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
Through the Judge's Eyes: Inferred Thinking Traces Improve Reliability of LLM Raters
TicketLLM: Next-Generation Sparse and Low-bit Transformers with Supermask-based Method
TimeAutoDiff: A Unified Framework for Generation, Imputation, Forecasting, and Time-Varying Metadata Conditioning of Heterogeneous Time Series Tabular Data
Time Series Domain Adaptation via Channel-Selective Representation Alignment
Time-Uniform Confidence Spheres for Means of Random Vectors
To Be Greedy, or Not to Be – That Is the Question for Population Based Training Variants
ToMoE: Converting Dense Large Language Models to Mixture-of-Experts through Dynamic Structural Pruning
Top-$k$ Feature Importance Ranking
Topological Inductive Bias fosters Multiple Instance Learning in Data-Scarce Scenarios
Toward Efficient Influence Function: Dropout as a Compression Tool
Toward Linearly Regularizing the Geometric Bottleneck of Linear Generalized Attention
Towards Better Understanding of In-Context Learning Ability from In-Context Uncertainty Quantification
Towards Customized Knowledge Distillation for Efficient Dense Image Predictions
Towards Efficient Contrastive PAC Learning
Towards Efficient Training of Graph Neural Networks: A Multiscale Approach
Towards Fast Safe Online Reinforcement Learning via Policy Finetuning
Towards Formalizing Spuriousness of Biased Datasets Using Partial Information Decomposition
Towards Generalized Certified Robustness with Multi-Norm Training
Towards Graph Foundation Models: A Study on the Generalization of Positional and Structural Encodings
Towards identifiability of micro total effects in summary causal graphs with latent confounding: extension of the front-door criterion
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 Multimodal Active Learning: Efficient Learning with Limited Paired Data
Towards Online Multimodal Social Interaction Understanding
Towards Robust Scale-Invariant Mutual Information Estimators
Towards Scalable Language-Image Pre-training for 3D Medical Imaging
Towards shutdownable agents via stochastic choice
Towards Undistillable Models by Minimizing Conditional Mutual Information
TP-Blend: Textual-Prompt Attention Pairing for Precise Object-Style Blending in Diffusion Models
TRA: Better Length Generalisation with Threshold Relative Attention
Tracking the Median of Gradients with a Stochastic Proximal Point Method
Tractable Representation Learning with Probabilistic Circuits
Training Dynamics of the Cooldown Stage in Warmup-Stable-Decay Learning Rate Scheduler
Training More Robust Classification Model via Discriminative Loss and Gaussian Noise Injection
Transfer Learning in ℓ1 Regularized Regression: Hyperparameter Selection Strategy based on Sharp Asymptotic Analysis
Transformers as Implicit State Estimators: In-Context Learning in Dynamical Systems
Transformers in the Dark: Navigating Unknown Search Spaces via Bandit Feedback
Transformers trained on proteins can learn to attend to Euclidean distance
TRecViT: A Recurrent Video Transformer
Tree Search for Language Model Agents
Tree Structure for the Categorical Wasserstein Weisfeiler-Lehman Graph Kernel
Triple Preference Optimization: Achieving Better Alignment using a Single Step Optimization
Trustworthy and Responsible AI for Human-Centric Autonomous Decision-Making Systems
TSkips: Efficiency Through Explicit Temporal Delay Connections in Spiking Neural Networks
TS-Reasoner: Domain-Oriented Time Series Inference Agents for Reasoning and Automated Analysis
Two Is Better Than One: Aligned Representation Pairs for Anomaly Detection
Two-Step Offline Preference-Based Reinforcement Learning on Explicitly Constrained Policies
UFO2: The Desktop AgentOS
UltraEdit: Training-, Subject-, and Memory-Free Lifelong Editing in Language Models
ULTra: Unveiling Latent Token Interpretability in Transformer-Based Understanding and Segmentation

« prev Page 28/30 next »