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
Simple Calibration via Geodesic Kernels
Simplifying Knowledge Transfer in Pretrained Models
Single-loop Algorithms for Stochastic Non-Convex Optimization with Weakly-Convex Constraints
Single-pass Detection of Jailbreaking Input in Large Language Models
Single-positive Multi-label Learning with Label Cardinality
SIRE: SE(3) Intrinsic Rigidity Embeddings
SKADA-Bench: Benchmarking Unsupervised Domain Adaptation Methods with Realistic Validation On Diverse Modalities
Slicing the Gaussian Mixture Wasserstein Distance
Slicing Unbalanced Optimal Transport
SL-S4Wave: Self-Supervised Learning of Physiological Waveforms with Structured State Space Models
SMILE: A Composite Lexical-Semantic Metric for Question-Answering Evaluation
SmoothLLM: Defending Large Language Models Against Jailbreaking Attacks
SocialFusion: Addressing Social Degradation in Pre-trained Vision-Language Models
Socrates Loss: Unifying Confidence Calibration and Classification by Leveraging the Unknown
Solution Augmentation for ARC Problems Using GFlowNet: A Probabilistic Exploration Approach
Solving Inverse Problems using Diffusion with Iterative Colored Renoising
Solving Multi-agent Path Finding as an LLM Benchmark: How, How Good and Why
Solving Quadratic Programs via Deep Unrolled Douglas-Rachford Splitting
Solving the Cold Start Problem on One's Own as an End User via Preference Transfer
SoundnessBench: A Soundness Benchmark for Neural Network Verifiers
Spaced Scheduling for Large Language Model Training
SPARC: Concept-Aligned Sparse Autoencoders for Cross-Model and Cross-Modal Interpretability
Sparse Decomposition of Graph Neural Networks
SparseDiff: Sparse Discrete Diffusion for Scalable Graph Generation
Sparse, Efficient and Explainable Data Attribution with DualXDA
Sparse Neural Architectures via Deterministic Ramanujan Graphs
Sparser, Better, Faster, Stronger: Sparsity Detection for Efficient Automatic Differentiation
Sparsified State-Space Models are Efficient Highway Networks
Sparsity-Driven Plasticity in Multi-Task Reinforcement Learning
Sparsity regularization via tree-structured environments for disentangled representations
Spatio-temporal Partial Sensing Forecast of Long-term Traffic
Spectral Clustering and Labeling for Crowdsourcing with Inherently Distinct Task Types
SPFormer: Enhancing Vision Transformer with Superpixel Representation
SpidR: Learning Fast and Stable Linguistic Units for Spoken Language Models Without Supervision
SpikingBrain: Spiking Brain-inspired Large Models
SpikingMamba: Towards Energy-Efficient Large Language Models via Knowledge Distillation from Mamba
Spurious Privacy Leakage in Neural Networks
SR-Reward: Taking The Path More Traveled
SSFL: Discovering Sparse Unified Subnetworks at Initialization for Efficient Federated Learning
Stability-Aware Training of Machine Learning Force Fields with Differentiable Boltzmann Estimators
Stabilizing black-box model selection with the inflated argmax
Stacking Variational Bayesian Monte Carlo
State-Constrained Offline Reinforcement Learning
State space models can express n-gram languages
Statistical Error Bounds for GANs with Nonlinear Objective Functionals
Statistical Guarantees for Approximate Stationary Points of Shallow Neural Networks
Statistical Inference for Generative Model Comparison
Statistical Test for Saliency Maps of Graph Neural Networks via Selective Inference
Steering Dialogue Dynamics for Robustness against Multi-turn Jailbreaking Attacks
Steering Large Reasoning Models towards Concise Reasoning via Flow Matching

« prev Page 25/30 next »