Lattice AI Research

Research focus

Inference & Quantization (2)Scalable Oversight & Alignment Theory (1)Architecture Design (Transformers, SSMs, MoE) (1)Distributed Systems & Hardware (1)

Frequent co-authors

Hang Gu (2)Teng Wang (2)Wenqi Lou (2)Lei Gong (2)

Papers (2)

Aug 10, 2026

Thanks:2w ago

UnionSparse: An Index-Efficient Sparsity Framework for Low-Bit Sparse LLM Inference on Edge

UnionSparse achieves up to 3.46x faster low-bit sparse LLM inference on edge GPUs by optimizing metadata handling, challenging the status quo in model efficiency.

Tianhao Jiang, Hang Gu, Teng Wang +8

Inference & Quantization Scalable Oversight & Alignment Theory

Mar 2, 2026

Thanks:Mar 2, 2026·also OPPO, SYSU, USTC

Hermes: A Unified High-Performance NTT Architecture with Hybrid Dataflow

Forget slow NTTs: Hermes' hybrid dataflow architecture delivers up to 13.6x faster throughput for homomorphic encryption than GPUs.

Hang Gu, Teng Wang, Qianyu Cheng +5

Architecture Design (Transformers, SSMs, MoE)Distributed Systems & Hardware Inference & Quantization

Search

Qianyu Cheng

Publication activitypapers/week, last 8 weeks

Research focus

Frequent co-authors

Papers (2)