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
147 results for “keyword:"sensitivity"” in ICLR 2027. 46 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]FROM ATTENTION SENSITIVITY TO LAYER ROLE: REVISITING MIXED-PRECISION QUANTIZATION OF TRANSFORMERS▼1.2k1.67
[PDF]Where Compression Hurts: Function-Space Sensitivity for Mixed-Precision Neural Network Quantization▼4.3k2.00
[PDF]The Emperor's New Scaffold: Semantically Equivalent Harnesses Reshuffle the Leaderboard▼4.3k2.00
[PDF]Adaptive View Harness: Learning to Select Target-Preserving Views for Large Language Models▼71.25
[PDF]Same Results, Different Rankings: Measuring Evaluation-View Dependence in LLM Agent Benchmarks▼4.3k2.00
[PDF]Local Sensitivity in Decision Tree Ensembles with Applications to Explainability and Monitoring▼5.8k2.33
[PDF]StructViz-Bench: A Controlled Study of Visualization-Format Dependence in Multimodal LLM Reasoning over Structured Data▼1.2k1.67
[PDF]Applied but Not Received: Designing Effective Surrogate Gradients for Spiking Neural Networks▼4.5k2.67
[PDF]Four Cells Are Not the Same Dose: Size-Conditioned Spatial Lesions in Detection Transformers▲3.0k2.33
[PDF]Family-Dependent Changes in Token-Level Prompt Dependence across Post-Training Checkpoints▲6.1k2.00
[PDF]Interface-Controlled Evaluation and Size Transfer of Language-Model Equilibrium Solvers on Procedural Zero-Sum Matrix Games▲3.0k2.33
[PDF]Entropy as a Lens: Revealing Structural Importance in Masked Self-Supervised Vision Transformers▼1611.50
[PDF]When is Compositional Generation Feasible? Distributional Estimation Error and Inference-time Approximation Error in Diffusion Models▲3.0k2.33
[PDF]In Plain Sight: CurioBench-1K, a Benchmark for Whether Agents Utilize Environmental Resource Leads▼1361.33
[PDF]When Fisher Information Mispredicts Prior Sensitivity: Model Misspecification, Not Noise▲3.0k2.50
[PDF]Parameter Symmetries Are Not Task Symmetries: Which Invariances Can Weight-Space Learning Afford?▼11k2.33
[PDF]What Should We Freeze? Guarded Freezing: Connectivity Shapes the Fine-Tuning of Pretrained Models▲6.1k2.00
[PDF]Attention under Bounded Key–Query Similarity: Space Complexity and Transformer Anisotropy▲3972.67
[PDF]The Butterfly Effect in LLM Social Simulations: From Architecture Sensitivity to Robustness Audits▼4.5k2.67
[PDF]The Arithmetic Error Bar: A First-Passage Law for the Numerical Fragility of Language Models▼1361.33
Withdrawn or desk rejected (46)
[PDF]SlimVLM: Sensitivity-aware Dynamic Structured Pruning with Adaptive Visual Token Selection for Efficient Vision-Language ModelsDesk rejected2.33
[PDF]Rules Move Verdicts Mote Than Paraphrases: Controlled Evaluation of LLM-Judge PanelsWithdrawn1.00