8 papers
Short Chains, Deep Thoughts: Balancing Reasoning Efficiency and Intra-Segment Capability via Split-Merge Optimization
Runquan Gui, Jie Wang, Zhihai Wang +3
While Large Reasoning Models (LRMs) have demonstrated impressive capabilities in solving complex tasks through the generation of long reasoning chains, this reliance on verbose gen…
Why Attention Patterns Exist: A Unifying Temporal Perspective Analysis
Qingyue Yang, Jie Wang, Xing Li +6
Attention patterns play a crucial role in both training and inference of large language models (LLMs). Prior works have identified individual patterns such as retrieval heads, sink…
AttentionPredictor: Temporal Patterns Matter for KV Cache Compression
Qingyue Yang, Jie Wang, Xing Li +8
With the development of large language models (LLMs), efficient inference through Key-Value (KV) cache compression has attracted considerable attention, especially for long-context…
Piano: A Multi-Constraint Pin Assignment-Aware Floorplanner
Zhexuan Xu, Kexin Zhou, Jie Wang +5
Floorplanning is a critical step in VLSI physical design, increasingly complicated by modern constraints such as fixed-outline requirements, whitespace removal, and the presence of…
One Step Beyond: Feedthrough & Placement-Aware Rectilinear Floorplanner
Zhexuan Xu, Jie Wang, Siyuan Xu +3
Floorplanning determines the shapes and locations of modules on a chip canvas and plays a critical role in optimizing the chip's Power, Performance, and Area (PPA) metrics. However…
HyperTree Planning: Enhancing LLM Reasoning via Hierarchical Thinking
Runquan Gui, Zhihai Wang, Jie Wang +7
Recent advancements have significantly enhanced the performance of large language models (LLMs) in tackling complex reasoning tasks, achieving notable success in domains like mathe…