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

485 papers, page 4 of 10

151. NeurIPS 2026SpecBridge: Learning Natural-Language Formalization Plans for the Formal Specification Synthesis Task
152. NeurIPS 2026SpecHop: Continuous Speculation for Accelerating Multi-Hop Retrieval Agents
153. NeurIPS 2026Spectral-Spatial Interpretation
154. NeurIPS 2026Split the Differences, Pool the Rest: Provably Efficient Multi-Objective Imitation
155. NeurIPS 2026Standing on the Shoulders of Giants: Rethinking EEG Foundation Model Pretraining via Multi-Teacher Distillation
156. NeurIPS 2026STEP: Learning STructured Embeddings for Progressive Time Series
157. NeurIPS 2026Structurally Separated DAG Learning with Multi-Scale Normalized Closure
158. NeurIPS 2026Surface Recovery Is Not State Recovery: Pressure–Recovery–Relapse in Multi-turn LLMs
159. NeurIPS 2026Sustainability in the Loop: AI Model Development Should Be Multi-Objective
160. NeurIPS 2026SyncLight: Single-Edit Multi-View Relighting
161. NeurIPS 2026TAPIOCA: Why Task- Aware Pruning Improves OOD model Capability
162. NeurIPS 2026Task-Aware KV Cache Compression for LLM Agents via Utility-Driven Step Pruning
163. NeurIPS 2026The End Justifies the Mean: Linear Ranking Rules for Proportional Sequential Decisions
164. NeurIPS 2026TOPPO: Rethinking PPO for Multi-Task Reinforcement Learning with Critic Balancing
165. NeurIPS 2026Towards High Semantic Fidelity: Hyperdimensional Symbolic Messages in Multi-Agent Communication
166. NeurIPS 2026Train the Agent, Not the Expert: Learning to Harness Heterogeneous Experts for Multi-Turn Visual Reasoning
167. NeurIPS 2026Truthful Calibration Errors for Multi-Class Prediction
168. NeurIPS 2026U-MOF: Uncertainty-Guided Parameter-Efficient Multi-Objective Fine-Tuning for Long-Tailed Recognition
169. NeurIPS 2026UGM: Unified Multi-scale Genomic Event Modeling with Site-level Joint Prediction
170. NeurIPS 2026Unified Resource-Grounded Coordination Protocol for Orchestrator-Free Heterogeneous Multi-Agent Systems
171. NeurIPS 2026ViewSAM: Learning View-aware Semantics for Weakly Supervised Cross-view Referring Multi-Object Tracking
172. NeurIPS 2026Virtual Task Prompting for Multi-Task Scene Understanding
173. NeurIPS 2026When Attention Closes: How LLMs Lose the Thread in Multi-Turn Interaction
174. NeurIPS 2026When Does Non-Uniform Replay Matter in Reinforcement Learning?
175. NeurIPS 2026When Parallelism Pays Off: Cohesion-Aware Task Partitioning for Multi-Agent Coding
176. NeurIPS 2025A Data-Driven Prism: Multi-View Source Separation with Diffusion Model Priors
177. NeurIPS 2025A High-Dimensional Statistical Method for Optimizing Transfer Quantities in Multi-Source Transfer Learning
178. NeurIPS 2025A machine learning approach that beats Rubik's cubes
179. NeurIPS 2025A Minimalistic Unified Framework for Incremental Learning across Image Restoration Tasks
180. NeurIPS 2025A Multi-Task Benchmark for Abusive Language Detection in Low-Resource Settings
181. NeurIPS 2025AdaMSS: Adaptive Multi-Subspace Approach for Parameter-Efficient Fine-Tuning
182. NeurIPS 2025Adaptable Safe Policy Learning from Multi-task Data with Constraint Prioritized Decision Transformer
183. NeurIPS 2025Adversarial Graph Fusion for Incomplete Multi-view Semi-supervised Learning with Tensorial Imputation
184. NeurIPS 2025AGI-Elo: How Far Are We From Mastering A Task?
185. NeurIPS 2025Are Greedy Task Orderings Better Than Random in Continual Linear Regression?
186. NeurIPS 2025AutoData: A Multi-Agent System for Open Web Data Collection
187. NeurIPS 2025Beyond Single-Task: Robust Multi-Task Length Generalization for LLMs
188. NeurIPS 2025Bigger, Regularized, Categorical: High-Capacity Value Functions are Efficient Multi-Task Learners
189. NeurIPS 2025BioCLIP 2: Emergent Properties from Scaling Hierarchical Contrastive Learning
190. NeurIPS 2025Bit-swapping Oriented Twin-memory Multi-view Clustering in Lifelong Incomplete Scenarios
191. NeurIPS 2025Can Class-Priors Help Single-Positive Multi-Label Learning?
192. NeurIPS 2025Can Multi-Modal LLMs Provide Live Step-by-Step Task Guidance?
193. NeurIPS 2025Centralized Reward Agent for Knowledge Sharing and Transfer in Multi-Task Reinforcement Learning
194. NeurIPS 2025COLA: Towards Efficient Multi-Objective Reinforcement Learning with Conflict Objective Regularization in Latent Space
195. NeurIPS 2025ComRank: Ranking Loss for Multi-Label Complementary Label Learning
196. NeurIPS 2025Constrained Feedback Learning for Non-Stationary Multi-Armed Bandits
197. NeurIPS 2025Constructing an Optimal Behavior Basis for the Option Keyboard
198. NeurIPS 2025Continual Model Merging without Data: Dual Projections for Balancing Stability and Plasticity
199. NeurIPS 2025Continual Optimization with Symmetry Teleportation for Multi-Task Learning
200. NeurIPS 2025Contribution of task-irrelevant stimuli to drift of neural representations

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.