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
695 results for “keyword:"generative models"” in ICLR 2027. 150 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]The Rank Bottleneck in Diffusion Transformers: Why and When Width Must Track Token Dimension▲452.75
[PDF]BrainGenFlow: Modeling Longitudinal Progression via Residual Flow Matching and Gaussian Imputation▲3.0k2.50
[PDF]Reinforcement Learning on the Discrete Composition Channel of a Crystal Generator: Validated Gains and Reward Hacking▲5.7k2.00
[PDF]Rhythm Flow: Bridging the Gap Between Functional Fluctuations and Neural Spikes Through Oscillatory Synchronization▼5.8k2.33
[PDF]Commutator-Guided Calibration of Attention-Head Interactions in Diffusion Transformers▼4.3k2.00
[PDF]Design yield is a tail functional: why distributional metrics cannot rank generative designers▲6.1k2.00
[PDF]What Defines a High-Quality Generated Material? Stress-Testing Generative Models on Amorphous Matter▲444.00
[PDF]Nethobench: Forecasting design and conditioning shape the structural realism of generated neural dynamics▼1.3k1.75
[PDF]POST-TRAIN THE MAP YOU SOLVE: DEPLOYMENT-ALIGNED SPECIALIZATION FOR FEW-STEP FLOW SAMPLING▼5.8k2.33
[PDF]Physics Before the First Step: Rectifying the Text Embedding of Frozen Video Generators▲3972.67
[PDF]Your VAE Knows Where to Sample, Not What It Doesn't Know: Merged Aggregated Posteriors as Deterministic Priors and Cluster Maps▲11.00
Withdrawn or desk rejected (150)
[PDF]Propagation Is Not Decoration: When Physical Diffraction Carries Generative ComputationWithdrawn1.00
[PDF]Exploration-NFT: Reinforcing Protein Dynamics Generators for Persistent Conformational ExplorationWithdrawn2.00
[PDF]A Compact Probabilistic Recurrent Operator for Forecasting Climate-Sensitive Disease Incidence under Partial ObservabilityDesk rejected