SOTAVerified

valid

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 476–500 of 3589 papers

TitleStatusHype
Learning Deep Dissipative DynamicsCode0
A Markovian Model for Learning-to-Optimize—0
Optical ISAC: Fundamental Performance Limits and Transceiver Design—0
Safety-Critical Stabilization of Force-Controlled Nonholonomic Mobile Robots—0
Inference with Many Weak Instruments and Heterogeneity—0
Conformalized Interval Arithmetic with Symmetric CalibrationCode0
On Learning Action Costs from Input Plans—0
BLADE: Benchmarking Language Model Agents for Data-Driven ScienceCode1
Physics-Aware Combinatorial Assembly Sequence Planning using Data-free Action MaskingCode0
Uncertainty Quantification of Surrogate Models using Conformal PredictionCode1
Importance Weighting Can Help Large Language Models Self-ImproveCode0
Data-driven Conditional Instrumental Variables for Debiasing Recommender Systems—0
Generating Automatically Print/Scan Textures for Morphing Attack Detection ApplicationsCode0
Anytime-Valid Inference for Double/Debiased Machine Learning of Causal Parameters—0
GraphSPNs: Sum-Product Networks Benefit From Canonical OrderingsCode0
Externally Valid Selection of Experimental Sites via the k-Median Problem—0
A Confidence Interval for the _2 Expected Calibration ErrorCode0
A Mechanistic Interpretation of Syllogistic Reasoning in Auto-Regressive Language Models—0
An Unsupervised Learning Framework Combined with Heuristics for the Maximum Minimal Cut ProblemCode0
Evaluating the Validity of Word-level Adversarial Attacks with Large Language ModelsCode0
QirK: Question Answering via Intermediate Representation on Knowledge Graphs—0
Defining and Measuring Disentanglement for non-Independent Factors of Variation—0
Design Proteins Using Large Language Models: Enhancements and Comparative AnalysesCode0
Approximating Discrimination Within Models When Faced With Several Non-Binary Sensitive AttributesCode0
People over trust AI-generated medical responses and view them to be as valid as doctors, despite low accuracy—0
Show:102550
← PrevPage 20 of 144Next →

No leaderboard results yet.