DRATS derives a minimax objective from a feasibility formulation of MTRL to adaptively sample tasks with the largest return gaps, leading to better worst-task performance on MetaWorld benchmarks.
Online merging optimizers for boosting rewards and mitigating tax in alignment
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
roles
background 1polarities
background 1representative citing papers
The paper introduces a new taxonomy for model merging methods and reviews their applications in LLMs, MLLMs, continual learning, multi-task learning, and other subfields while outlining open challenges.
Qwen2.5 LLMs scale pre-training data to 18 trillion tokens and apply multistage reinforcement learning, achieving competitive performance on benchmarks with models up to 5 times larger.
citing papers explorer
-
Distributionally Robust Multi-Task Reinforcement Learning via Adaptive Task Sampling
DRATS derives a minimax objective from a feasibility formulation of MTRL to adaptively sample tasks with the largest return gaps, leading to better worst-task performance on MetaWorld benchmarks.
-
Model Merging in LLMs, MLLMs, and Beyond: Methods, Theories, Applications and Opportunities
The paper introduces a new taxonomy for model merging methods and reviews their applications in LLMs, MLLMs, continual learning, multi-task learning, and other subfields while outlining open challenges.
-
Qwen2.5 Technical Report
Qwen2.5 LLMs scale pre-training data to 18 trillion tokens and apply multistage reinforcement learning, achieving competitive performance on benchmarks with models up to 5 times larger.