Multi-Task Ranking papers, 2023–2026

Key findings

• Multi-Task Ranking went from 252 papers in 2023 to 480 in 2026, roughly 1.9x in three years.
• NeurIPS publishes the most Multi-Task Ranking work: 485 papers from 2023 to 2026, 34% of the four-venue total.
• The fastest-growing overlap is with AI Agents: papers tagged with both rose from 8 in 2023 to 52 in 2026.
• Among the 5 topics under Recommenders and Ads, it ranks #1 by 2026 paper count; the fastest grower in the group, Click-Through Prediction, is up 2.6x versus 1.9x here.

Representative papers

Spread across years and venues so every edition shows up

• NeurIPS 2026A Mahalanobis Margin \texorpdfstring{$\gamma_{\min}$}{gamma\_min} Bound on Task Confusion in Pretrained Class-Incremental Learning: From Infeasibility to Exponential Attenuation
• ICML 2026Adaptive Personalized Federated Learning via Multi-task Averaging of Kernel Mean Embeddings
• ICLR 2026Automatic Stage Lighting Control: Is it a Rule-Driven Process or Generative Task?
• CVPR 2026A Supervised Multi-task Framework for Joint cryo-ET Restoration Enabled by
• NeurIPS 2025A High-Dimensional Statistical Method for Optimizing Transfer Quantities in Multi-Source Transfer Learning
• ICML 2025ATA: Adaptive Task Allocation for Efficient Resource Management in Distributed Machine Learning
• ICLR 2025Balanced Ranking with Relative Centrality: A multi-core periphery perspective
• CVPR 2025ACAttack: Adaptive Cross Attacking RGB-T Tracker via Multi-Modal Response Decoupling
• NeurIPS 2024CoMix: A Comprehensive Benchmark for Multi-Task Comic Understanding
• ICML 2024Bayesian Uncertainty for Gradient Aggregation in Multi-Task Learning
• ICLR 2024Order-Preserving GFlowNets
• CVPR 2024Domain Separation Graph Neural Networks for Saliency Object Ranking
• NeurIPS 2023AbdomenAtlas-8K: Annotating 8,000 CT Volumes for Multi-Organ Segmentation in Three Weeks
• ICML 2023Hypervolume Knowledge Gradient: A Lookahead Approach for Multi-Objective Bayesian Optimization with Partial Information
• ICLR 2023An Extensible Multi-modal Multi-task Object Dataset with Materials
• CVPR 2023AMT: All-Pairs Multi-Field Transforms for Efficient Frame Interpolation
• NeurIPS 2026A Scalable Multi-Task Model for Virtual Sensors
• ICML 2026Alleviating Observation Bias via Causal-Invariant Meta-Learning for Unbalanced Incomplete Multi-view Clustering
• ICLR 2026Dataless Weight Disentanglement in Task Arithmetic via Kronecker-Factored Approximate Curvature
• CVPR 2026Block-Sparse Global Attention for Efficient Multi-View Geometry Transformers

All Multi-Task Ranking papers

250 papers, page 3 of 5

101. ICLR 2025GlycanML: A Multi-Task and Multi-Structure Benchmark for Glycan Machine Learning
102. ICLR 2025HMoRA: Making LLMs More Effective with Hierarchical Mixture of LoRA Experts
103. ICLR 2025Holographic Node Representations: Pre-training Task-Agnostic Node Embeddings
104. ICLR 2025How to Find the Exact Pareto Front for Multi-Objective MDPs?
105. ICLR 2025ILLUSION: Unveiling Truth with a Comprehensive Multi-Modal, Multi-Lingual Deepfake Dataset
106. ICLR 2025InstantPortrait: One-Step Portrait Editing via Diffusion Multi-Objective Distillation
107. ICLR 2025It Helps to Take a Second Opinion: Teaching Smaller LLMs To Deliberate Mutually via Selective Rationale Optimisation
108. ICLR 2025Joint Gradient Balancing for Data Ordering in Finite-Sum Multi-Objective Optimization
109. ICLR 2025Learned Reference-based Diffusion Sampler for multi-modal distributions
110. ICLR 2025Learning Diagrams: A Graphical Language for Compositional Training Regimes
111. ICLR 2025Learning Multi-Index Models with Neural Networks via Mean-Field Langevin Dynamics
112. ICLR 2025Learning to Help in Multi-Class Settings
113. ICLR 2025Leveraging Submodule Linearity Enhances Task Arithmetic Performance in LLMs
114. ICLR 2025Leveraging Variable Sparsity to Refine Pareto Stationarity in Multi-Objective Optimization
115. ICLR 2025LiveXiv - A Multi-Modal live benchmark based on Arxiv papers content
116. ICLR 2025Many-Objective Multi-Solution Transport
117. ICLR 2025MAP: Low-compute Model Merging with Amortized Pareto Fronts via Quadratic Approximation
118. ICLR 2025MAP: Multi-Human-Value Alignment Palette
119. ICLR 2025Mastering Task Arithmetic: $\tau$Jp as a Key Indicator for Weight Disentanglement
120. ICLR 2025MGDA Converges under Generalized Smoothness, Provably
121. ICLR 2025Mitigating Parameter Interference in Model Merging via Sharpness-Aware Fine-Tuning
122. ICLR 2025Mitigating the Backdoor Effect for Multi-Task Model Merging via Safety-Aware Subspace
123. ICLR 2025MolSpectra: Pre-training 3D Molecular Representation with Multi-modal Energy Spectra
124. ICLR 2025MQuAKE-Remastered: Multi-Hop Knowledge Editing Can Only Be Advanced with Reliable Evaluations
125. ICLR 2025Multi-Dimensional Conformal Prediction
126. ICLR 2025Multi-Label Node Classification with Label Influence Propagation
127. ICLR 2025Multi-objective Differentiable Neural Architecture Search
128. ICLR 2025Multi-session, multi-task neural decoding from distinct cell-types and brain regions
129. ICLR 2025Multi-Task Dense Predictions via Unleashing the Power of Diffusion
130. ICLR 2025Neural Multi-Objective Combinatorial Optimization via Graph-Image Multimodal Fusion
131. ICLR 2025NeuroLM: A Universal Multi-task Foundation Model for Bridging the Gap between Language and EEG Signals
132. ICLR 2025OBI-Bench: Can LMMs Aid in Study of Ancient Script on Oracle Bones?
133. ICLR 2025On Generalization Across Environments In Multi-Objective Reinforcement Learning
134. ICLR 2025Optimized Multi-Token Joint Decoding With Auxiliary Model for LLM Inference
135. ICLR 2025Pareto Low-Rank Adapters: Efficient Multi-Task Learning with Preferences
136. ICLR 2025ParetoFlow: Guided Flows in Multi-Objective Optimization
137. ICLR 2025Perm: A Parametric Representation for Multi-Style 3D Hair Modeling
138. ICLR 2025QMP: Q-switch Mixture of Policies for Multi-Task Behavior Sharing
139. ICLR 2025Redefining the task of Bioactivity Prediction
140. ICLR 2025Rethinking Neural Multi-Objective Combinatorial Optimization via Neat Weight Embedding
141. ICLR 2025Reward Dimension Reduction for Scalable Multi-Objective Reinforcement Learning
142. ICLR 2025Selective Task Group Updates for Multi-Task Optimization
143. ICLR 2025STAFF: Speculative Coreset Selection for Task-Specific Fine-tuning
144. ICLR 2025Swiss Army Knife: Synergizing Biases in Knowledge from Vision Foundation Models for Multi-Task Learning
145. ICLR 2025Task Descriptors Help Transformers Learn Linear Models In-Context
146. ICLR 2025Task-Adaptive Pretrained Language Models via Clustered-Importance Sampling
147. ICLR 2025TaskGalaxy: Scaling Multi-modal Instruction Fine-tuning with Tens of Thousands Vision Task Types
148. ICLR 2025Tool-Planner: Task Planning with Clusters across Multiple Tools
149. ICLR 2025Towards Optimal Multi-draft Speculative Decoding
150. ICLR 2025Transformers Learn to Implement Multi-step Gradient Descent with Chain of Thought

FAQ

How many Multi-Task Ranking papers were published at NeurIPS, ICLR, ICML and CVPR from 2023 to 2026?

1,440 in total: 252 in 2023, 315 in 2024, 393 in 2025, 480 in 2026.

How many Multi-Task Ranking papers are at NeurIPS 2026?

NeurIPS 2026 has 175 Multi-Task Ranking papers, versus 144 the year before.

How many Multi-Task Ranking papers are at ICLR 2026?

ICLR 2026 has 79 Multi-Task Ranking papers, versus 75 the year before.

How many Multi-Task Ranking papers are at ICML 2026?

ICML 2026 has 107 Multi-Task Ranking papers, versus 80 the year before.

How many Multi-Task Ranking papers are at CVPR 2026?

CVPR 2026 has 119 Multi-Task Ranking papers, versus 94 the year before.

Which conference publishes the most Multi-Task Ranking papers?

NeurIPS, with 485 papers from 2023 to 2026.