visual generation

Learning What to Trust: Bayesian Prior-Guided Optimization for Visual Generation CVPR 2026 ParaUni: Enhance Generation in Unified Multimodal Model with Reinforcement-driven Hierarchical Parallel Information Interaction CVPR 2026 Rethinking UMM Visual Generation: Masked Modeling for Efficient Image-Only Pre-training CVPR 2026 SCAN: Self-Calibrated AutoregressioN for High-Quality Visual Generation AAAI 2026 SeaCache: Spectral-Evolution-Aware Cache for Accelerating Diffusion Models CVPR 2026 ThinkGen: Generalized Thinking for Visual Generation CVPR 2026 Thinking-while-Generating: Interleaving Textual Reasoning throughout Visual Generation CVPR 2026 Uni-MMMU: A Massive Multi-discipline Multimodal Unified Benchmark ACL 2026 VisionReward: Fine-Grained Multi-Dimensional Human Preference Learning for Image and Video Generation AAAI 2026 VQRAE: Representation Quantization Autoencoders for Multimodal Understanding, Generation and Reconstruction CVPR 2026 ACE: All-round Creator and Editor Following Instructions via Diffusion Transformer ICLR 2025 Beyond Next-Token: Next-X Prediction for Autoregressive Visual Generation ICCV 2025 CODA: Repurposing Continuous VAEs for Discrete Tokenization ICCV 2025 Generating Pedagogically Meaningful Visuals for Math Word Problems: A New Benchmark and Analysis of Text-to-Image Models ACL 2025 Goku: Flow Based Video Generative Foundation Models CVPR 2025 Imbalance in Balance: Online Concept Balancing in Generation Models ICCV 2025 MetaMorph: Multimodal Understanding and Generation via Instruction Tuning ICCV 2025 MUSE-VL: Modeling Unified VLM through Semantic Discrete Encoding ICCV 2025 Neighboring Autoregressive Modeling for Efficient Visual Generation ICCV 2025 Parallelized Autoregressive Visual Generation CVPR 2025 PUMA: Empowering Unified MLLM with Multi-granular Visual Generation ICCV 2025 RandAR: Decoder-only Autoregressive Visual Generation in Random Orders CVPR 2025 RealGeneral: Unifying Visual Generation via Temporal In-Context Learning with Video Models ICCV 2025 ScImage: How good are multimodal large language models at scientific text-to-image generation? ICLR 2025 Toward Guidance-Free AR Visual Generation via Condition Contrastive Alignment ICLR 2025