π“Ÿ host1.bitchan.one

𓀐 @tVQW4Xtc

⏱ 5d seenβ›“ 0πŸ‘ 0β§– 1

filter [-]

languages:onother

>mfw Research news 11/02/2026 >RADI3N: GeometRic ImAge EDiting via ParametrIc 3D CoNtrol https://arxiv.org/abs/2610.40973 >GenDSR: Transferring Representations from Video Generation Models for Dynamic Spatial Reasoning https://arxiv.org/abs/2610.41314 >Any Forcing: Any-Step Generality and One-Step Stability for Autoregressive Video Generation https://arxiv.org/abs/2610.42031 >Latent Reasoning in Continuous Space for Unified Multimodal Models https://arxiv.org/abs/2610.42149 >GeoFlip: Benchmarking Geometry-Sensitive Physics in Video Generation https://arxiv.org/abs/2610.42002 >A Better Critic Matters for Distribution Matching Distillation https://peppaking8.github.io/critic-matters >No Channels Left Behind: Understanding Diffusion Acceleration through Residual Gates https://arxiv.org/abs/2610.40914 >TACO: Trajectory-Aware Curvature Observation for Memorization Localization and Mitigation in Diffusion Models https://arxiv.org/abs/2610.41520 >Grounding Image Composition with Label-Conditioned Visual Evidence https://arxiv.org/abs/2610.41080 >MoETok: Sparse Expert Routing for 1D Visual Tokenizers https://gjhhust.github.io/moetok-project >Coarse3D: Controllable and Faithful Sparse Structure Generation for Image-to-3D https://arxiv.org/abs/2610.41231 >From Evaluation to Evolution: Benchmarking Image Editing and Evolving Image Models https://arxiv.org/abs/2610.41210 >Scout-Refine-Correct: Teaching Flow Models to Refine Their Own Samples https://arxiv.org/abs/2610.41598 >Retrieval-Augmented Initialization with Dual-Guided Inversion for Flow-Based Inverse Problem Solvers https://arxiv.org/abs/2610.41695 >Understanding the Performance Plateau in Text-to-Video Retrieval: A Comprehensive Empirical and Linguistic Analysis https://arxiv.org/abs/2605.00826⏱ 5d↩