SARA: Selective and Adaptive Retrieval-augmented Generation with Context Compression
SARA is a unified RAG framework that balances local factual precision with global coverage by combining natural-language spans with compact semantic compression vectors, achieving consistent gains under strict context budgets.
Jul 1, 2026
UniSD: Towards a Unified Self-Distillation Framework for Large Language Models
UniSD unifies the fragmented landscape of self-distillation for large language models, providing a principled framework that supports systematic comparison and new combinations across data, representation, and decoding levels.
May 30, 2026
UniSD
A unified self-distillation framework for large language models that consolidates fragmented self-distillation directions into a single, modular formulation across data, representation, and decoding levels. Under review at NeurIPS 2026.
May 30, 2026
SARA
Selective and Adaptive Retrieval-augmented Generation with Context Compression. A unified RAG framework that combines fine-grained natural-language spans with compact semantic compression vectors under strict context budgets. Accepted at ACL 2026 main conference.
Mar 15, 2026
AgentArk: Distilling Multi-Agent Intelligence into a Single LLM Agent
AgentArk distills the collaborative behavior of multi-agent systems into a single LLM agent, decomposing trajectories into role-conditioned skills and recovering most of the ensemble's performance at a fraction of the cost.
Feb 4, 2026
Efficient Knowledge Probing of Large Language Models by Adapting Pre-trained Embeddings
An efficient approach to probing LLM knowledge that adapts pre-trained embeddings to query model knowledge with substantially reduced compute.
Feb 1, 2026
A Survey on Efficient LLM Training: From Data-centric Perspectives
A survey of efficient LLM training organized around data-centric techniques — selection, mixing, ordering, and synthesis — and their trade-offs with compute and downstream performance.
Jul 31, 2025