← Optimization & Theory
Machine Learning › Optimization & Theory ›

Theory

4950 directly classified papers

Papers per year

Papers

A Regex Minimization Benchmark: A PSPACE-Complete Challenge for Language Models EACL 2026
Angular Gradient Sign Method: Uncovering Vulnerabilities in Hyperbolic Networks AAAI 2026
BOP-Distrib: Revisiting 6D Pose Estimation Benchmarks for Better Evaluation under Visual Ambiguities WACV 2026
Rethinking Hallucinations: Correctness, Consistency, and Prompt Multiplicity EACL 2026
FLUKE: A Linguistically-Driven and Task-Agnostic Framework for Robustness Evaluation EACL 2026
Rethinking Saliency Maps: A Cognitive Human Aligned Taxonomy and Evaluation Framework for Explanations AAAI 2026
3D Cell Oversegmentation Correction via Geo-Wasserstein Divergence WACV 2026
Quantifying the Limits of Segmentation Foundation Models: Modeling Challenges in Segmenting Tree-Like and Low-Contrast Objects WACV 2026
TRACE: A Framework for Analyzing and Enhancing Stepwise Reasoning in Vision-Language Models EACL 2026
Speculative Decoding Speed-of-Light: Optimal Lower Bounds via Branching Random Walks EACL 2026
Balanced Accuracy: The Right Metric for Evaluating LLM Judges - Explained through Youden’s J statistic EACL 2026
Garbage In, Reasoning Out? Why Benchmark Scores are Unreliable and What to Do About It EACL 2026
Barriers to Discrete Reasoning with Transformers: A Survey Across Depth, Exactness, and Bandwidth EACL 2026
Transferable Hypergraph Attack via Injecting Nodes into Pivotal Hyperedges AAAI 2026
Locally Explaining Prediction Behavior via Gradual Interventions and Measuring Property Gradients WACV 2026
DoTA: Latent Distribution Conditioned Data Attribution for Diffusion Models WACV 2026
FAIR-SIGHT: Fairness Assurance in Image Recognition via Simultaneous Conformal Thresholding and Dynamic Output Repair WACV 2026
Evaluating Text-to-Image and Text-to-Video Synthesis with a Conditional Frechet Distance WACV 2026
CaFlow: Enhancing Long-Term Action Quality Assessment with Causal Counterfactual Flow WACV 2026
ExAnte: A Benchmark for Ex-Ante Inference in Large Language Models EACL 2026
Validating Automatic Evaluation of Controllable Counterspeech Generation: Rankings Matter More Than Scores EACL 2026
Tracking the Limits of Knowledge Propagation: How LLMs Fail at Multi-Step Reasoning with Conflicting Knowledge EACL 2026
Detecting Overflow in Compressed Token Representations for Retrieval-Augmented Generation EACL 2026
SymPyBench: A Dynamic Benchmark for Scientific Reasoning with Executable Python Code EACL 2026
CertMask: Certifiable Defense Against Adversarial Patches via Theoretically Optimal Mask Coverage AAAI 2026