mirror of
https://github.com/zoo-apps/papers.git
synced 2026-10-30 14:56:54 +00:00
97 lines
4.2 KiB
TeX
97 lines
4.2 KiB
TeX
\section*{Acknowledgments}
|
|
|
|
|
|
This work was supported by Zoo Labs Foundation (501(c)(3) non-profit) and Hanzo AI. We thank the Qwen team for open-sourcing Qwen3-Embedding-8B, Tencent youtu-agent team for training-free GRPO, and the broader open-source AI community for tools and datasets enabling this research.
|
|
|
|
\begin{thebibliography}{99}
|
|
|
|
\bibitem{brown2020language}
|
|
Brown, T., et al. (2020). Language models are few-shot learners. \textit{NeurIPS}.
|
|
|
|
\bibitem{touvron2023llama}
|
|
Touvron, H., et al. (2023). LLaMA: Open and efficient foundation language models. \textit{arXiv:2302.13971}.
|
|
|
|
\bibitem{qwen2024qwen3}
|
|
Qwen Team. (2024). Qwen3 technical report. \textit{arXiv:2505.09388}.
|
|
|
|
\bibitem{zoo2025hllm}
|
|
Zoo Labs Foundation. (2025). HLLM: Hamiltonian Large Language Models for decentralized semantic optimization. \textit{Technical Report}.
|
|
|
|
\bibitem{tencent2025grpo}
|
|
Tencent youtu-agent Team. (2025). Training-Free Group Relative Policy Optimization. \textit{arXiv:2510.08191v1}.
|
|
|
|
\bibitem{mikolov2013word2vec}
|
|
Mikolov, T., et al. (2013). Efficient estimation of word representations in vector space. \textit{ICLR}.
|
|
|
|
\bibitem{muennighoff2023mteb}
|
|
Muennighoff, N., et al. (2023). MTEB: Massive text embedding benchmark. \textit{arXiv:2210.07316}.
|
|
|
|
\bibitem{xiao2024bge}
|
|
Xiao, S., et al. (2024). C-Pack: Packaged resources to advance general Chinese embedding. \textit{arXiv:2309.07597}.
|
|
|
|
\bibitem{wang2024e5}
|
|
Wang, L., et al. (2024). Text embeddings by weakly-supervised contrastive pre-training. \textit{arXiv:2212.03533}.
|
|
|
|
\bibitem{qwen2024embedding}
|
|
Qwen Team. (2024). Qwen3-Embedding technical report. \textit{arXiv:2506.05176}.
|
|
|
|
\bibitem{mcmahan2017federated}
|
|
McMahan, B., et al. (2017). Communication-efficient learning of deep networks from decentralized data. \textit{AISTATS}.
|
|
|
|
\bibitem{gupta2018split}
|
|
Gupta, O., \& Raskar, R. (2018). Distributed learning of deep neural network over multiple agents. \textit{J. Network and Computer Applications}.
|
|
|
|
\bibitem{warnat2021swarm}
|
|
Warnat-Herresthal, S., et al. (2021). Swarm Learning for decentralized and confidential clinical machine learning. \textit{Nature}.
|
|
|
|
\bibitem{jegou2011pq}
|
|
Jégou, H., et al. (2011). Product quantization for nearest neighbor search. \textit{IEEE TPAMI}.
|
|
|
|
\bibitem{shen2015binary}
|
|
Shen, F., et al. (2015). Hashing on nonlinear manifolds. \textit{IEEE TIP}.
|
|
|
|
\bibitem{hanzo2025bitdelta}
|
|
Hanzo AI. (2025). BitDelta: Delta encoding for high-dimensional embeddings. \textit{Technical Report}.
|
|
|
|
\bibitem{blanchard2017krum}
|
|
Blanchard, P., et al. (2017). Machine learning with adversaries: Byzantine tolerant gradient descent. \textit{NeurIPS}.
|
|
|
|
\bibitem{yin2018median}
|
|
Yin, D., et al. (2018). Byzantine-robust distributed learning: Towards optimal statistical rates. \textit{ICML}.
|
|
|
|
\bibitem{yin2018trimmed}
|
|
Yin, D., et al. (2018). Defending against saddle point attack in Byzantine-robust distributed learning. \textit{ICML}.
|
|
|
|
\bibitem{nguyen2016msmarco}
|
|
Nguyen, T., et al. (2016). MS MARCO: A human generated machine reading comprehension dataset. \textit{arXiv:1611.09268}.
|
|
|
|
\bibitem{bowman2015snli}
|
|
Bowman, S. R., et al. (2015). A large annotated corpus for learning natural language inference. \textit{EMNLP}.
|
|
|
|
\bibitem{voorhees2020trec}
|
|
Voorhees, E., et al. (2020). TREC-COVID: Constructing a pandemic information retrieval test collection. \textit{arXiv:2005.04474}.
|
|
|
|
\bibitem{thakur2021beir}
|
|
Thakur, N., et al. (2021). BEIR: A heterogeneous benchmark for zero-shot evaluation of information retrieval models. \textit{arXiv:2104.08663}.
|
|
|
|
\bibitem{karpukhin2020dpr}
|
|
Karpukhin, V., et al. (2020). Dense passage retrieval for open-domain question answering. \textit{EMNLP}.
|
|
|
|
\bibitem{buterin2017casper}
|
|
Buterin, V., \& Griffith, V. (2017). Casper the Friendly Finality Gadget. \textit{arXiv:1710.09437}.
|
|
|
|
\bibitem{cohen2019certified}
|
|
Cohen, J., et al. (2019). Certified adversarial robustness via randomized smoothing. \textit{ICML}.
|
|
|
|
\bibitem{groth2016zk}
|
|
Groth, J. (2016). On the size of pairing-based non-interactive arguments. \textit{EUROCRYPT}.
|
|
|
|
\bibitem{gentry2009fhe}
|
|
Gentry, C. (2009). Fully homomorphic encryption using ideal lattices. \textit{STOC}.
|
|
|
|
\bibitem{abadi2016dp}
|
|
Abadi, M., et al. (2016). Deep learning with differential privacy. \textit{CCS}.
|
|
|
|
\end{thebibliography}
|
|
|