Gradient-free Task-Conditioned Retrieval for On-Device In-Context Learning

arXiv:2607.27766 · cs.CL, cs.IR, cs.LG · Submitted 2026-07-30 · Read on arXiv

Xinyu Luo, Hui Liu, Yihua Shao, Junyi Yang, Arindam Basu, Haoliang Li

cs.CL, cs.IR, cs.LG

Submitted: 2026-07-30

Comments: Under review

Code: https://github.com/openclaw/openclaw

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• In-Context Learning — 31× in this paper · explained in 7 episodes
• Benchmark — 17× in this paper · explained in 2 episodes
• Fine-Tuning — 9× in this paper · explained in 5 episodes
• Accuracy — 6× in this paper · explained in 1 episode
• Redundancy — 6× in this paper · explained in 2 episodes
• Transformer — 6× in this paper · explained in 2 episodes
• Papers — 5× in this paper · explained in 3 episodes
• Ablation — 4× in this paper · explained in 1 episode
• Calibration — 4× in this paper · explained in 9 episodes
• Cosine Similarity — 4× in this paper · explained in 3 episodes
• Embeddings — 4× in this paper · explained in 2 episodes
• Empirical Methods in Natural Language Processing — 4× in this paper
• In-Context Learning (ICL) — 3× in this paper · explained in 11 episodes
• Decoder — 2× in this paper · explained in 2 episodes
• Foundation Model — 2× in this paper · explained in 3 episodes
• Foundation Models — 2× in this paper · explained in 8 episodes
• Reconstruction Error — 2× in this paper · explained in 2 episodes
• Regularization — 2× in this paper · explained in 3 episodes
• Transformers — 2× in this paper · explained in 2 episodes
• Ablation Study — 1× in this paper · explained in 3 episodes
• Centered Kernel Alignment — 1× in this paper
• Centered Kernel Alignment (CKA) — 1× in this paper · explained in 3 episodes
• Composition — 1× in this paper · explained in 2 episodes
• Compositionality — 1× in this paper · explained in 2 episodes
• Cooperation — 1× in this paper · explained in 2 episodes
• Downstream Tasks — 1× in this paper · explained in 2 episodes
• Edge Devices — 1× in this paper · explained in 2 episodes
• Energy Efficiency — 1× in this paper · explained in 4 episodes
• Evaluation Protocol — 1× in this paper · explained in 2 episodes
• Failure Modes — 1× in this paper · explained in 3 episodes
• Few-Shot Learning — 1× in this paper · explained in 6 episodes
• Grounding — 1× in this paper · explained in 3 episodes
• Lightweight Adaptation — 1× in this paper · explained in 2 episodes
• Linear Centered Kernel Alignment (CKA) — 1× in this paper · explained in 2 episodes
• Model-Agnostic — 1× in this paper · explained in 2 episodes
• Point Clouds — 1× in this paper · explained in 2 episodes
• Prompt Engineering — 1× in this paper · explained in 6 episodes
• Pseudo-labeling — 1× in this paper · explained in 3 episodes
• Resource Constraints — 1× in this paper · explained in 5 episodes
• Transferability — 1× in this paper · explained in 5 episodes
• Transformer Model — 1× in this paper · explained in 2 episodes
• Transformer Models — 1× in this paper · explained in 3 episodes
• Vision-language models — 1× in this paper · explained in 2 episodes
• Visual Grounding — 1× in this paper · explained in 2 episodes

Sources

• OpenFlamingo: An Open-Source Framework for Training Large Autoregressive Vision-Language Models
• Microsoft COCO Captions: Data Collection and Evaluation Server
• The Llama 3 Herd of Models
• MobileLLM-Pro Technical Report
• A Unified Model and Document Representation for On-Device Retrieval-Augmented Generation
• Universal Text Representation from BERT: An Empirical Study
• Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation Models

Related papers

• Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
• Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
• Subliminal Steering: Stronger Encoding of Hidden Signals
• MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
• The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
• Untangling the Mechanisms of Misleading Context in Medical Question Answering