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
93 results for “keyword:"feed forward"” in ICLR 2027. 35 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]SpectralSplat: Appearance-Disentangled Feed-Forward Gaussian Splatting for Driving Scenes▼4.3k2.00
[PDF]StableCrowd: Spatio-Temporally Consistent Feed-Forward Crowd Reconstruction with Multi-Joint Height▲5.4k3.00
[PDF]Inverse Rendering without Training from Scratch: Unsupervised Post-Training of Feedforward 3D Gaussian Models▼4.3k2.00
[PDF]RemixGS: Scalable Feed-Forward Gaussian Splatting with View-Register Mixing and Interleaved Gaussian Queries▼4.3k2.00
[PDF]Understanding Affective Adaptation in Multimodal Foundation Models: Emergent Functional Specialization▼5.9k2.50
[PDF]S2D-Splat: Static-First Gaussian Reconstruction of Dynamic Driving Scenes with Layer-Wise Feature Guidance▼4.5k2.67
[PDF]Prox: Training-Free FFN Activation Sparsification in LLMs via Approximate Intermediate-State Salience▲3952.67
[PDF]DriveR: Feed-Forward Gaussian Reconstruction for Camera-LiDAR Simulation in Autonomous Driving▲3.0k2.33
[PDF]GaLA-SVR: Feed-Forward 3D Gaussian Framework with Physics-Aware Latent Aggregation for Slice-to-Volume Reconstruction▼5.8k2.33
[PDF]Learning Incompressible 3D Flows from Sparse Samples: A Set Transformer Approach to Divergence-Free Kernel Fitting▼1.2k3.00
[PDF]SplatAnything: Gaussian Spacing Normalization for Feed-forward 3DGS across Arbitrary Scenes▲5.4k3.00
Withdrawn or desk rejected (35)
[PDF]Activation Density in Transformer Feed-Forward Networks Is Set by the Nonlinearity, Not the WidthWithdrawn2.00