PulseAugur
EN
LIVE 10:24:55

New CoRA framework enables gradient-free on-device AI retrieval

By PulseAugur Editorial · [2 sources] ·

Researchers have developed a new gradient-free framework called Conditional Retrieval Alignment (CoRA) for on-device in-context learning. CoRA converts a frozen encoder into a task-conditioned retriever by aligning candidate input representations to an output-derived conditioning space. This method allows for effective retrieval without requiring retriever fine-tuning or backpropagation, and has been demonstrated on various textual and multimodal benchmarks using models like Llama 3.2 1B and Qwen3.5 2B, even on a Raspberry Pi 5. AI

IMPACT Enables more efficient and accessible on-device AI applications by reducing computational requirements for retrieval.

RANK_REASON The cluster contains an academic paper detailing a new framework for AI retrieval.

Read on arXiv cs.CL →

AI-generated summary · Google Gemini · from 2 sources. How we write summaries →

New CoRA framework enables gradient-free on-device AI retrieval

COVERAGE [2]

  1. arXiv cs.CL TIER_1 English(EN) · Xinyu Luo, Hui Liu, Yihua Shao, Junyi Yang, Arindam Basu, Haoliang Li ·

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

    arXiv:2607.27766v1 Announce Type: new Abstract: On-device in-context learning (ICL) relies on pre-inference retrieval to select demonstrations for useful context before downstream model inference. This retrieval must exploit task-specific information while operating over local me…

  2. arXiv cs.IR (Information Retrieval) TIER_1 English(EN) · Haoliang Li ·

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

    On-device in-context learning (ICL) relies on pre-inference retrieval to select demonstrations for useful context before downstream model inference. This retrieval must exploit task-specific information while operating over local memories under limited computation, memory, and da…

RELATED ENTITIES

RELATED TOPICS