13 papers
Dissimilarity-Based Markov Decision Processes for Stabilizing State Distributions
Xun Shen, Yuepeng Wang, Daniyal Sajedi-Hosseini +6
Reinforcement learning for stochastic systems typically optimizes expected cumulative rewards, while reliable and repeatable behavior also depends on how the state distribution evo…
Enforcing a Strict Safety Margin in LLM Text Generation via Barrier Lyapunov Control
Anand Singh, Shubham Singh, Anjali Tiwari +1
Large language models are increasingly deployed without formal guarantees against toxic text generation. Existing control barrier function (CBF) based safety filters can keep the g…
Safe Unicycle Navigation Among Multiple Obstacles Under Bounded Disturbances: A Learning-Augmented CLF-CBF Approach (Extended Version)
Shubham Singh, Anjali Tiwari, Anand Singh +1
This paper presents a robust control framework for safe navigation of a unicycle robot to a goal among multiple static obstacles under an unknown, time-varying disturbance. The con…
BRIDGE: Bilevel Retrieval-Credit-Aware Agentic Reinforcement Learning
Quan Xiao, Mingda Liu, Gaowen Liu +2
Agentic reinforcement learning (ARL) with verifiable rewards improves the ability of large language models (LLMs) to tackle knowledge-intensive tasks by learning to interleave sear…
Interaction-Limited Safe Continuous-Time RL for Dynamical Medical Treatment
Xun Shen, Yuepeng Wang, Akifumi Wachi +13
Dynamic medical treatment requires deciding treatment intensity and intervention timing, while patient states evolve continuously and adverse events may occur between clinical inte…
A Unified Benchmark for Dynamic Medical Treatment Reinforcement Learning
Yuepeng Wang, Ken Kawano, Yongqi Zhou +12
Medical treatment recommendation poses several challenges to reinforcement learning (RL): patient physiology evolves in continuous time, measurements and interventions are performe…
Signs Beat Floats: Low-Rank Double-Binary Adaptation for On-Device Fine-Tuning
Yoshihiko Fujisawa, Yuma Ichikawa, Yudai Fujimoto +2
On-device adaptation of large language models commonly keeps a quantized base model frozen while training and deploying a small, task-specific LoRA adapter. In the unmerged adapter…
OneComp: One-Line Revolution for Generative AI Model Compression
Yuma Ichikawa, Keiji Kimura, Akihiro Yoshida +11
Deploying foundation models is increasingly constrained by memory footprint, latency, and hardware costs. Post-training compression can mitigate these bottlenecks by reducing the p…
Norm Anchors Make Model Edits Last
Mingda Liu, Zhenghan Zhu, Ze'an Miao +1
Sequential Locate-and-Edit (L&E) model editing can fail abruptly after many edits. We identify and formalize this failure as a positive norm-feedback loop, in which solved value ve…
More Than Bits: Multi-Envelope Double Binary Factorization for Extreme Quantization
Yuma Ichikawa, Yoshihiko Fujisawa, Yudai Fujimoto +2
For extreme low-bit quantization of large language models (LLMs), Double Binary Factorization (DBF) is attractive as it enables efficient inference without sacrificing accuracy. Ho…
Superpixel Attack: Enhancing Black-box Adversarial Attack with Image-driven Division Areas
Issa Oe, Keiichiro Yamamura, Hiroki Ishikura +2
Deep learning models are used in safety-critical tasks such as automated driving and face recognition. However, small perturbations in the model input can significantly change the…
Enhancing Quantum-ready QUBO-based Suppression for Object Detection with Appearance and Confidence Features
Keiichiro Yamamura, Toru Mitsutake, Hiroki Ishikura +3
Quadratic Unconstrained Binary Optimization (QUBO)-based suppression in object detection is known to have superiority to conventional Non-Maximum Suppression (NMS), especially for…
Enhancing Output Diversity Improves Conjugate Gradient-based Adversarial Attacks
Keiichiro Yamamura, Issa Oe, Hiroki Ishikura +1
Deep neural networks are vulnerable to adversarial examples, and adversarial attacks that generate adversarial examples have been studied in this context. Existing studies imply th…