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
How does overparametrization affect performance on minority groups?
How far away are truly hyperparameter-free learning algorithms?
How iteration composition influences convergence and stability in deep learning
How Many Images Does It Take? Estimating Imitation Thresholds in Text-to-Image Models
How to Leverage Predictive Uncertainty Estimates for Reducing Catastrophic Forgetting in Online Continual Learning
How to Upscale Neural Networks with Scaling Law?
How Well Can Preference Optimization Generalize Under Noisy Feedback?
Hypergraph Neural Networks through the Lens of Message Passing: A Common Perspective to Homophily and Architecture Design
Hypergraphs as Weighted Directed Self-Looped Graphs: Spectral Properties, Clustering, Cheeger Inequality
Hyperparameters in Continual Learning: A Reality Check
HyperVQ: MLR-based Vector Quantization in Hyperbolic Space
Hypothesis-Driven Feature Manifold Analysis in LLMs via Supervised Multi-Dimensional Scaling
HyResPINNs: A Hybrid Residual Physics-Informed Neural Network Architecture Designed to Balance Expressiveness and Trainability
Identification of Average Outcome under Interventions in Confounded Additive Noise Models
Identifying Macro Causal Effects in a C-DMG over ADMGs
Illusion or Algorithm? Investigating Memorization, Emergence, and Symbolic Processing in In-Context Learning
Illustrated Landmark Graphs for Long-horizon Policy Learning
Implicit Bias and Fast Convergence Rates for Self-attention
(Implicit) Ensembles of Ensembles: Epistemic Uncertainty Collapse in Large Models
Importance Weighting for Aligning Language Models under Deployment Distribution Shift
Improved Localized Machine Unlearning Through the Lens of Memorization
Improving Adversarial Training for Two-player Competitive Games via Episodic Reward Engineering
Improving CLIP Counting Accuracy via Parameter-Efficient Fine-Tuning
Improving Consistency in Large Language Models through Chain of Guidance
Improving Detection of Watermarked Language Models
Improving Foundation Model Group Robustness with Auxiliary Sentence Embeddings
Improving GFlowNets for Text-to-Image Diffusion Alignment
Improving Local Explainability By Learning Causal Graphs From Data
Improving Single-round Active Adaptation: A Prediction Variability Perspective
Improving Visual Discriminability of CLIP for Training-Free Open-Vocabulary Semantic Segmentation
Incentive-Aware Synthetic Control: Accurate Counterfactual Estimation via Incentivized Exploration
In-context Learning for Mixture of Linear Regression: Existence, Generalization and Training Dynamics
In-context Learning in Presence of Spurious Correlations
Incorporating Interventional Independence Improves Robustness against Interventional Distribution Shift
Incorporating Spatial Information into Goal-Conditioned Hierarchical Reinforcement Learning via Graph Representations
IndicFake Meets SAFARI-LLM: Unifying Semantic and Acoustic Intelligence for Multilingual Deepfake Detection
In-distribution adversarial attacks on object recognition models using gradient-free search
Influential Bandits: Pulling an Arm May Change the Environment
Information Theoretic Guarantees For Policy Alignment In Large Language Models
Infrastructure for AI Agents
Inherently Robust Control through Maximum-Entropy Learning-Based Rollout
Initialization Matters: Unraveling the Impact of Pre-Training on Federated Learning
InkSight: Offline-to-Online Handwriting Conversion by Teaching Vision-Language Models to Read and Write
Integrating Large Language Models in Causal Discovery: A Statistical Causal Approach
Interactive Large Language Models for Reliable Answering under Incomplete Context
Interactive Task Planning with Language Models
Interpretable LLM-based Table Question Answering
Interpreting Kolmogorov-Arnold Networks in Neuroimaging: A Path-Based Attribution Framework
Interpreting Neurons in Deep Vision Networks with Language Models
Intra-Cluster Mixup: An Effective Data Augmentation Technique for Complementary-Label Learning

« prev Page 14/30 next »