NeurIPS 2026 reviews are up: reviews, scores, rebuttals and meta-reviews for 7,877 papers. See the highest rated
acceptodds: the papers of ICLR 2027
2,210 results for “area:"generative models"” in ICLR 2027. 672 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]Internalizing Agent Experience into Diffusion Model Weights via On-Policy Context Distillation▼4.5k2.67
[PDF]LARC: A General Late-stage Adaptive Reconstruction Corrector for Diffusion Inverse Problems▼4.3k2.00
[PDF]SPIN: Scale-aware Position-unbound Identity Injection for Consistent Visual Autoregressive Generation▲3.0k2.33
[PDF]SmartDirector: Keyframe-Conditioned Cinematic Video Generation with Narrative Pacing Control▲3952.67
[PDF]PhonoNoise: Reshaping Diffusion Geometry via Phonology-Aware Non-isotropic Diffusion for Sign Language Production▼12k1.67
[PDF]Walking the Score Manifold: Continuous-time Generative Dynamics on Learned Data Manifolds▲143.33
[PDF]From Set Diversity to Output Diversity: Progressive Selection for Inference-Time Alignment▲5103.00
[PDF]Calibrate Before You Measure: Conditioning Interfaces Decide What a Generative Probe Reports▼1.2k1.67
[PDF]Context-Tower Conversion Preserves Generation While Freezing Retains Knowledge: Low-Budget AR-to-Diffusion Conversion of MoE LLMs▼1361.33
[PDF]Explore Widely, Exploit Wisely: Harnessing Text–Image Cost Asymmetry for Unified Multimodal Reinforcement Learning▼4.5k2.25
[PDF]SphericalMark: Third-Moment Preserving Diffusion Watermarks with Adaptive Augmentation Detection▼1611.50
[PDF]ArtiVidRM: Verifiable Artifact-as-Rubric Reward Modeling for Explicit Quality Articulation in Video Generation▲3952.67
[PDF]Weighting Schedules Govern What and When Score-Based Generative Models Learn from Multimodal Data▲1.7k3.33
[PDF]Native Generation of Tileable Pixel-Art Textures from a Material Name and a Target Colour▼1.2k1.67
[PDF]One Schedule Does Not Fit All: Adaptive Inference Schedules for Diffusion Language Models▼4.3k2.00
[PDF]Pixel Art Is a Palette, Not a Downscale: Rebuilding Targets and Decoding for Sprite Generation▼5.3k1.33
Withdrawn or desk rejected (672)
[PDF]Propagation Is Not Decoration: When Physical Diffraction Carries Generative ComputationWithdrawn1.00