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
143 results for “keyword:"functions"” in ICLR 2027. 29 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]Arbitrary-Accuracy Neural Approximation with Optimal Neuron Count and Near-Optimal Bit Complexity▲1.7k3.33
[PDF]Lightweight Explainable Physics-Informed Neural Networks by Learnable Activation Function▲6.1k2.00
[PDF]LTCC: Localized Testing of Coordinate Contributions to Conditional Distribution Discrepancy▼5.8k2.33
[PDF]A Manifold-Aware Activation Steering Method for Large Language Models via Geometric Safety Control▼3.7k2.25
[PDF]What Makes Two Robot Failures the Same? Learning Recoverability Functions for Zero-Shot Robot Recovery▼1.2k1.67
[PDF]Refreshing Less, Selecting Better: Cache-Efficient Diverse Influence Selection for LLM▼4.3k2.00
[PDF]Scaling Influence Functions in LLMs through Eigenbasis-Corrected One-Bit Gradient Projection▲5103.00
[PDF]On computing Goldstein approximate second-order stationary points of structured nonsmooth nonconvex programs▲452.75
[PDF]On the hardness of deterministic second-order optimization of functions with Lipschitz gradients▼1.2k1.67
[PDF]Which Influence Are We Estimating? The Role of Counterfactual Specifications in Data Attribution▲3972.67
Withdrawn or desk rejected (29)
[PDF]Activation Density in Transformer Feed-Forward Networks Is Set by the Nonlinearity, Not the WidthWithdrawn2.00
[PDF]NASA-INR: Non-linear Adaptive Spectrally-spanning Activation for Implicit Neural RepresentationWithdrawn1.00
[PDF]High Influence Is Not New Influence: A No-Arbitrage Analysis of Multi-Capability Data SelectionWithdrawn2.00