12 citations · 24 across the 14 of their papers we have counts for
14 papers
MobileLLM-Flash: Latency-Guided On-Device LLM Design for Industry Scale Deployment
Hanxian Huang, Igor Fedorov, Andrey Gromov +14
Real-time AI experiences call for on-device large language models (OD-LLMs) optimized for efficient deployment on resource-constrained hardware. The most useful OD-LLMs produce nea…
dTRPO: Trajectory Reduction in Policy Optimization of Diffusion Large Language Models
Wenxuan Zhang, Lemeng Wu, Changsheng Zhao +11
Diffusion Large Language Models (dLLMs) introduce a new paradigm for language generation, which in turn presents new challenges for aligning them with human preferences. In this wo…
The Path Not Taken: RLVR Provably Learns Off the Principals
Hanqing Zhu, Zhenyu Zhang, Hanxian Huang +11
Reinforcement Learning with Verifiable Rewards (RLVR) reliably improves the reasoning performance of large language models, yet it appears to modify only a small fraction of parame…
MobileLLM-Pro Technical Report
Patrick Huber, Ernie Chang, Wei Wen +16
Efficient on-device language models around 1 billion parameters are essential for powering low-latency AI applications on mobile and wearable devices. However, achieving strong per…
SHARP: Accelerating Language Model Inference by SHaring Adjacent layers with Recovery Parameters
Yiping Wang, Hanxian Huang, Yifang Chen +3
While Large language models (LLMs) have advanced natural language processing tasks, their growing computational and memory demands make deployment on resource-constrained devices l…
ParetoQ: Improving Scaling Laws in Extremely Low-bit LLM Quantization
Zechun Liu, Changsheng Zhao, Hanxian Huang +13
The optimal bit-width for achieving the best trade-off between quantized model size and accuracy has been a subject of ongoing debate. While some advocate for 4-bit quantization, o…
OrcaLoca: An LLM Agent Framework for Software Issue Localization
Zhongming Yu, Hejia Zhang, Yujie Zhao +4
Recent developments in Large Language Model (LLM) agents are revolutionizing Autonomous Software Engineering (ASE), enabling automated coding, problem fixes, and feature improvemen…
MAGE: A Multi-Agent Engine for Automated RTL Code Generation
Yujie Zhao, Hejia Zhang, Hanxian Huang +2
The automatic generation of RTL code (e.g., Verilog) through natural language instructions has emerged as a promising direction with the advancement of large language models (LLMs)…
You Only Use Reactive Attention Slice For Long Context Retrieval
Yun Joon Soh, Hanxian Huang, Yuandong Tian +1
Supporting longer context for Large Language Models (LLM) is a promising direction to advance LLMs. As training a model for a longer context window is computationally expensive, ma…
Towards LLM-Powered Verilog RTL Assistant: Self-Verification and Self-Correction
Hanxian Huang, Zhenghan Lin, Zixuan Wang +3
We explore the use of Large Language Models (LLMs) to generate high-quality Register-Transfer Level (RTL) code with minimal human interference. The traditional RTL design workflow…
GeoT: Tensor Centric Library for Graph Neural Network via Efficient Segment Reduction on GPU
Zhongming Yu, Genghan Zhang, Hanxian Huang +2
In recent years, Graph Neural Networks (GNNs) have ignited a surge of innovation, significantly enhancing the processing of geometric data structures such as graphs, point clouds,…
Multi-modal Learning for WebAssembly Reverse Engineering
Hanxian Huang, Jishen Zhao
The increasing adoption of WebAssembly (Wasm) for performance-critical and security-sensitive tasks drives the demand for WebAssembly program comprehension and reverse engineering.…
Learning to Maximize Mutual Information for Chain-of-Thought Distillation
Xin Chen, Hanxian Huang, Yanjun Gao +3
Knowledge distillation, the technique of transferring knowledge from large, complex models to smaller ones, marks a pivotal step towards efficient AI deployment. Distilling Step-by…
Sibyl: Forecasting Time-Evolving Query Workloads
Hanxian Huang, Tarique Siddiqui, Rana Alotaibi +6
Database systems often rely on historical query traces to perform workload-based performance tuning. However, real production workloads are time-evolving, making historical queries…