9 papers
-Musketeers: Reinforcement Learning Shapes Collaboration Among Language Models
Ryozo Masukawa, Sanggeon Yun, Hyunwoo Oh +8
Recent progress in reinforcement learning with verifiable rewards (RLVR) shows that small, specialized language models (SLMs) can exhibit structured reasoning without relying on la…
QUILL: An Algorithm-Architecture Co-Design for Cache-Local Deformable Attention
Hyunwoo Oh, Hanning Chen, Sanggeon Yun +5
Deformable transformers deliver state-of-the-art detection but map poorly to hardware due to irregular memory access and low arithmetic intensity. We introduce QUILL, a schedule-aw…
T-SAR: A Full-Stack Co-design for CPU-Only Ternary LLM Inference via In-Place SIMD ALU Reorganization
Hyunwoo Oh, KyungIn Nam, Rajat Bhattacharjya +7
Recent advances in LLMs have outpaced the computational and memory capacities of edge platforms that primarily employ CPUs, thereby challenging efficient and scalable deployment. W…
ASTER: Attention-based Spiking Transformer Engine for Event-driven Reasoning
Tamoghno Das, Khanh Phan Vu, Hanning Chen +2
The integration of spiking neural networks (SNNs) with transformer-based architectures has opened new opportunities for bio-inspired low-power, event-driven visual reasoning on edg…
AVERY: Intent-Driven Adaptive VLM Split Computing via Embodied Self-Awareness for Efficient Disaster Response Systems
Rajat Bhattacharjya, Sing-Yao Wu, Hyunwoo Oh +5
Unmanned Aerial Vehicles (UAVs) in disaster response require complex, queryable intelligence that onboard CNNs cannot provide. While Vision-Language Models (VLMs) offer this semant…
LogHD: Robust Compression of Hyperdimensional Classifiers via Logarithmic Class-Axis Reduction
Sanggeon Yun, Hyunwoo Oh, Ryozo Masukawa +3
Hyperdimensional computing (HDC) suits memory, energy, and reliability-constrained systems, yet the standard "one prototype per class" design requires memory (with clas…