π“Ÿ host1.bitchan.one

𓀐 @U?q8Sg5F

⏱ 1h seenβ›“ 0πŸ‘ 0β§– 1

filter [-]

languages:onother

>mfw Research news 11/08/2026 >FlowRig: Unified Skeleton Generation for 3D and 4D Meshes via Flow Matching https://tamu-visual-ai.github.io/Flow >Computer Vision Applications for Art History: Reflections and paradigms for future research https://arxiv.org/abs/2611.026 >TaoMate-FVSR:Audio-Guided Facial Video Restoration https://arxiv.org/abs/2611.033 >Is This 3D Asset Usable? Beyond the Beauty Render for Asset Curation https://rbz-99.github.io/is-this-3d-asset >UniCross3D: Unified Cross-View and Cross-Domain Diffusion for Consistent Single-Image 3D Generation https://arxiv.org/abs/2611.026 >OmniOPD: Stable On-Policy Distillation for Joint Audio-Video Generation https://arxiv.org/abs/2611.028 >What Remains in Sight? Autoregressive Video Decoding as Representation-Guided Context Rewriting https://arxiv.org/abs/2611.041 >FlowTranslator: Training-Free In-Image Machine Translation with Flow-Based Editing https://arxiv.org/abs/2611.043 >EmoReward: Self-Evolving Reward Calibration for Emotional Video Generation RL https://arxiv.org/abs/2611.065 >Unlocking the Potential of Contrastive Regularization for Diffusion Transformer Training https://arxiv.org/abs/2611.029 >FFMT: Frequency-Factorized Multi-Rate Tokenization for Music-to-Dance Generation https://arxiv.org/abs/2611.073 >Generator-Aligned Reward Modeling with Target-Aware Bounded Optimization for Visual Generation https://arxiv.org/abs/2611.076 >PTQ4SAM3: Semantics-Preserving Post-Training Quantization for Segment Anything Model 3 https://arxiv.org/abs/2611.061 >Unaligned Image Guided Denoising via Cross-modal Conditional Flow Matching https://arxiv.org/abs/2611.064 >TRACEMARK: Editor-Aware Watermarking for User Attribution in Text-Guided Image Editing https://arxiv.org/abs/2611.076 >BISECT: Bilevel Spectral Decomposition for Low-Rank Continual Learning https://arxiv.org/abs/2611.035 >Scaling Laws for Multimodal Data Mixtures https://arxiv.org/abs/2610.144⏱ 1h↩