TMLR 2024

1,177 papers

Top Research Directions

Research directions most represented by TMLR 2024 papers.

Over-Smoothing in Graph Neural Networks 11
Overcoming the Homophily Assumption in Graph Neural Networks 10
Bypassing the Computational Bottleneck of Adversarial Training 10
Calibrating Uncertainty in Deep Neural Networks 9
Over-Squashing in Graph Neural Networks 8
Navigating Non-Convex Loss Landscapes in Deep Learning 7
The Non-Linear Function Approximation Gap in Reinforcement Learning 7
Overcoming the Iterative Inference Latency of Diffusion Models 7
Selective Prediction and Abstention Mechanisms 6
The Weisfeiler Lehman Expressivity Bottleneck 6
Scaling Causal Graph Discovery to High Dimensions 6
Shifting from Static Benchmarks to Dynamic Evaluation 6
Clean Accuracy Degradation in Machine Learning Defenses 6
Scaling Optimal Transport via One-Dimensional Projections 5
Mitigating Gradient Variance in Policy Optimization 5

Top Authors

AuthorPapers
Carola-Bibiane Schönlieb9
Kaushik Roy8
Mohit Bansal8
Cihang Xie7
Angelica I Aviles-Rivero6
Wenhu Chen6
Han Zhao5
Jean Honorio5
Mark Coates5
Mathieu Salzmann5
Percy Liang5
Philip Torr5
Sayash Kapoor5
Yoshua Bengio5
Bingchen Zhao4
Christopher Pal4
Daniel Rueckert4
Faez Ahmed4
Georgios Kaissis4
Giovanni Montana4

Impactful Papers

Papers from TMLR 2024 that shaped research clusters.

Foundational

Influential

Papers

Title
To Transfer or Not to Transfer: Suppressing Concepts from Source Representations
Toward a Complete Criterion for Value of Information in Insoluble Decision Problems
Towards Backwards-Compatible Data with Confounded Domain Adaptation
Towards Cross-Tokenizer Distillation: the Universal Logit Distillation Loss for LLMs
Towards Efficient Mixture of Experts: A Holistic Study of Compression Techniques
Towards Empirical Interpretation of Internal Circuits and Properties in Grokked Transformers on Modular Polynomials
Towards fully covariant machine learning
Towards generalizing deep-audio fake detection networks
Towards Graph Foundation Models: A Study on the Generalization of Positional and Structural Encodings
Towards LifeSpan Cognitive Systems
Towards Measuring Predictability: To which extent data-driven approaches can extract deterministic relations from data exemplified with time series prediction and classification
Towards Minimal Targeted Updates of Language Models with Targeted Negative Training
Towards Provable Log Density Policy Gradient
Towards Size-Independent Generalization Bounds for Deep Operator Nets
Towards Truly Zero-shot Compositional Visual Reasoning with LLMs as Programmers
Towards Trustworthy Reranking: A Simple yet Effective Abstention Mechanism
Towards Unbiased Calibration using Meta-Regularization
Towards Understanding Adversarial Transferability in Federated Learning
Towards Understanding Dual BN In Hybrid Adversarial Training
Towards Understanding Variants of Invariant Risk Minimization through the Lens of Calibration
Training-free Graph Neural Networks and the Power of Labels as Features
Training-free linear image inverses via flows
Training Graph Neural Networks Subject to a Tight Lipschitz Constraint
Training LLMs over Neurally Compressed Text
Transfer Learning for Bayesian Optimization on Heterogeneous Search Spaces
Transfer Learning for High-dimensional Quantile Regression with Statistical Guarantee
Transfer Learning in $\ell_1$ Regularized Regression: Hyperparameter Selection Strategy based on Sharp Asymptotic Analysis
Transfer Learning with Informative Priors: Simple Baselines Better than Previously Reported
Transformer Architecture Search for Improving Out-of-Domain Generalization in Machine Translation
Transformer-Based Models Are Not Yet Perfect At Learning to Emulate Structural Recursion
Transformers as Implicit State Estimators: In-Context Learning in Dynamical Systems
Transformers in Uniform TC$^0$
TRecViT: A Recurrent Video Transformer
Tree Ensembles for Contextual Bandits
Trusted Aggregation (TAG): Backdoor Defense in Federated Learning
Tweedie Moment Projected Diffusions for Inverse Problems
Two Failures of Self-Consistency in the Multi-Step Reasoning of LLMs
Uncertainty-aware Evaluation of Auxiliary Anomalies with the Expected Anomaly Posterior
Uncertainty in Graph Neural Networks: A Survey
Uncertainty Representations in State-Space Layers for Deep Reinforcement Learning under Partial Observability
Uncovering Strong Lottery Tickets in Graph Transformers: A Path to Memory Efficient and Robust Graph Learning
Understanding and Improving Transfer Learning of Deep Models via Neural Collapse
Understanding Fairness Surrogate Functions in Algorithmic Fairness
Understanding LLM Embeddings for Regression
Understanding Sparse Neural Networks from their Topology via Multipartite Graph Representations
Understanding the Role of Invariance in Transfer Learning
Understanding the Role of Layer Normalization in Label-Skewed Federated Learning
UniCtrl: Improving the Spatiotemporal Consistency of Text-to-Video Diffusion Models via Training-Free Unified Attention Control
Unified Convergence Theory of Stochastic and Variance-Reduced Cubic Newton Methods
Unified Risk Analysis for Weakly Supervised Learning

« prev Page 22/24 next »