2 citations · 5 across the 17 of their papers we have counts for
18 papers
Learnable Low-Rank Polynomial Sketch for Effective Linear Attention
Zongyue Qin, Haoran Deng, Jason Cong +1
Softmax attention in Transformers suffers from quadratic complexity in sequence length, making it impractical for long-context applications. Linear attention alleviates this issue…
ACLArena: Agent Continue Learning in Multi-stage Post-training
Haixin Wang, Xiaoxuan Wang, Junkai Zhang +9
Building general-purpose agents for industrial deployment requires integrating multiple capabilities, each typically acquired at a distinct stage of training. Yet there is currentl…
SeDeM: Selective Decompression of Hidden-State Memories for Long-Context Question Answering
Maryam Haghifam, Jason Cong, Yizhou Sun
Long-context inference with large language models (LLMs) is costly: self-attention during prefill scales quadratically with sequence length, and the key-value (KV) cache grows with…
HarnessBridge: Learnable Bidirectional Controller for LLM Agent Harness
Xiaoxuan Wang, Haixin Wang, Alexander Taylor +3
Large language models are increasingly deployed as agents for long-horizon tasks, yet their performance is shaped not only by model capability and environment design, but also by t…
HMT: Semantic Hierarchy-Aware Hierarchical Memory Transformer
Maryam Haghifam, Zifan He, Jason Cong +1
Transformer-based LLMs achieve strong results on many language tasks; however, long inputs remain challenging because context windows are finite, and prefill latency and memory gro…
Understand and Accelerate Memory Processing Pipeline for Large Language Model Inference
Zifan He, Rui Ma, Yizhou Sun +1
Modern large language models (LLMs) increasingly depends on efficient long-context processing and generation mechanisms, including sparse attention, retrieval-augmented generation…
ARLArena: A Unified Framework for Stable Agentic Reinforcement Learning
Xiaoxuan Wang, Han Zhang, Haixin Wang +11
Agentic reinforcement learning (ARL) has rapidly gained attention as a promising paradigm for training agents to solve complex, multi-step interactive tasks. Despite encouraging ea…
FlexLLM: Composable HLS Library for Flexible Hybrid LLM Accelerator Design
Jiahao Zhang, Zifan He, Nicholas Fraser +3
We present FlexLLM, a composable High-Level Synthesis (HLS) library for rapid development of domain-specific LLM accelerators. FlexLLM exposes key architectural degrees of freedom…
Report for NSF Workshop on AI for Electronic Design Automation
Deming Chen, Vijay Ganesh, Weikai Li +7
This report distills the discussions and recommendations from the NSF Workshop on AI for Electronic Design Automation (EDA), held on December 10, 2024 in Vancouver alongside NeurIP…
Iceberg: Enhancing HLS Modeling with Synthetic Data
Zijian Ding, Tung Nguyen, Weikai Li +3
Deep learning-based prediction models for High-Level Synthesis (HLS) of hardware designs often struggle to generalize. In this paper, we study how to close the generalizability gap…
LIFT: LLM-Based Pragma Insertion for HLS via GNN Supervised Fine-Tuning
Neha Prakriya, Zijian Ding, Yizhou Sun +1
FPGAs are increasingly adopted in datacenter environments for their reconfigurability and energy efficiency. High-Level Synthesis (HLS) tools have eased FPGA programming by raising…
Hierarchical Mixture of Experts: Generalizable Learning for High-Level Synthesis
Weikai Li, Ding Wang, Zijian Ding +4
High-level synthesis (HLS) is a widely used tool in designing Field Programmable Gate Array (FPGA). HLS enables FPGA design with software programming languages by compiling the sou…
Dynamic-Width Speculative Beam Decoding for Efficient LLM Inference
Zongyue Qin, Zifan He, Neha Prakriya +2
Large language models (LLMs) have shown outstanding performance across numerous real-world tasks. However, the autoregressive nature of these models makes the inference process slo…
Accelerating Large Language Model Pretraining via LFR Pedagogy: Learn, Focus, and Review
Neha Prakriya, Jui-Nan Yen, Cho-Jui Hsieh +1
Traditional Large Language Model (LLM) pretraining relies on autoregressive language modeling with randomly sampled data from web-scale datasets. Inspired by human learning techniq…
Efficient Task Transfer for HLS DSE
Zijian Ding, Atefeh Sohrabizadeh, Weikai Li +3
There have been several recent works proposed to utilize model-based optimization methods to improve the productivity of using high-level synthesis (HLS) to design domain-specific…
Cross-Modality Program Representation Learning for Electronic Design Automation with High-Level Synthesis
Zongyue Qin, Yunsheng Bai, Atefeh Sohrabizadeh +4
In recent years, domain-specific accelerators (DSAs) have gained popularity for applications such as deep learning and autonomous driving. To facilitate DSA designs, programmers us…
Optimized Multi-Token Joint Decoding with Auxiliary Model for LLM Inference
Zongyue Qin, Ziniu Hu, Zifan He +3
Large language models (LLMs) have achieved remarkable success across diverse tasks, yet their inference processes are hindered by substantial time and energy demands due to single-…
HMT: Hierarchical Memory Transformer for Efficient Long Context Language Processing
Zifan He, Yingqi Cao, Zongyue Qin +3
Transformer-based large language models (LLM) have been widely used in language processing applications. However, due to the memory constraints of the devices, most of them restric…