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
Latte: Latent Diffusion Transformer for Video Generation
Layer Collapse Can be Induced by Unstructured Pruning
LBMamba: Locally Bi-directional Mamba
LC-PLM: Long-context Protein Language Modeling Using Bidirectional Mamba with Shared Projection Layers
LeanProgress: Guiding Search for Neural Theorem Proving via Proof Progress Prediction
Learned-Database Systems Security
Learning Actionable Counterfactual Explanations in Large State Spaces
Learning Adaptive Multi-Stage Energy-based Prior for Hierarchical Generative Model
Learning and Transferring Physical Models through Derivatives
Learning Deformable Body Interactions With Adaptive Spatial Tokenization
Learning Energy-Based Generative Models via Potential Flow: A Variational Principle Approach to Probability Density Homotopy Matching
Learning Energy-Based Models by Self-Normalising the Likelihood
Learning Equivalence Classes of Bayesian Network Structures with GFlowNet
Learning Federated Neural Graph Databases for Answering Complex Queries from Distributed Knowledge Graphs
Learning few-step posterior samplers by unfolding and distillation of diffusion models
Learning from Online Videos at Inference Time for Computer-Use Agents
Learning in complex action spaces without policy gradients
Learning Lagrangian Interaction Dynamics with Sampling-Based Model Order Reduction
Learning Representations for Independence Testing
Learning Robust Representations for Visual Reinforcement Learning via Task-Relevant Mask Sampling
Learning Task-Aware Abstract Representations for Meta-Reinforcement Learning
Learning the Language of Protein Structure
Learning Time-Series Representations by Hierarchical Uniformity-Tolerance Latent Balancing
Learning to Be Cautious
Learning to Defer with an Uncertain Rejector via Conformal Prediction
Learning to Imitate with Less: Efficient Individual Behavior Modeling in Chess
Learning to Localize Leakage of Cryptographic Sensitive Variables
Learning to Prompt Your Domain for Federated Vision-Language Models
Learning to Rank with Top-$K$ Fairness
Learning to reconstruct from saturated data: audio declipping and high-dynamic range imaging
Learning Using a Single Forward Pass
LEGO-Learn: Label-Efficient Graph Open-Set Learning
Length independent generalization bounds for deep SSM architectures via Rademacher contraction and stability constraints
Lens: A Knowledge-Guided Foundation Model for Network Traffic
Leopard: A Vision Language Model for Text-Rich Multi- Image Tasks
Let's Roll a BiFTA: Bi-refinement for Fine-grained Text-visual Alignment in Vision-Language Models
Let Your Light Shine: Foreground Portrait Matting via Deep Flash Priors
Leveraging a Simulator for Learning Causal Representations from Post-Treatment Covariates for CATE
Leveraging AutoML for Sustainable Deep Learning: A Multi- Objective HPO Approach on Deep Shift Neural Networks
Leveraging Fully-Observable Solutions for Improved Partially-Observable Offline Reinforcement Learning
Leveraging Gradients for Unsupervised Accuracy Estimation under Distribution Shift
Leveraging Multimodal LLM Descriptions of Activity for Explainable Semi-Supervised Video Anomaly Detection
Leveraging Recursive Methods for Efficient Federated Learning
Leveraging the True Depth of LLMs
Lie Symmetry Net: Preserving Conservation Laws in Modelling Financial Market Dynamics via Differential Equations
Lifelong Learning in StyleGAN through Latent Subspaces
LightTransfer: Your Long-Context LLM is Secretly a Hybrid Model with Effortless Adaptation
Linear Convergence of Decentralized FedAvg for PL Objectives: The Interpolation Regime
LiSeCo: Linear Semantic Control for Language Generation
LitLLMs, LLMs for Literature Review: Are we there yet?

« prev Page 16/30 next »