collaborators

24 papers

cs.AR2026

Sparse by Command: Task-Conditional Compute Skipping for Multi-Task Inference Accelerators

Afzal Ahmad, Gaoyu Mao, Shoubo Hu +4

Multi-task inference models share a single backbone across diverse tasks, yet execute identical computation regardless of which task is active - wasting energy and cycles on task-i…

cs.CL2026

YouZhi: Towards High-Concurrency Financial LLMs via Adaptive GQA-to-MLA Transition

PSBC LLM Team, Huawei LLM Team, Ruihan Long +56

Large language models (LLMs) drive significant financial innovations, yet their high-concurrency deployment is severely bottlenecked by KV cache memory overhead, which inflates inf…

cs.AI2026

SCOPE: Prompt Evolution for Enhancing Agent Effectiveness

Zehua Pei, Hui-Ling Zhen, Shixiong Kai +4

Large Language Model (LLM) agents are increasingly deployed in environments that generate massive, dynamic contexts. However, a critical bottleneck remains: while agents have acces…

cs.CL2026

Verilog-Evolve: Feedback-Driven and Skill-Evolving Verilog Generation

Zehua Pei, Hui-Ling Zhen, Yu Zhang +3

Large language models (LLMs) have improved Verilog generation from natural-language specifications, but most pipelines still treat generation as isolated sampling followed by funct…

cs.CL2026

PSD: Pushing the Pareto Frontier of Diffusion LLMs via Parallel Speculative Decoding

Shengyin Sun, Yiming Li, Renxi Liu +7

Diffusion large language models (dLLMs) generate text by iteratively denoising masked token sequences. Although dLLMs can predict all masked positions in parallel within each step,…

cs.CL2026

FocuSFT: Bilevel Optimization for Dilution-Aware Long-Context Fine-Tuning

Zehua Pei, Hui-Ling Zhen, Xianzhi Yu +3

Large language models can now process increasingly long inputs, yet their ability to effectively use information spread across long contexts remains limited. We trace this gap to h…