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
1,104 results for “keyword:"diffusion models"” in ICLR 2027. 316 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]Decoding Beyond Hemodynamic Delay: Delay-Coupled Graph Dynamics for fMRI-to-Image Reconstruction▼4.3k2.00
[PDF]Learning Field Reconstruction from Incomplete Data by Globally Correcting Local Estimates▼5.8k2.33
[PDF]MC-Sparse: Deconstructing and Closing the Dense-Sparse Attention Gap in Diffusion Transformers▼4.3k2.00
[PDF]ResiSparse: Residual-Informed Exact-or-Approximate Sparse Attention for Efficient Video Generation▼12k1.67
[PDF]Not All Regions Need Equal Tokens: Motion-Adaptive Representation Allocation for Complex Human Image Animation▼5.8k2.33
[PDF]ReCAT: Recurrent Composable Activation Transition for Test-Time Scaling of Diffusion Models▲14k3.00
[PDF]Beyond Linear Representation Hypothesis: Non-Linear Activation Steering in Text-to-Image Models▲5.4k3.00
[PDF]A Continuous-Time Reinforcement Learning Framework for Fine-Tuning Discrete Diffusion Models▲9.2k2.67
[PDF]Inertial Fragment Matching: scalable shape-conditioned molecular generation via descriptor decomposition▲11.00
[PDF]CCTC: Constructive–Corrective Transition Calibration for Unsupervised Combinatorial Optimization▼4.3k2.00
[PDF]Multi-Resolution Flow Matching: Training-Free Diffusion Acceleration via Staged Sampling▼5.8k2.33
[PDF]Beyond the Estimate: Wiener-Informed Decoding for Easier Training of Pixel-Space Flow Models▲5103.00
[PDF]Diagnosing Pixel-Space Diffusion Transformers: From Depth-Wise Connectivity to Layer-Wise Attention Patterns▲1.9k3.67
[PDF]Not All Privilege Is Distillable: Calibrating Teacher Corrections for Few-Step Video Generation▲5103.00
[PDF]Displacement Matching: One Objective for Reward Learning and Distillation in Few-Step Generators▲452.75
[PDF]SANA-Video 2.0: Hybrid Linear Attention with Attention Residuals for Efficient Video Generation▼1.2k3.00
Withdrawn or desk rejected (316)
[PDF]PragyaMD: Parameter-Efficient Adaptation of Humanoid Motion Generators to Indic LanguagesDesk rejected
[PDF]Exploration-NFT: Reinforcing Protein Dynamics Generators for Persistent Conformational ExplorationWithdrawn2.00