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
448 results for “keyword:"function"” in ICLR 2027. 115 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]When Labels Have Structure: Improving Image Classification with Hierarchy-Aware Cross-Entropy▲3.0k2.33
[PDF]A Manifold-Aware Activation Steering Method for Large Language Models via Geometric Safety Control▼3.7k2.25
[PDF]Efficient Online Reinforcement Learning with All-Policy Linear -Realizability and Sparse Stochastic Transitions▼1.2k3.00
[PDF]A Smooth Polynomial Lyapunov Certificate for Convergence of Q-Learning and Its Smooth Variants▼5.8k2.33
[PDF]Compact Chain-of-Thought Distillation with Visual Grounding Guidance for Vision-Language Models▲9.2k2.67
[PDF]HiBrain: Structure-Calibrated Higher-Order Hypergraph Learning for Brain Network Analysis▲3.0k2.33
[PDF]ArticulateCode: Functional Contracts and Physical Baking for Articulated 3D Asset Generation▼1351.33
[PDF]How Much Structural Abstraction Does Traffic Forecasting Need? A Benchmark for Controllable Multimodal Representations▼5.8k2.33
[PDF]RELU NEURAL NETWORK APPROXIMATION TO SMOOTH FUNCTIONAL OPERATOR: DIMENSIONAL DECAY AND ERROR ANALYSIS▲5103.00
[PDF]GEM-Reasoner: Protein Function Reasoning for Genome-Scale Metabolic Model Reconstruction▼4.3k2.00
[PDF]CRANE: Functional Selectivity of Language-Conditioned Neurons in Multilingual Large Language Models▼1.2k1.67
[PDF]Machine Learning Force Fields Without Precomputed Labels: Variational Kohn-Sham Training▲3.8k2.50
[PDF]What Makes Two Robot Failures the Same? Learning Recoverability Functions for Zero-Shot Robot Recovery▼1.2k1.67
[PDF]Are Foundation Models Enough for Data-Scarce Functional Connectivity Diagnosis? Revisiting Task-Specific Learning with BrainLRR▼4.5k2.67
[PDF]OUTPUT FORMAT AND INDEX LOOKUP DEGRADE INCONTEXT TOOL SELECTION AT LARGE CATALOG SIZES▼1.3k1.75
Withdrawn or desk rejected (115)
[PDF]Activation Density in Transformer Feed-Forward Networks Is Set by the Nonlinearity, Not the WidthWithdrawn2.00
[PDF]Reflection Rewards Pay for Deferral: Capability-Aware Rewards for Reflective RLDesk rejected3.00
[PDF]Same Head, Different Calls? Auditing Functional Role Claims in Looped TransformersWithdrawn1.33