71 papers
Circuit Depth Compression via Spectral Gap Amplification in Quantum Phase Estimation
Sk Mujaffar Hossain, Satadeep Bhattacharjee
We show that quantum phase estimation (QPE) circuits can be significantly compressed in depth by preprocessing the input operator with a sigmoid spectral filter before estimation.…
Bootstrapping Niche Multilingual Code Translation via Reinforcement Learning with Execution-Based Verifiable Supervision
Kouki Yuki, Jie Zeng, Kyoko Ogawa +6
Code translation must preserve executable behavior across many programming languages, yet neural code translation has largely focused on a few popular languages such as C++, Java,…
Auditing Instruction-Trajectory Mismatches in Multimodal Robot Demonstrations
Simon Holk, Ryosuke Takanami, Tatsuya Matsushima +4
Robot demonstration datasets used to train vision-language-action policies can contain a subtle but harmful failure mode: trajectories that are behaviorally correct but paired with…
Benchmarking and Reasoning Distillation of Large Language Models for Feedback Controller Design in Complex Dynamical Systems
Zhongchao Zhou, Yixuan Xie, Wenwei Yu +5
Although remarkable capabilities have been demonstrated by Large Language Models (LLMs) across scientific domains, feedback controller design remains underexplored. Existing benchm…
Looped Transformers with Source-Centered State Evolution
Bum Jun Kim, Kohei Hayashi, Shunsuke Kamiya +3
The paper introduces Source‑Centered State Evolution (SCSE), a method for looped Transformers that preserves input conditioning while keeping a fixed reference point, improving rec…
Temporally Centered SIGReg Improves Multi-Task LeWorldModel Learning: From Analysis to Method
Chang Liu, Fei Suo, Yanzhou Jin +3
The paper introduces a temporally centered version of the Sketched Isotropic Gaussian Regularizer (SIGReg) that regularizes residuals instead of latent marginals, improving stabili…