Multi-Task Learning papers, 2023–2026

Key findings

• Multi-Task Learning went from 288 papers in 2023 to 402 in 2026, roughly 1.4x in three years.
• NeurIPS publishes the most Multi-Task Learning work: 399 papers from 2023 to 2026, 34% of the four-venue total.
• The fastest-growing overlap is with Datasets and Benchmarks: papers tagged with both rose from 6 in 2023 to 16 in 2026.
• Among the 5 topics under Meta-Learning and Transfer, it ranks #2 by 2026 paper count; the fastest grower in the group, Foundation Model Adaptation, is up 3.8x versus 1.4x 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 2026A Systematic Study of Behavioral Cloning for Scientific Data Annotation
• ICLR 2026Automatic Stage Lighting Control: Is it a Rule-Driven Process or Generative Task?
• CVPR 20263D-Aware Multi-Task Learning with Cross-View Correlations for Dense Scene Understanding
• 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 2025CodeMMLU: A Multi-Task Benchmark for Assessing Code Understanding & Reasoning Capabilities of CodeLLMs
• 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 2024Class Incremental Learning via Likelihood Ratio Based Task Prediction
• CVPR 2024Differentiable Information Bottleneck for Deterministic Multi-view Clustering
• NeurIPS 2023A Spectral Algorithm for List-Decodable Covariance Estimation in Relative Frobenius Norm
• ICML 2023A Conditional Normalizing Flow for Accelerated Multi-Coil MR Imaging
• 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 2026Beyond Hearing: Learning Task-agnostic ExG Representations from Earphones via Physiology-informed Tokenization
• CVPR 2026Any Resolution Any Geometry From Multi-View To Multi-Patch

All Multi-Task Learning papers

402 papers, page 6 of 9

251. ICML 2026Orthogonal Model Merging
252. ICML 2026Personalized Additive Modeling for Multi-level Federated Learning
253. ICML 2026Post-Hoc Merging is Not Enough: Many-Shot Model Merging with Loss-Gap Balancing
254. ICML 2026Predicting evolutionary rate as a pretraining task improves genome language model representations
255. ICML 2026Probabilistic Performance Guarantees for Multi-Task Reinforcement Learning
256. ICML 2026Problem Distributions as Tasks: Repurposing Meta Learning for Generative Combinatorial Optimization towards Multi-task Pretraining and Adaptation
257. ICML 2026Rethinking Human Intent-to-CAD: Parametric CAD Model Generation via Cooperative Multi-Task Alignment and Spatial-Aware Reinforcement Learning
258. ICML 2026Saliency-Aware Model Merging
259. ICML 2026Shared Lexical Task Representations Explain Behavioral Variability In LLMs
260. ICML 2026Sketch-Based Low-Rank Model Merging with Shared Circulant Transforms
261. ICML 2026Structured Expert Routing with Multi-View Task Priors for Offline Meta-Reinforcement Learning
262. ICML 2026Structured Multi-modal Graph Disentanglement for Psychiatric Diagnosis
263. ICML 2026SyMerge: From Non-Interference to Synergistic Merging via Single-Layer Adaptation
264. ICML 2026T-GINEE: A Tensor-Based Multi-Graph Representation Learning
265. ICML 2026TACTIC: Task-Aware Sparse Coordination Graphs for Multi-Task Multi-agent Reinforcement Learning
266. ICML 2026Task-Aware Exploration via a Predictive Bisimulation Metric
267. ICML 2026Task-Aware Structured Memory for Dynamic Multi-modal In-Context Learning
268. ICML 2026The Geometry of Updates: Fisher Alignment at Vocabulary Scale
269. ICML 2026TimeMRA: LLM-Empowered Time Series Forecasting via Multi-Scale Retrieval-Augmented Representations
270. ICML 2026Transformers learn factored representations
271. ICML 2026Transporting Task Vectors across Different Architectures without Training
272. ICML 2026Unifying Heterogeneous Multi-Modal Remote Sensing Detection Via Language-Pivoted Pretraining
273. ICML 2026WarmServe: Enabling One-for-Many GPU Prewarming for Multi-LLM Serving
274. ICML 2026Weaving in the Clouds: Achieving Synergistic Collaboration among LLM Agents via Federated Learning
275. ICML 2026What Linear Probes Miss: Multi-View Probing for Weight-Space Learning
276. ICML 2026When Shared Knowledge Hurts: Spectral Over-Accumulation in Model Merging
277. NeurIPS 2026A Black-Box Reduction from Regret to Multi-Level Coverage
278. NeurIPS 2026A Mahalanobis Margin \texorpdfstring{$\gamma_{\min}$}{gamma\_min} Bound on Task Confusion in Pretrained Class-Incremental Learning: From Infeasibility to Exponential Attenuation
279. NeurIPS 2026A Scalable Multi-Task Model for Virtual Sensors
280. NeurIPS 2026A Unified Graph Language Model for Multi-Domain Multi-Task Graph Alignment Instruction Tuning
281. NeurIPS 2026Adaptive LLM Routing for Multi-Turn Conversations with Continuously Evolving User Queries
282. NeurIPS 2026Adaptive Multi-view Graph Contrastive Learning via Fractional Continuous Dynamics
283. NeurIPS 2026AgentRoom: Concurrent Multi-Agent Coding in a CRDT-Backed Shared Workspace
284. NeurIPS 2026ArcMark: Distortion-Free Multi-Byte LLM Watermark via Optimal Transport
285. NeurIPS 2026ASTOR: Multi-Task Code Reinforcement Learning via Utility-Driven Coordination
286. NeurIPS 2026Attention Is More Than You Need: Spectral Redundancy in Multi-Head Routing
287. NeurIPS 2026BACE: Behavior-Adaptive Connectivity Estimation from Multi-Region Neural Recordings
288. NeurIPS 2026Balanced Multi-Task Learning from an Optimality-Gap Perspective
289. NeurIPS 2026Bandits via Additive Quantized Representations
290. NeurIPS 2026Benchmarking Open-Ended Multi-Agent Coordination in Language Agents
291. NeurIPS 2026BESS-Bench: Benchmarking Spectral Representations for Be-Star Variability
292. NeurIPS 2026Beyond FLOPs: Train-Full, Deploy-Partial Multi-Exit Inference via Selective Lightweight IC Ensemble
293. NeurIPS 2026Beyond Outcome: Trajectory-Driven Prompt Optimization via Multi-Dimensional Rewards
294. NeurIPS 2026Beyond Semantic Alignment: Geometric Incomparability in Multi-Oracle Soft Fusion
295. NeurIPS 2026Bilevel Optimization of Synthetic Trajectories for Multi-Turn LLM Fine-Tuning
296. NeurIPS 2026BitMTP: When Multi-Token Prediction Meets Low-Bit Large Language Models
297. NeurIPS 2026BrainCoT: A Multi-Task Zero-Shot Brain Signal Foundation Model with Neurometric-Anchored Chain-of-Thought Reasoning
298. NeurIPS 2026C3P: Contrastive promoter-protein pretraining yields representations capturing bacterial gene regulation
299. NeurIPS 2026Can Metadata Fix the Gauge? Calibration Turns Sparse Multi-Source Learning from Sparse PCA into Sparse Mean Recovery
300. NeurIPS 2026Causal Multi-Task Demand Learning

FAQ

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

1,181 in total: 288 in 2023, 227 in 2024, 264 in 2025, 402 in 2026.

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

NeurIPS 2026 has 126 Multi-Task Learning papers, versus 101 the year before.

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

ICLR 2026 has 57 Multi-Task Learning papers, versus 40 the year before.

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

ICML 2026 has 91 Multi-Task Learning papers, versus 47 the year before.

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

CVPR 2026 has 128 Multi-Task Learning papers, versus 76 the year before.

Which conference publishes the most Multi-Task Learning papers?

NeurIPS, with 399 papers from 2023 to 2026.