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
1,168 results for “keyword:"generative"” in ICLR 2027. 259 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]C-Steering: Constrained Noise-Space Steering of Behaviour-Cloned Flow Policies for Offline Safe RL▼1361.33
[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]Data, Objective, and Architecture: When Do Independent Policy-Gradient Learners Collude?▼1.2k1.67
[PDF]MultiUS : Unsupervised Persona Mixture and Norm-Bounded Latent Steering for User Simulation▼1361.33
[PDF]DreamCloth : Structural Counterfactual Score Factorization for Behavioral System Identification▼5.8k2.33
[PDF]Nethobench: Forecasting design and conditioning shape the structural realism of generated neural dynamics▼1.3k1.75
[PDF]Spec-CoFrGeNet: Reparametrizing Continued Fraction Networks for Stable and Accurate Training▼5.8k2.33
[PDF]POST-TRAIN THE MAP YOU SOLVE: DEPLOYMENT-ALIGNED SPECIALIZATION FOR FEW-STEP FLOW SAMPLING▼5.8k2.33
[PDF]Efficient Generative Prediction for EHR Foundation Models: The SCOPE and REACH Estimators▲3972.67
[PDF]Generative Bellman Flow: Mitigating the CVaR Gradient Bottleneck in Risk-Sensitive Reinforcement Learning▼4.3k2.00
[PDF]Decentralized Master-Mind: Joint Action Refinement through Iterative Intent Denoising in Multi-Agent Pathfinding▲5103.00
[PDF]Universal Mixup Loss: Training Audio Autoencoders to Decode the Positive-Weight Mixing Cone▲3972.67
[PDF]Physics Before the First Step: Rectifying the Text Embedding of Frozen Video Generators▲3972.67
Withdrawn or desk rejected (259)
[PDF]Propagation Is Not Decoration: When Physical Diffraction Carries Generative ComputationWithdrawn1.00
[PDF]Beyond the Observed: Knowledge-Informed Controllable Augmentation for Few-Shot Class-Incremental LearningWithdrawn1.50
[PDF]TYPED AMPLITUDE COMPOSITION FOR REUSABLE INFERENCE: SEMANTICS, ERROR BOUNDS, AND EXACT CORRECTIONWithdrawn
[PDF]Exploration-NFT: Reinforcing Protein Dynamics Generators for Persistent Conformational ExplorationWithdrawn2.00