7 papers
CANN Bench: Benchmarking Agent Generated Kernels against Real NPU and Algorithmic Limits
Xue-Jian Gao, Deng Pan, Yueming Su +12
AI agents are now capable of writing, compiling, and iteratively optimizing low-level operator kernels on different hardware platforms. Existing benchmarks, however, focus almost e…
An Industrial-Scale Insurance LLM Achieving Verifiable Domain Mastery and Hallucination Control without Competence Trade-offs
Qian Zhu, Xinnan Guo, Jingjing Huo +5
Adapting Large Language Models (LLMs) to high-stakes vertical domains like insurance presents a significant challenge: scenarios demand strict adherence to complex regulations and…
Text-Preserving Lossy Text Compression: A Study of Strategic Deletion and LLM Reconstruction
Yuchun Zou, Junhong Tong, Jun Li
Traditional lossless text compression preserves every byte, but its gains on natural language are often modest in realistic operating regimes. We study \emph{lossy semantic text co…
Multi-Scale Dequant: Eliminating Dequantization Bottleneck via Activation Decomposition for Efficient LLM Inference
Lingchao Zheng, Yuwei Fan, Jun Li +5
Quantization is essential for efficient large language model (LLM) inference, yet the dequantization step-converting low-bit weights back to high-precision for matrix multiplicatio…
DAIT: Distillation from Vision-Language Models to Lightweight Classifiers with Adaptive Intermediate Teacher Transfer
Zhengxu He, Jun Li, Zhijian Wu
Large-scale Vision-Language Models (VLMs) encode rich multimodal semantics that are highly beneficial for fine-grained visual categorization (FGVC). However, their prohibitive comp…
LoPT: Lossless Parallel Tokenization Acceleration for Long Context Inference of Large Language Model
Wei Shao, Lingchao Zheng, Pengyu Wang +3
Long context inference scenarios have become increasingly important for large language models, yet they introduce significant computational latency. While prior research has optimi…