3 papers
cs.SE2026
LatentSift: Policy-State Filtering for Token-Efficient Verification of Software Engineering Agents
Yuning Han, Yangchenchen Jin, Tyler Jandreau +1
Test-time scaling improves software engineering agents by generating multiple candidate trajectories and selecting the best one. Verifying and selecting among these long interactio…
physics.optics2026
A generative pre-trained transformer with Kerr-soliton attention
Lindell M. Williams, Yan Jin, Scott B. Papp
Generative pre-trained transformers (GPTs) have enabled capability-rich language models, but their operation incurs substantial costs in computation, memory, and data movement. A m…
cs.LG2026
CATS: Cascaded Adaptive Tree Speculation for Memory-Limited LLM Inference Acceleration
Yuning Han, Yangchenchen Jin, Dylan Zhao +1
Auto-regressive decoding in Large Language Models (LLMs) is inherently memory-bound: every generation step requires loading the model weights and intermediate results from memory (…