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93 results for “keyword:"feed forward"” in ICLR 2027. 35 withdrawn or desk rejected listed apart.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]Which output absorbs the conflict? Gauge-aware attribution for feed-forward 3D reconstruction▼1.2k1.67
[PDF]Every View Counts: View-Consistent Panoptic Quality for Multi-view Panoptic Segmentation▼5.8k2.33
[PDF]ConFixGS: Learning to Fix Feedforward 3D Gaussian Splatting with Confidence-Aware Diffusion Priors in Driving Scenes▲3952.67
[PDF]X-Splatter: Feed-Forward Metric 4D Gaussian Splatting for Surround-View Driving Scenes▼4.3k2.75
[PDF]DeltaSplat: Iterative Gaussian Refinement for Pose-Free Feed-Forward 3D Gaussian Splatting▲3952.67
[PDF]READ: Geometry-Guided Source Evidence Retrieval for Feed-Forward 3D Gaussian Splatting▲5.4k3.00
[PDF]Confidence Is Not Coverage: Budgeted Confidence Ranking Can Fail Under Fixed Reconstruction Budgets▼3.7k2.25
[PDF]Gaussian for Gaussian: Unifying Feature Representation and Rendering in Feed-Forward Driving Scene Reconstruction▼4.5k2.25
[PDF]TrajForward: Feed-Forward Dynamic 3D Gaussian Reconstruction for Urban Driving Scenes with Explicit Motion Trajectories▼1.2k3.00
[PDF]LUMEN-GS: Towards Light-Disentangled and Intrinsic-Aware Gaussian Splatting for Feed-forward Sparse-View Street Reconstruction▲143.33
[PDF]CSplat: Exploiting Cross-View Redundancy for Compact Feed-Forward 3D Gaussian Splatting▼4.3k2.00
[PDF]From Pixels to Compact Gaussians: Generalizable 2D Gaussian Image Representation via Error-Aware Graph Coarsening▼4.3k2.00
[PDF]Extending 3D Foundation Models from to Any Central Camera with Distortion Awareness Token▼1.2k3.00
[PDF]ZoomSplat: Rethinking Multi-view Frequency Bounds for Anti-aliased Feed-forward 3D Gaussian Splatting▲3952.67
Withdrawn or desk rejected (35)
[PDF]Real-Time Human Frontal View Synthesis from a Single Image via Unified Geometry ModelingDesk rejected
[PDF]Hybrid-VGGT: Scaling Visual Geometry Grounded Transformers to High Resolution via Multi-Scale Detail InjectionWithdrawn2.00