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2,210 results for “area:"generative models"” in ICLR 2027. 672 withdrawn or desk rejected listed apart.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]UniRect-CoT: Enhancing Generation in Unified Multimodal Models via Reflective Rectification with Inherent Understanding▲5103.00
[PDF]High Scores, Narrow Vocabularies: Measuring Cross-Trial Diversity in Large Language Models▼1.2k1.67
[PDF]CAST: Conditional Generation and Adversarial Selection for Tabular Data Synthesis with Long Text Columns▼5.9k2.50
[PDF]HorizonKV: Future-Aware KVCache Reuse via Lightweight Relevance Estimation for Interleaved Agent Contexts▼1.2k1.67
[PDF]Correct While Verifying: Intermediate Target Predictions for Speculative Draft Correction▼1361.33
[PDF]Know When to Hold 'em: Correct-Token Retention in Uniform-State Diffusion Language Models▲3952.67
[PDF]Let It Go or Learn to Self-Correct: Continuous Diffusion for Constrained Discrete Tasks▲9.2k2.67
[PDF]DexBeyond: Scaling Dexterous Manipulation Through Iterative Hand-Object Interaction Generation▲3.0k2.33
[PDF]Cannot Wait to Verify: Parallel Drafting to Eliminate Verifier Idle Time in Speculative Decoding▼1361.33
[PDF]Multi-Bit Watermarking for Discrete Diffusion Language Models via Bitwise Evidence Feedback▼4.5k2.67
[PDF]Rule-Guided Graph Synthesis: Integrating First-Order Logic into Deep Generative Models▼1.2k1.67
Withdrawn or desk rejected (672)
[PDF]Propagation Is Not Decoration: When Physical Diffraction Carries Generative ComputationWithdrawn1.00