Tracked topic
…AI-generated summary In this paper, we propose AlphaGRPO, a novel framework that applies Group Relative Policy Optimization (GRPO) to AR-Diffusion Unified Multimodal Models (UMMs) to enhance multimodal generation capabilities without…
…Junbo Cui , , Chongyi Wang , Tianyu Yu , , , , , , , , , , , , , , , , , , Rongkang Wang Abstract MiniCPM-o 4.5 enables real-time full-duplex multimodal interaction through Omni-Flow, a unified streaming framework that aligns inputs and outputs…
…This formulation unifies category-conditioned counting with interpretable spatial localization. To support this setting, we construct CLOC, a Cross-domain Large-scale Object Counting dataset that reorganizes diverse public data sources into…
…However, existing open-source methods mainly rely on either dual-tower designs with posterior alignment or fully unified tri-modal designs that mix textual context, audio and video in one shared space…
…AI-generated summary Foundation models have established unified representations for natural language processing, yet this paradigm remains largely unexplored for tabular data. Existing methods face fundamental limitations: LLM-based approaches lack retrieval…
…We further introduce Unified Relative RoPE Recipe, which anchors the sink frames to start from id 0 and lets the newest frame id grow at most to the DiTs ' pretrained maximum temporal…
Papers arxiv:2607.19343 Masked Visual Actions for Unified World Modeling Published on Jul 21 Submitted by taesiri on Jul 22 Authors: , , , , , , , , , , Abstract V i d e o m o d e…
…Xu Guo , , , , , , , , , , , , , Abstract ContextMaster unifies multi-shot video generation, reference conditioning, and editing via role-aware context routing and privileged distillation to maintain history with fixed cost. Generated by thinkingmachines/Inkling-Small…
…A unified feature pipeline enables consistent alignment across video trajectories, acoustic signatures, and chart-derived measurements, allowing EMMA to estimate parameters under forced, implicit, and multivariate dynamics without requiring segmentation masks, differentiable…
…Wei Zhou , Xiongwei Zhu , , , , , Meng Chu , , Lingdong Kong , , Abstract A novel on-policy generative field distillation framework called DanceOPD is proposed to unify text-to-image generation, local editing, and global editing…