Skip to content
conftrace_

Core Methods

51,083 papers (8 classified directly here)

Subtopics · a paper can sit in several, so these overlap

Representation Learning (22,308) Classification (15,497) Regression (5,281) Clustering (3,809) Embedding Learning (3,795) Metric Learning (2,938) Graph Neural Networks (1,211) Graphical Models (1,093) Feature Learning (891) Kernel Methods (795) Dimensionality Reduction (780) Interpretability (512) Feature Selection (511) Matrix Factorization (408) Ranking (315) Ensemble Methods (300) Support Vector Machine (295) Anomaly Detection (281) Sequence Modeling (244) Structured Prediction (237) Sequence Labeling (157) Topic Modeling (150) Sparse Coding (140) Matrix Completion (131) Neural Networks (114) Retrieval (105) Density Estimation (104) Estimation (83) Inference (56) Decision Tree (50) Feature Extraction (40) Model Selection (39) Prediction (35) Information Extraction (7)

Papers per year

4
51
357
966
4,853
5,823
2000
'5
'10
'15
'20
'25

Papers (including subtopics)

The Hyperfitting Phenomenon: Sharpening and Stabilizing LLMs for Open-Ended Text Generation ICLR 2025 The Illusion of Role Separation: Hidden Shortcuts in LLM Role Learning (and How to Fix Them) ICML 2025 The Knowledge Microscope: Features as Better Analytical Lenses than Neurons ACL 2025 The late-stage training dynamics of (stochastic) subgradient descent on homogeneous neural networks COLT 2025 The Learning Dynamics of Subword Segmentation for Morphologically Diverse Languages IJCNLP 2025 The LLM Already Knows: Estimating LLM-Perceived Question Difficulty via Hidden Representations EMNLP 2025 The Logical Implication Steering Method for Conditional Interventions on Transformer Generation ICML 2025 The Master Key Filters Hypothesis: Deep Filters Are General AAAI 2025 The Million Authors Corpus: A Cross-Lingual and Cross-Domain Wikipedia Dataset for Authorship Verification ACL 2025 The Missing Parts: Augmenting Fact Verification with Half Truth Detection EMNLP 2025 The Nature of NLP: Analyzing Contributions in NLP Papers ACL 2025 The Noisy Laplacian: a Threshold Phenomenon for Non-Linear Dimension Reduction ICML 2025 The Noisy Path from Source to Citation: Measuring How Scholars Engage with Past Research ACL 2025 The OMG dataset: An Open MetaGenomic corpus for mixed-modality genomic language modeling ICLR 2025 The Optimization Landscape of SGD Across the Feature Learning Strength ICLR 2025 Theoretical Limitations of Ensembles in the Age of Overparameterization ICML 2025 Theory-Inspired Deep Multi-View Multi-Label Learning with Incomplete Views and Noisy Labels CVPR 2025 The Practical Impacts of Theoretical Constructs on Empathy Modeling EMNLP 2025 The PRECOM-SM Corpus: Gambling in Spanish Social Media COLING 2025 The Price of Format: Diversity Collapse in LLMs EMNLP 2025 The Ranking Trick: A Simple and Robust Alternative to Score-Based Regression for AutoML AutoML 2025 The Reader is the Metric: How Textual Features and Reader Profiles Explain Conflicting Evaluations of AI Creative Writing ACL 2025 The Role of Abstract Representations and Observed Preferences in the Ordering of Binomials in Large Language Models ACL 2025 The Role of Sparsity for Length Generalization in LLMs ICML 2025 The Rotary Position Embedding May Cause Dimension Inefficiency in Attention Heads for Long-Distance Retrieval ACL 2025