The paper demonstrates that specialized coding agents, using only text and image access within a sandbox, can effectively solve complex omnimodal tasks, often outperforming state-of-the-art native omn…

T2Mo is a novel framework that generates controllable dynamic 3D object shapes by combining explicit 3D trajectories for spatial guidance with natural language text semantics.

The paper proposes a novel cross-axis feature fusion architecture and an auxiliary joint-difference prediction task to significantly improve text-based 3D human motion editing by better understanding…

RoboDream introduces an embodiment-centric world model that synthesizes photorealistic, physically feasible robot demonstrations by decoupling motion generation from environment synthesis, significant…

The paper introduces Archon, a unified, fully pretrained multimodal model that addresses the challenge of generating holistic digital humans by integrating seven modalities (including text, audio, mot…

The paper proposes a novel render-free framework that conditions video diffusion models directly on compressed 3D human mesh tokens, enabling robust 3D-aware human motion control without relying on re…

PhyGenHOI introduces a novel framework that generates physically accurate and visually faithful 4D Human-Object Interactions by coupling generative human motion with explicit physical object simulatio…

The paper introduces MOV-Bench, a challenging benchmark for multi-hop audio-visual reasoning, and proposes AOP-Agent, an agentic framework that significantly improves open-source Omni-LLMs' ability to…

The paper introduces Humanoid-GPT, a large-scale generative Transformer model that achieves robust zero-shot motion tracking and control by training on a massive, unified corpus of motion data.

Lumos-Nexus is a training-efficient framework that enhances video generation quality by progressively bridging generation from a lightweight model to a high-fidelity generator in a shared latent space…

The paper proposes FedMChain, a novel federated learning framework that structures multimodal training into sequential phases to mitigate modality competition and improve model performance while reduc…

Real2SAM2Real introduces a framework that uses explicit 3D caches, derived from 3D lifting models, to provide robust geometric guidance to Video Diffusion Models, significantly improving spatiotempora…

V-LynX is a framework that enhances Video LLMs by integrating new modalities into their existing token interface, achieving state-of-the-art performance across diverse video understanding tasks.

The paper introduces semantic motion anchors, a method that bridges the gap between spoken text and gesture meaning by providing structured, semantically grounded supervision, significantly improving…

This paper introduces the concept of Safety Geometry Collapse, demonstrating that multimodal inputs degrade the safety separation of LLMs, and proposes ReGap, a training-free method that adaptively co…

This paper presents GRAIL, a digital generation pipeline that synthesizes human-object interactions for humanoid robots.

The paper introduces CrossMPI, a novel cross-modal prompt injection attack that uses image-only perturbations to steer the interpretation of both textual and visual inputs in Large Vision-Language Mod…