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2,210 results for “area:"generative models"” in ICLR 2027. 672 withdrawn or desk rejected listed apart.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]The Parallel-Decoding Score of Masked Diffusion Language Models Is Not a Mutual Information▲13k2.33
[PDF]Attract to Align, Repel to Differentiate: Contrastive Representation Alignment for Diffusion Models▼5.8k2.33
[PDF]Does the Denoising Trajectory Reveal the Source of Uncertainty in Diffusion Language Models?▼5.8k2.33
[PDF]AlphaRef: Reference‑Guided Autoregressive Formula Generation for Formulaic Alpha Mining▼1361.33
[PDF]Solver.EXE: Learning to Solve Expert-level Problems via EXploration and Exploitation at Test-time▼5.8k2.33
[PDF]OvaDiP: Controlling Structured Diffusion Paths, Separating Training and Sampling Contributions, and Tracking Their Dynamics▼1361.33
[PDF]CAVC: Convergence-Adaptive Audio-Visual Cache for Modality-Asymmetric Diffusion Generation▼4.3k2.00
[PDF]Rewire then Express: Cascaded Flow Matching for Single-Cell Perturbation Response Prediction▲1.7k3.33
[PDF]Ordered Representations for Pixel Diffusion: Denoising with Learned Velocity Correction▲5103.00
[PDF]Mean-Shifted Intermediate Sampling: Training-Free Acceleration for Few-Step Diffusion Generation▲5103.00
[PDF]FreqWak: Lightweight Inversion-Free Frequency-Domain Watermarking For Time Series Data▼1.2k1.67
[PDF]Test-Time Scaling for Multi-View Diffusion Models: Generation, Verification, and Search▲3942.67
Withdrawn or desk rejected (672)
[PDF]Propagation Is Not Decoration: When Physical Diffraction Carries Generative ComputationWithdrawn1.00