motivation prediction module to reason over accumulated dialogue and visual context and determine when proactive intervention is appropriate. The Behavioral System further includes an intention-conditioned streaming flow-matching motion generator with a disentangled ControlNet branch, which translates deliberative intentions into continuous non-verbal behavior without disrupting interaction fluency. We deploy ProAct on a physical humanoid robot and validate the framework through comprehensive experiments, including real-world user studies, motion-generation benchmarks, and evaluation on ProActBench, a new, targeted benchmark for evaluating proactive trigger detection and restraint in embodied interaction.
Recent diffusion-based models have enabled realistic audio-driven avatar generation in real-time streaming. However, existing approaches struggle to maintain visual temporal consistency and fail to explicitly perceive user intent in complex interactive streaming scenarios. To address these challenges, we propose InteractiveAvatar, a real-time infinite-streaming video generation framework that supports visually consistent avatar video generation and intent-aware interactions. With autoregressive distillation, InteractiveAvatar achieves real-time str-eaming generation of human avatars over arbitrarily long durations. For visual consistency, we introduce a Long-Short Visual Memory (LSVM) mechanism that flexibly compresses historical visual information into compact tokens, preserving both short-range coherence and long-term consistency. To generate avatars with speeches and actions aligned with user intent, we propose a Reasoning-Reaction Module (RRM), which incorporates a State-Cycling strategy and a Cache-Switching mechanism. Extensive experimental results over diverse scenarios demonstrate that our method achieves state-of-the-art visual consistency in long-duration generation, while enabling complex user-avatar interaction in real time.
Quanyue Song, Yishan He, Yanfei Zhang +6
State Key Laboratory of Human-Machine Hybrid Augmented Intelligence, Institute of Artificial Intelligence and Robotics, Xi’an Jiaotong University, China · China Telecom Artificial Intelligence Technology (Beijing) Co., Ltd., China · State Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing, Wuhan University, China +1
We present Action Agent, a two-stage framework that unifies agentic navigation video generation with flow-constrained diffusion control for multi-embodiment robot navigation. In Stage I, a large language model (LLM) acts as an orchestration module that selects video diffusion models, refines prompts through iterative validation, and accumulates cross-task memory to synthesize physically plausible first-person navigation videos from language and image inputs. This increases video generation success from 35% (single-shot) to 86% across 50 navigation tasks. In Stage II, we introduce FlowDiT, a Flow-Constrained Diffusion Transformer that converts optimized goal videos and language instructions into continuous velocity commands using action-space denoising diffusion. FlowDiT integrates DINOv2 visual features, learned optical flow for ego-motion representation, and CLIP language embeddings for semantic stopping. We pretrain on the RECON outdoor navigation dataset and fine-tune on 203 Unitree G1 humanoid episodes collected in Isaac Sim to calibrate velocity dynamics. A single 43M-parameter checkpoint achieves 73.2% navigation success in simulation and 64.7% task completion on a real Unitree G1 in unseen indoor environments under open-loop execution, while operating at 40--47 Hz. We evaluate Action Agent across three embodiments: a Unitree G1 humanoid (real hardware), a drone, and a wheeled mobile robot (Isaac Sim), demonstrating that decoupling trajectory imagination from execution yields a scalable and embodiment-aware paradigm for language-guided navigation.
Jeffrin Sam, Nguyen Khang, Yara Mahmoud +2
Intelligent Space Robotics Laboratory, Skoltech, Bolshoy Boulevard, 30, Moscow 121205, Russia