#data-efficiency4 articles

4 articles

AIBullisharXiv – CS AI · 4h ago5

🧠

From Generator to Embedder: Harnessing Innate Abilities of Multimodal LLMs via Building Zero-Shot Discriminative Embedding Model

Researchers propose a data-efficient framework to convert generative Multimodal Large Language Models into universal embedding models without extensive pre-training. The method uses hierarchical embedding prompts and Self-aware Hard Negative Sampling to achieve competitive performance on embedding benchmarks using minimal training data.

AIBullisharXiv – CS AI · 4h ago4

🧠

Alignment through Meta-Weighted Online Sampling: Bridging the Gap between Data Generation and Preference Optimization

Researchers propose MetaAPO, a new framework for aligning large language models with human preferences that dynamically balances online and offline training data. The method uses a meta-learner to evaluate when on-policy sampling is beneficial, resulting in better performance while reducing online annotation costs by 42%.

AINeutralarXiv – CS AI · 4h ago0

🧠

Less is more -- the Dispatcher/ Executor principle for multi-task Reinforcement Learning

Researchers propose a dispatcher/executor principle for multi-task Reinforcement Learning that partitions controllers into task-understanding and device-specific components connected by a regularized communication channel. This structural approach aims to improve generalization and data efficiency as an alternative to simply scaling large neural networks with vast datasets.

AINeutralarXiv – CS AI · 4h ago0

🧠

Operator Learning with Domain Decomposition for Geometry Generalization in PDE Solving

Researchers propose a new framework called Operator Learning with Domain Decomposition to solve partial differential equations (PDEs) on arbitrary geometries using neural operators. The approach addresses data efficiency and geometry generalization challenges by breaking complex domains into smaller subdomains that can be solved locally and then combined into global solutions.