… The following papers were recommended by the Semantic Scholar API Uni-ViGU: Towards Unified Video Generation and Understanding via A Diffusion-Based Video Generator 2026 MMCORE: MultiModal COnnection with Representation Aligned Latent Embeddings 2026 UniCSG: Unified High-Fidelity Content-Constraine… …
Papers arxiv:2605.04128 Awaking Spatial Intelligence in Unified Multimodal Understanding and Generation Published on May 5 Submitted by taesiri on May 7 Authors: , Wenbo Li , , , Bo Wang , , , , , , , , , , , , , , Abstract JoyAI-Image integrates a spatially enhanced MLLM with MMDiT to achieve unif… …
Papers arxiv:2605.08029 STARFlow2: Bridging Language Models and Normalizing Flows for Unified Multimodal Generation Published on May 8 Submitted by taesiri on May 11 Apple Authors: , , , , , , , , Abstract Autoregressive normalizing flows based on Transformer architecture enable unified multimodal … …
Papers arxiv:2606.01048 Decoupled Residual Denoising Diffusion Models for Unified and Data Efficient Image-to-Image Translation Published on May 31 Submitted by Liangqiong Qu on Jun 3 The University of Hong Kong Authors: , , , , , , , Jiawei Liu , Abstract Decoupled Residual Denoising Diffusion mod… …
… The following papers were recommended by the Semantic Scholar API LIVE: Leveraging Image Manipulation Priors for Instruction-based Video Editing 2026 MMCORE: MultiModal COnnection with Representation Aligned Latent Embeddings 2026 ImVideoEdit: Image-learning Video Editing via 2D Spatial Difference … …
Papers arxiv:2605.03941 A Benchmark for Interactive World Models with a Unified Action Generation Framework Published on May 5 Submitted by taesiri on May 6 Authors: , , , , , , , , , , Abstract A comprehensive benchmark named iWorld-Bench is introduced to evaluate world models' physical interactio… …
Papers arxiv:2605.31604 Representation Forcing for Bottleneck-Free Unified Multimodal Models Published on May 29 Submitted by taesiri on Jun 1 3 Paper of the day ByteDance Seed Authors: Yuqing Wang , , , , , , , , Fuyun Wang , Shuai Wang , , , Abstract Representation Forcing enables unified multimo… …
Papers arxiv:2606.01027 τ 0-WM: A Unified Video-Action World Model for Robotic Manipulation Published on May 31 Submitted by Jianlan Luo on Jun 2 Authors: , , , , , , , , , , , , , , , , , , , Abstract A unified video-action world model integrates policy learning, video prediction, and action evalu… …
… AI-generated summary We propose X-WAM, a Unified 4D World Model that unifies real-time robotic action execution and high-fidelity 4D world synthesis video + 3D reconstruction in a single framework, addressing the critical limitations of prior unified world models e.g., UWM that only model 2D pixel-… …
… To this end, we propose Skill Reward Model Skill-RM , a unified framework that reformulates reward modeling as the execution of a reusable Reward-Evaluation Skill. …
