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2,210 results for “area:"generative models"” in ICLR 2027. 672 withdrawn or desk rejected listed apart.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]Conditional Diffusion without ERM Oracles: From Finite Neural Training to Sampling Guarantees▼5.8k2.33
[PDF]Joint Branch-Space Transform Coding for Diffusion Activation Quantization with Classifier-Free Guidance▼4.5k2.67
[PDF]EXACT WARM-STATE REUSE FOR HYBRID DIFFUSION LANGUAGE MODELS: CONTRACTS, SPEEDUPS, AND FAILURE BOUNDARIES▲3.0k2.33
[PDF]Spec2Twin-Chain: Orchestrating Bi-Level Optimization with LLMs for Blockchain Digital Twin Construction▼1.2k1.67
[PDF]Order-Marginalized Generation of Semantic and Collaborative IDs for Generative Recommendation▲5103.00
[PDF]What Makes a Search Space Effective for Evolution Strategies in Diffusion Fine-Tuning?▼1.2k1.67
[PDF]Codebook-Geometry Correction: Replacing Test-Time Refinement with a Few Analytic Steps in Trajectory-Controlled Text-to-Motion Generation▼11k2.33
[PDF]Reconstruction Does Not Determine Generative Learnability: A Theory of Resource-Matched Visual Tokenization▼4.3k2.00
[PDF]Gauge and Drift: Separating Commanded Change from Error Accumulation in Autoregressive Generation▼5.8k2.33
Withdrawn or desk rejected (672)
[PDF]Propagation Is Not Decoration: When Physical Diffraction Carries Generative ComputationWithdrawn1.00