arXiv Computer Vision
EchoWM: Open and Enterable Omnimodal World Models
Read the original on arXiv Computer Vision →The Flow has not summarised this story yet — read it at arXiv Computer Vision.
Related stories
arXiv Computer Vision
2d ago
Long-Horizon Audio-Visual Generation for Persistent Stories and Interactive Worlds
arXiv:2608.23383v1 Announce Type: new Abstract: Video generation is progressing beyond isolated clips toward long-form narratives and interactive worlds, requiring models to preserve identities, foll...
arXiv Computer Vision
6d ago
OmniCamera: A Unified Framework for Multi-task Video Generation with Arbitrary Camera Control
arXiv:2604. 06010v2 Announce Type: replace Abstract: Video fundamentally intertwines two crucial axes: the dynamic content of a scene and the camera motion through which it is observed.
Hugging Face Trending Papers
Jul 21
OmniReasoner: Thinking with Long Audio-Video via Native Tool Use
Long audio-video reasoning is difficult for omnimodal LLMs because the decisive evidence is often sparse, cross-modal, and too expensive to preserve with uniformly high-fidelity inputs. We introduce OmniReasoner, a tool-use post-training framework for Thinking with Long Audio-Video: omni-modal LLMs learn, via supervised fine-tuning and reinforcement learning, to decide whether and where to call a zoom-in tool before answering.
arXiv AI
Jun 2
AnyMo: Scaling Any-Modality Conditional Motion Generation with Masked Modeling
arXiv:2605. 29488v2 Announce Type: replace-cross Abstract: Conditional human motion generation remains a fundamental challenge in computer vision and robotics.
arXiv Computer Vision
1d ago
Tora3: Trajectory-Guided Audio-Video Generation with Physical Coherence
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...
Hugging Face Trending Papers
Aug 6
Vorch-Omni: Multi-Task Orchestration of Sight and Sound
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.