20 results for “Meta-learning”
CS papers onlyHybrid search: Keyword + semantic, ranked by combined score.ⓘ
Want pure semantic search? Try claim verification →
This paper analyzes the poor performance of Meta-learning for Training-data Selection (MTS) and proposes that increasing the batch size and incorporating informative features can significantly improve…
The paper proposes a Bayesian meta-learner to accurately predict the distribution of Alzheimer's disease progression scores for individuals, outperforming existing methods, especially for long-term pr…
The paper introduces AutoHebb, a class of online learning feedforward neural networks that realize strong inductive biases and autonomously controlled learning.
The paper proposes a novel framework combining behavior-invariant task representation learning and a Transformer-based world model to achieve robust generalization in offline meta-reinforcement learni…
Xujun Li, Kehan Zheng, Mingyuan Zhao, Yize Geng +6 more
The paper proposes HiSME, a lightweight hierarchical skill meta-evolving solution that jointly optimizes skills and the skill evolving strategy by learning meta-skills from task execution traces, lead…
Cheng Qian, Kunlun Zhu, Beibin Li, Zhenhailong Wang +1 more
This paper studies how a Builder AI can learn to construct better environments for a Target AI model without changing its weights.
The paper proposes pretraining a Perceiver-style in-context learner on synthetic data to solve Multiple Instance Learning (MIL) tasks efficiently in the low-label regime.
This paper proposes a novel method called Skill-MAS that decouples experience retention from parametric updates to improve the performance of Large Language Model-based Multi-Agent Systems.
Aditya Kumar, Zhihan Lei, Jerry Yan, Joshua W. Momo +5 more
The paper proposes a modular agent framework and novel learning methods to design and optimize practical, cost-effective, and controllable LLM-based agentic systems.
Ali Najar, Hosein Hasani, Amir Kooshan Fattah, Yasamin Rajabi +1 more
This paper proposes Memory-Enhanced Test-Time Adaptation (METTA) for meta-reinforcement learning, which enables efficient adaptation to unseen tasks and task families.
Jian Yao, Zhiyao Zhang, Yichen Li, Xingyu Wu +1 more
This paper introduces Algorithm Modelization, a paradigm that turns iterative algorithms into trainable models.
This paper provides a mathematical framework for studying different policy learning problems and shows reductions between them.
Xinchen Zhang, Bowei Liu, Jiale Liu, Chufan Shi +6 more
The paper introduces OmniVerifier-M1, a multimodal meta-verifier that uses symbolic outputs and decoupled reinforcement learning to provide robust, fine-grained verification and error localization for…
Liad Erez, Fan Chen, Alon Cohen, Tomer Koren +3 more
The paper analyzes the sample complexity of contextual bandits in the $s$-sparse setting, achieving optimal sample bounds for identifying an $\epsilon$-optimal policy.
Anzhe Xie, Weihang Su, Yujia Zhou, Yiqun Liu +1 more
The paper introduces MetaSyn, a dataset of 442 expert-curated meta-analyses to evaluate the full retrieval-screening-synthesis pipeline of systematic scientific reasoning.
This paper introduces mean field reinforcement learning through Markov decision processes in large-population stochastic control, developing the necessary framework for representative-agent learning,…
This paper develops a policy-learning framework to optimally assign prediction tasks to multiple agents, considering individual agent expertise and capacity constraints, achieving systematic performan…
Junyuan Liu, Hongyue Lin, Jiale Hong, Yi Zhao +1 more
One clear sentence describing what this paper does
Develops a max-risk objective for active learning in multi-group mean estimation d-armed bandits and proves a lower bound for this objective.