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
Stepwise Guided Policy Optimization: Coloring Your Incorrect Reasoning in GRPO
StethoLM: Audio Language Model for Cardiopulmonary Analysis Across Clinical Tasks
StFT: Spatio-temporal Fourier Transformer for Long-term Dynamics Prediction
STLDM: Spatio-Temporal Latent Diffusion Model for Precipitation Nowcasting
S-TLLR: STDP-inspired Temporal Local Learning Rule for Spiking Neural Networks
Stochastic Block Model-Aware Topological Neural Networks for Graph Link Prediction
Stochastic Multi-Objective Multi-Armed Bandits: Regret Definition and Algorithm
Stochastic Primal-Dual Double Block-Coordinate for Two- way Partial AUC Maximization
Stochastic Subspace Descent Accelerated via Bi-fidelity Line Search
Stochastic Variance-Reduced Newton: Accelerating Finite-Sum Minimization with Large Batches
Stop Overthinking: A Survey on Efficient Reasoning for Large Language Models
Streaming Heteroscedastic Probabilistic PCA with Missing Data
Streamlining Language Models via Semantic Basis Analysis
StructEval: Benchmarking LLMs' Capabilities to Generate Structural Outputs
Structural Causal Circuits: Probabilistic Circuits Climbing All Rungs of Pearl's Ladder of Causation
Structure is Supervision: Multiview Masked Autoencoders for Radiology
Studying memorization of large language models using answers to Stack Overflow questions
Sublinear Algorithms for Estimating Wasserstein and TV Distances: Applications to Fairness and Privacy Auditing
Subspace based Federated Unlearning
Successor Clusters: A Behavior Basis for Unsupervised Zero-Shot Reinforcement Learning
SuFP: Piecewise Bit Allocation Floating-Point for Robust Neural Network Quantization
Super-fast Rates of Convergence for Neural Network Classifiers under the Hard Margin Condition
Superposition as Lossy Compression — Measure with Sparse Autoencoders and Connect to Adversarial Vulnerability
SURFACEBENCH: A Geometry-Aware Benchmark for Symbolic Surface Discovery
Survey of Video Diffusion Models: Foundations, Implementations, and Applications
Synapse: Adaptive Arbitration of Complementary Expertise in Time Series Foundational Models
Synchrony-Gated Plasticity with Dopamine Modulation for Spiking Neural Networks
SynCode: LLM Generation with Grammar Augmentation
Synergistic Benefits of Joint Molecule Generation and Property Prediction
SyntheRela: A Benchmark For Synthetic Relational Database Generation
Synthesizing Minority Samples for Long-tailed Classification via Distribution Matching
Synthesizing world models for bilevel planning
System-2 Mathematical Reasoning via Enriched Instruction Tuning
System-Aware Neural ODE Processes for Few-Shot Bayesian Optimization
T$^3$-S2S: Training-free Triplet Tuning for Sketch to Scene Synthesis in Controllable Concept Art Generation
T2L: Efficient Zero-Shot Action Recognition with Temporal Token Learning
Tabby: A Language Model Architecture for Tabular and Structured Data Synthesis
Table Foundation Models: on knowledge pre-training for tabular learning
TabRep: Training Tabular Diffusion Models with a Simple and Effective Continuous Representation
Tackling Feature and Sample Heterogeneity in Decentralized Multi-Task Learning: A Sheaf-Theoretic Approach
Tackling the Abstraction and Reasoning Corpus with Vision Transformers: the Importance of 2D Representation, Positions, and Objects
TACO: Training-free Sound Prompted Segmentation via Semantically Constrained Audio-visual CO-factorization
TACO Vision Models Can Be Efficiently Specialized via Few-Shot Task-Aware Compression
TapWeight: Reweighting Pretraining Objectives for Task-Adaptive Pretraining
Targeted Unlearning Using Perturbed Sign Gradient Methods With Applications On Medical Images
Task-agnostic Prompt Compression with Context-aware Sentence Embedding and Reward-guided Task Descriptor
Task Arithmetic Through The Lens Of One-Shot Federated Learning
Task Diversity Shortens the In-Context Learning Plateau
Taxonomy, Opportunities, and Challenges of Representation Engineering for Large Language Models
Teaching Diffusion Models to Ground Alpha Matte

« prev Page 26/30 next »