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
657 results for “keyword:"metric"” in ICLR 2027. 165 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]QUERY-CONDITIONED RECONSTRUCTION REFINEMENT FOR 3D AFFORDANCE GROUNDING UNDER OCCLUSION▼3.7k2.25
[PDF]Accelerating End-to-End Cryptanalytic Extraction via Geometric Critical Point Screening▼4.3k2.00
[PDF]LEMON: Equivariant Learning over Attention Maps for Zero-Shot Misbehavior Monitoring on New LLMs▲5103.00
[PDF]Learning What Retrieval Misses: Federated Retrieval-Residual Memory for Language Models▼1.2k1.67
[PDF]Alignment Is Not Enough: Preserving Message Separability for Geometrically Robust Image Watermarking▼4.3k2.00
[PDF]Quaternion Structural-Spectral Aggregation for Training-Free Fine-Grained Leaf Image Retrieval▼4.3k2.00
[PDF]What Does Neural Collapse Indicate for Generalization?: A Singular Learning Theory Perspective▲3.9k1.67
[PDF]When High ROC-AUC Fails: Score Collapse and the Gradient Exposure Deficit in Anomaly Detection▼1361.33
[PDF]The Scientific Research Taste Benchmark (SciTaste-Bench): A Multi-Disciplinary Benchmark for Assessing Large Language Models' Judgment of Research Taste in Scientific Papers▲11.00
[PDF]Preserve, Then Bound: Conditionally Informative Acoustic Context for Few-Shot ATC Call-Sign Spotting▼4.3k2.00
[PDF]Large-scale factor analysis shows machine intelligence is only partially interpretable▼1.2k1.67
[PDF]Beyond the Transcript: Asymmetric Cognitive Graphs for LLM Agents in Social Deduction Games▼4.3k2.00
[PDF]Better Contrast Decisions, Worse Ranking? How Validation Selects Readouts for Text Embeddings▼1361.33
[PDF]Wider Groups, Fewer Weights: Efficient Pseudo-Orthogonal Equivariance via Geometric Algebras▼4.3k2.00
[PDF]Temporal Geometry Consistency for Local Structural Drift Verification in Generated Videos▼1.2k1.67
[PDF]Prediction Is Not Action: Reliability-Guided Analytic Refinement of Molecular Conformers▼1361.33
[PDF]Parameters as Agentic Memory: Internalizing Long-Horizon Memories for Efficient LLM Agents▲3.0k2.33
[PDF]Learning State Transitions Improves Downstream Policy Learning in Geometry Theorem Proving▼13k2.00
[PDF]SCAL: A Station-Calibrated Asymmetric Loss for Extreme-Aware Spatiotemporal Wind Forecasting▼4.3k2.00
[PDF]InfluPose: Learning State-Conditioned Geometric Influence for Category-Level Object Pose Estimation▲3952.67
Withdrawn or desk rejected (165)
[PDF]What a 3D Reconstruction Benchmark Can and Cannot Tell About Geometric Foundation ModelsWithdrawn2.00
[PDF]Depth-Resolved Gene Expression Estimation from Tissue Morphology and Sparse Spatial TranscriptomicsWithdrawn1.67
[PDF]Beyond the Visible Surface: Geometry-Guided Joint Optimization of Multi-Layer Gaussians for Single-View Scene ReconstructionWithdrawn1.67
[PDF]Learning Scalar Quadratic Contrasts for High-Dimensional Change Point LocalizationDesk rejected1.75
[PDF]When Geometry Flips Architecture Rankings: An Exact Theory of Alignment and ComplexityDesk rejected
[PDF]When the Average Doesn't Exist: Why Learned Insurance Payouts Fail Under Distribution ShiftDesk rejected