arxivJul 23bullish

SUM: Unified Geometric Surgery on Spatio-Temporal Adaptation Vectors for Federated Class Incremental Learning

arXiv:2607.19384v1 Announce Type: new Abstract: Real-world intelligent systems often require both distributed collaboration across data-isolated clients and continual adaptation to evolving tasks. This setting naturally gives rise to Federated Class Incremental Learning (FCIL), which combines Federa

#federated-learning #continual-learning #multi-task-learning Read on arxiv →

arxivJun 26bullish

RecallRisk-BERT: A Multi-Task Framework for Post-Report Medical Device Recall Triage

arXiv:2606.27174v1 Announce Type: new Abstract: Medical device recalls are a critical regulatory mechanism for protecting patient safety. The growing volume of FDA recall records presents challenges in post-report recall triage, severity assessment, and root-cause interpretation. Existing studies mo

REMILI3 models #medical-device #recall-prediction #multi-task-learning Read on arxiv →

arxivJun 24bullish

PACT: Preserving Anchored Cores in Task-vectors for Model Merging

arXiv:2606.18627v3 Announce Type: replace Abstract: Model merging has emerged as a training-free alternative to multi-task learning, aiming to combine multiple task-specific fine-tuned models into a single multi-task model. Most existing model merging approaches follow the Task Arithmetic paradigm,

#model-merging #multi-task-learning #pre-trained-models Read on arxiv →

SUM: Unified Geometric Surgery on Spatio-Temporal Adaptation Vectors for Federated Class Incremental Learning

JL1-CC&QA: Extending the JL1-CD Benchmark with Change Captioning and Question Answering

RecallRisk-BERT: A Multi-Task Framework for Post-Report Medical Device Recall Triage

PACT: Preserving Anchored Cores in Task-vectors for Model Merging