TMLR 2025

1,499 papers

Top Research Directions

Research directions most represented by TMLR 2025 papers.

Shifting from Static Benchmarks to Dynamic Evaluation 16
Overcoming the Homophily Assumption in Graph Neural Networks 12
Over-Smoothing in Graph Neural Networks 10
Clean Accuracy Degradation in Machine Learning Defenses 10
Sample Efficient Reinforcement Learning 9
Accelerating Sparse Neural Networks on Dense Hardware 8
Distilling Large Model Capabilities via Synthetic Data 8
Preserving Model Utility During Machine Unlearning 8
The Non-Linear Function Approximation Gap in Reinforcement Learning 8
Model Calibration Under Distribution Shift 8
The Computational Overhead of Generative Data Synthesis 8
Overcoming the Iterative Inference Latency of Diffusion Models 8
Reducing the Memory and Latency of Language Model Inference 8
The Pareto Frontier of Algorithmic Accuracy and Fairness 7
Scaling Gaussian Processes Beyond Cubic Complexity 7

Top Authors

AuthorPapers
Kaushik Roy9
Heng Ji7
Caiming Xiong6
Stephen Casper6
Wenhu Chen6
Cihang Xie5
Ichiro Takeuchi5
Jan Peters5
Masashi Sugiyama5
Mohit Bansal5
Prathosh AP5
Tianbao Yang5
Ziwei Liu5
Ali Etemad4
Ameet Talwalkar4
Anton van den Hengel4
Bernard Ghanem4
Carola-Bibiane Schönlieb4
Chao Du4
Chaoyun Zhang4

Impactful Papers

Papers from TMLR 2025 that shaped research clusters.

Foundational

Influential

Papers

Title
UMP-Net: Uncertainty-Aware Mixture of Prompts Network for Efficient Instruction Tuning
Unbiased Loss Functions for Multilabel Classification with Missing Labels
Uncertainty-aware Evaluation of Auxiliary Anomalies with the Expected Anomaly Posterior
Uncertainty-Aware Surrogate-based Amortized Bayesian Inference for Computationally Expensive Models
Uncertainty Quantification in Retrieval Augmented Question Answering
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
Uncovering the Computational Roles of Nonlinearity in Sequence Modeling Using Almost-Linear RNNs
Uncovering the Redundancy in Transformers via a Unified Study of Layer Dropping
Understanding and Reducing the Class-Dependent Effects of Data Augmentation with A Two-Player Game Approach
Understanding and Robustifying Sub-domain Alignment for Domain Adaptation
Understanding Class Bias Amplification in Graph Representation Learning
Understanding Embedding Scaling in Collaborative Filtering
Understanding Emergent In-Context Learning from a Kernel Regression Perspective
Understanding Fine-tuning in Approximate Unlearning: A Theoretical Perspective
Understanding Guidance Scale in Diffusion Models from a Geometric Perspective
Understanding In-Context Learning of Linear Models in Transformers Through an Adversarial Lens
Understanding LLM Embeddings for Regression
Understanding Self-supervised Contrastive Learning through Supervised Objectives
Unifi3D: A Study on 3D Representations for Generation and Reconstruction in a Common Framework
Unified Preference Optimization: Language Model Alignment Beyond the Preference Frontier
Unified Risk Analysis for Weakly Supervised Learning
Unified Triplet-Level Hallucination Evaluation for Large Vision-Language Models
Unified Wisdom: Harnessing Collaborative Learning to Improve Efficacy of Knowledge Distillation
Uniform Noise Distribution and Compact Clusters: Unveiling the Success of Self-Supervised Learning in Label Noise
Unifying Linear-Time Attention via Latent Probabilistic Modelling
Unifying Self-Supervised Clustering and Energy-Based Models
Unifying VXAI: A Systematic Review and Framework for the Evaluation of Explainable AI
Universal Black-Box Targeted Reward Poisoning Attack Against Online Deep Reinforcement Learning
Universal Link Predictor By In-Context Learning on Graphs
UniZero: Generalized and Efficient Planning with Scalable Latent World Models
Unlearning in Diffusion models under Data Constraints: A Variational Inference Approach
Unlearning Misalignment for Personalized LLM Adaptation via Instance-Response-Dependent Discrepancies
Unlearning Personal Data from a Single Image
Unleashing the Power of Data Tsunami: A Comprehensive Survey on Data Assessment and Selection for Instruction Tuning of Language Models
Unlocking [CLS] Features for Continual Post-Training
Unlocking the matrix form of the Quaternion Fourier Transform and Quaternion Convolution: Properties, connections, and application to Lipschitz constant bounding
Unlocking Visual Secrets: Inverting Features with Diffusion Priors for Image Reconstruction
Unmasking Trees for Tabular Data
Unrealized Expectations: Comparing AI Methods vs Classical Algorithms for Maximum Independent Set
Unreasonable effectiveness of LLM reasoning: a doubly cautionary tale of temporal question-answering
UnSTAR: Unlearning with Self-Taught Anti-Sample Reasoning for LLMs
Unsupervised Discovery of Object-Centric Neural Fields
Unsupervised Panoptic Interpretation of Latent Spaces in GANs Using Space-Filling Vector Quantization
Unveiling Multiple Descents in Unsupervised Autoencoders
Using representation balancing to learn conditional-average dose responses from clustered data
Variance Dichotomy in Feature Spaces of Facial Recognition Systems is a Weak Defense against Simple Weight Manipulation Attacks
Variance Reduced Smoothed Functional REINFORCE Policy Gradient Algorithms
Variance Reduction of Stochastic Hypergradient Estimation by Mixed Fixed-Point Iteration
Variational Neural Stochastic Differential Equations with Change Points

« prev Page 29/30 next »