In this report, we introduce the Reciprocal World Model (RWM) and present Duo v1, a full-duplex world model that continuously perceives audiovisual inputs while responding to users in real time. The RWM treats intelligence and physical reality as equally fundamental to what constitutes a world. Existing world models largely focus on simulating the latter, leaving reasoning and decision-making as external controls rather than intrinsic parts of the world itself. In RWM, we identify two equally fundamental capabilities: Intent, which provides the cognition underlying world interactions, and Realization, which generates coherent audio-visual behavior. To realize this formulation, Duo v1 introduces three key technical designs: (1) Leveraging autoregressive modeling for continuous interaction reasoning and participation decisions, rather than restricting it to instruction understanding for diffusion models. (2) Constructing chunk-specific conditions and synchronize tokens across Intent and Realization on a unified timeline. Module-specific attention masks enforce causal dependencies both within and across chunks, preventing access to future inputs. (3) Mitigating distribution shift in both modules through dual rollout distillation, training on autoregressively generated Intent tokens and synthesized audiovisual histories from Realization. Both modules continuously perceive real-time audio, video, and text, enabling full-duplex interaction with spontaneous conversations and interruptions. Beyond conversation, users can share real objects, reshape virtual scenes, guide assistants, or play audiovisual games without mouse or keyboard controls. The release of Duo v1 makes our first step, with the next version coming soon. We look forward to broader exploration of this emerging field.
Figures & tables
Figure 1: Illustrative scenarios for full-duplex interaction with Reciprocal World Model .
Figure 2: The framework of Duo v1 . A joint causal diffusion transformer is conditioned on hidden states from the Intent Module, directly encoded user video and audio, a visual reference, and previously generated assistant media. The conversation media illustrate an offline, script-conditioned example.
Figure 3: ASR-aligned chunk construction and causal supervision. On a shared audiovisual timeline, user text is assigned to chunks by aligned token end times, while assistant text targets are assigned by speech onset. The token <blank> marks the absence of newly available user text. An assistant chunk with no new speech onset uses <wait> , even if speech from the preceding chunk continues. At chunk k , the Intent Module predicts yk from Ckϕ , using user inputs available through chunk k−1 . The initial output y0 is fixed to <wait> . Only subsequent assistant targets contribute to the loss.
Figure 4: Overview of Stage 1 (Intent Training) and Stage 2 (Realization Training).
Figure 5: Training sequence, positional encoding, and attention mask of the Realization Module. (a) The training context CR contains the reference, the shared global instruction, clean media of all chunks, and, for each chunk, the Intent Module hidden states followed by the noisy media. (b) Temporal RoPE positions in chunk k follow playback time in 25 ms units from the chunk start sk : text tokens and audio latents advance by one unit per index, and each video latent takes the start time of its frame span. (c) Causal attention mask. The noisy media of chunk k read the reference, the shared instruction, clean media of earlier chunks, the hidden states of chunk k , and themselves, but not the clean media of chunk k or any later chunk.
Figure 6: DMD training with dual rollout. The frozen Intent Module replays recorded assistant text and generates the final assistant turn from chunk k0 onward. Its hidden states h^k condition the Realization Module Gθ , which generates the latent window zgen chunk by chunk. The frozen real score model μreal and the trainable fake score model μfake evaluate the corrupted latent window to construct the target zDMD . Red arrows indicate gradients to Gθ . Orange arrows indicate gradients to μfake and D . Dashed outlines indicate optional components.
Figure 7: Screenplay-driven dual-view generation. Stage I turns sampled control cards into a validated structured screenplay and renders it, without another LLM call, into one t2v prompt per block. Stage II generates one split-screen audio-video block by block. Each later block starts from the previous block’s final frame (orange) and is anchored to the same opening segment of block 0 (blue), so identity and voice references are never re-chained through earlier continuations. Frames and dialogue in this figure come from one generated 30 s sample.
Figure 8: Screenplay and t2v prompt. (a) The screenplay written by the LLM for the sample in Fig. 7 . (b) The t2v prompt rendered from it for a continuation block. Shaded sentences are fixed text shared by all samples, grouped as [1]-[3] in the main text. ⟨⋅⟩ marks screenplay fields copied into the prompt, and the remaining lines are abridged template text.
Figure 9: Error accumulation over a 60 s, ten-block rollout. Top: mean luma Y′ (0–255) of the full split-screen frame per block (table) and per frame (plot). Bottom: the split-screen frame at the middle of blocks 0, 3, 6, and 9. Base conditions each block only on the previous final frame, and Ours adds the fixed block-0 picture-quality reference. Both runs share the same block 0 and screenplay.
Figure 10: Recorded data sources, interaction formats The six categories describe the recorded sources, with selected categories requiring further processing or synthesis to construct training examples.
Figure 11: Streaming inference on eight GPUs. Time advances from left to right. The Intent Module runs its VLM with four-way tensor parallelism (TP4) on GPU 0-3, alongside auxiliary ASR. The Realization Module executes the DiT on GPU 0-7 using tensor or sequence parallelism (TP/SP), while the streaming VAE uses 4-way spatial tiling on GPU 4-7. The first visible execution of the Intent Module processes input k , which is omitted from the figure. The second execution processes input k+1 . Hidden states hk from the Intent Module condition the Realization Module, which performs 4 denoising steps followed by a clean forward that commits the KV state. The unified KV manager uses a sliding window for Intent Module KV and periodic resets for Realization Module KV. Chunk k+1 skips history reads but retains the clean write. Decoding overlaps intent inference on separate GPUs before generation resumes. KV boxes mark manager operations.
Figure 12: Five functions of user–assistant interaction. Examples connect dialogue to plans, visible actions, shared solutions, social responses, and interactive customization. Panels (a)-(d) show offline, script-conditioned paired-video data. Panel (e) shows successive moments from a provided project demo.
Figure 13: Decisions and coordination. Six additional script-conditioned paired-video examples illustrate how the user and assistant question a proposal, revise a plan, reason through constraints, explain visible evidence, and coordinate a shared task.
Figure 14: Grounded and social responses. Seven additional script-conditioned conversations connect visible context and dialogue to creative, instructional, and supportive behavior. Panels (a)-(f) show different conversations. Panel (g) shows two moments from one conversation.
Natural interaction in digital and physical environments requires continuous perception and timely responses. Spoken dialogue relies on acoustic and linguistic cues, while video interaction also requires grounding the conversation in evolving visual context. We present Realtime-Venus, a proactive full-duplex interaction system with two separately trained 9B models: Realtime-Venus-Omni for audio-visual interaction and Realtime-Venus-Audio for spoken interaction. Each model serves as a complete conversational frontend, integrating continuous perception, conversational control, and native speech generation through a shared causal timeline for user inputs, model outputs, and delegation events. A dual-loop runtime coordinates live interaction with background reasoning and tool execution. Foreground interaction continues while Realtime-Venus-Harness executes tasks asynchronously and returns results for integration into the ongoing dialogue. Both models follow a common post-training recipe combining offline understanding, proactive full-duplex trajectories, and delegation workflows. Among the evaluated online models, Realtime-Venus-Omni achieves the highest scores on six of eight video benchmarks, including StreamingBench (70.2%), OVO-Bench (64.7%), and Daily-Omni (81.3%). Across eight audio understanding and spoken question answering benchmarks, Realtime-Venus-Audio leads the compared models on MMAU (78.0%), MMAU-Pro (63.2%), Llama Questions (83.8%), and Speech CMMLU (67.8%), while matching the best VoiceBench AlpacaEval score of 4.81. On Full-Duplex-Bench v1.5, Realtime-Venus-Audio responds to 75% of user interruptions and achieves continuation rates of 97%, 88%, and 86% under backchannels, other-directed speech, and background speech, respectively, exceeding Gemini 3.1 Live and GPT-4o on all three continuation metrics.
Recent progress in multimodal large language models (MLLMs) has brought AI capabilities from static offline data processing to real-time streaming interaction, yet they still remain far from human-level multimodal interaction. The key bottlenecks are no longer modality coverage or latency alone, but the interaction paradigm itself. First, perception and response are still separated into alternating phases, preventing models from incorporating new inputs for timely adjustment during generation. Second, most current models remain reactive, responding only to explicit user requests instead of acting proactively in the evolving multimodal environment. We present MiniCPM-o 4.5, our latest effort towards human-like multimodal interaction, which mitigates these gaps by real-time full-duplex omni-modal interaction. It can see, listen, and speak simultaneously in real-time, while also exhibiting proactive behaviors such as issuing reminders or comments based on its continuous understanding of the live scene. The key technique behind MiniCPM-o 4.5 is Omni-Flow, a unified streaming framework that aligns omni-modal inputs and outputs along a shared temporal axis. This formulation converts conventional turn-based interaction into a full-duplex, time-aligned process, enabling simultaneous perception and response and allowing proactive behavior to arise within the same framework. With a total of 9B parameters, MiniCPM-o 4.5 approaches Gemini 2.5 Flash in vision-language capabilities, delivering state-of-the-art open-source performance at its scale. It also surpasses Qwen3-Omni-30B-A3B in omni-modal understanding and delivers better speech generation, with significantly higher computation efficiency. Driven by its efficient architecture design and inference optimization, the model can perform real-time full-duplex omni-modal interaction on edge devices with less than 12GB RAM cost.
We present Wan-Streamer v0.3, which reframes our native-streaming interaction model under a single organizing view: a video is a world plus an event stream. The world is the persistent context in which a video unfolds, including the environment, scene, subjects, ambient acoustic conditions, voice characteristics, and other relatively stable conditions. The event stream is everything that changes over time within that world, including scene or environmental changes, subject behavior, speech, and other sounds. This yields a general-purpose pretraining task over large amounts of real video: given a world and incoming input, predict how the world moves, changes, and responds in real time. The resulting competence can be specialized to a broad family of real-time downstream tasks. We instantiate it on real-time full-duplex audio-visual interaction, where the event stream is the agent's speech together with free-form behavior. Functionally, the model's multimodal understanding process is vision-language-action-like: it maps multimodal user input to language-form speech and behavior actions. Wan-Streamer v0.3 preserves the v0.2 operating point: 640x368 video at 25 FPS, a 160 ms streaming unit, approximately 200 ms model-side response latency, and approximately 550 ms total interaction latency under a 350 ms bidirectional network budget.