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
191 results for “keyword:"depth"” in ICLR 2027. 41 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]Depth Separation for Learning Hierarchical Interactions with Nonlinear State-Space Models▲3.0k2.33
[PDF]Modeling Depth Ambiguity: A Mixture-Density Representation for Flying-Point-Free Depth Estimation▼5.8k2.33
[PDF]Locked Evaluation Surfaces Transfer Failure and Sampling-Depth Entanglement in CRISPRi Perturbation-Effect Prediction▼1361.33
[PDF]Attention Routing Stabilizes Early: Working-Set Inference for Recurrent-Depth Language Models▼13k2.00
[PDF]Ablate-to-Validate: Are Vision-Language Models Really Using Continuous Thought Tokens?▼4.3k2.00
[PDF]DepState-JEPA: Learning Depth-Grounded State Representation for Visual Perception and Manipulation▲3972.67
[PDF]Self-Organizing Artificial Perceptron: Backpropagating through the Width and Depth of Neural Networks▲4.6k3.00
[PDF]DepthAgent: Advancing Geometry-Adaptive Depth Estimation via Sample-wise Expert Selection▼5.8k2.33
[PDF]Persistent Depth Ordering amid Shifting Block-Bypass Responses in Language Model Pretraining▲6.1k2.00
[PDF]CoverWeave: Coverage Percolation Governs Compositional Depth Extrapolation under Verifiable Rewards▼1361.33
[PDF]Learning from Recurrence: Internalizing Depth-Induced Preferences in Looped Language Models▲3.0k2.33
Withdrawn or desk rejected (41)
[PDF]GRE-GS: Geometry Repair and Gaussian Extrapolation for Sparse-View 3D Gaussian SplattingWithdrawn1.67
[PDF]DepthPruner: Visual Token Pruning with Pluggable Depth Guidance for Efficient Vision-Language-Action InferenceWithdrawn2.00
[PDF]Same Answer, Different Futures: Judging Latent States by Their Continuations in Looped TransformersDesk rejected
[PDF]Not All Recurrence Is Created Equal: Depth Sensitivity Differs Between Recurrence Dimensions of a Single CheckpointWithdrawn1.33
[PDF]Endogenous Signals Fail to Allocate: Per-Token Compute Value Is Real, Transient, and Not LearnableWithdrawn1.33
[PDF]Structure Before Attention: A Zero-Initialized Convolution Recovers Windowed Language-Model QualityWithdrawn1.33