Papers
Research papers from arXiv and related sources
When Drafts Evolve: Speculative Decoding Meets Online Learning
Speculative decoding has emerged as a widely adopted paradigm for accelerating large language model inference, where a lightweight draft model rapidly generates candidate tokens that are then verif...
Yu-Yang Qian, Hao-Cong Wu, Yichao Fu, Hao Zhang, Peng Zhao
Literary Narrative as Moral Probe : A Cross-System Framework for Evaluating AI Ethical Reasoning and Refusal Behavior
Existing AI moral evaluation frameworks test for the production of correct-sounding ethical responses rather than the presence of genuine moral reasoning capacity. This paper introduces a novel pro...
David C. Flynn
ChainFuzzer: Greybox Fuzzing for Workflow-Level Multi-Tool Vulnerabilities in LLM Agents
Tool-augmented LLM agents increasingly rely on multi-step, multi-tool workflows to complete real tasks. This design expands the attack surface, because data produced by one tool can be persisted an...
Jiangrong Wu, Zitong Yao, Yuhong Nan, Zibin Zheng
InterDeepResearch: Enabling Human-Agent Collaborative Information Seeking through Interactive Deep Research
Deep research systems powered by LLM agents have transformed complex information seeking by automating the iterative retrieval, filtering, and synthesis of insights from massive-scale web sources. ...
Bo Pan, Lunke Pan, Yitao Zhou, Qi Jiang, Zhen Wen, Minfeng Zhu, Wei Chen
A2Z-10M+: Geometric Deep Learning with A-to-Z BRep Annotations for AI-Assisted CAD Modeling and Reverse Engineering
Reverse engineering and rapid prototyping of computer-aided design (CAD) models from 3D scans, sketches, or simple text prompts are vital in industrial product design. However, recent advances in g...
Pritham Kumar Jena, Bhavika Baburaj, Tushar Anand, Vedant Dutta, Vineeth Ulavala, Sk Aziz Ali
How GenAI Mentor Configurations Shape Early Collaborative Dynamics: A Classroom Comparison of Individual and Shared Agents
Generative artificial intelligence (GenAI) is increasingly embedded in computer-supported collaborative learning (CSCL), yet little empirical research has unpacked how different configurations of A...
Siyu Zha, Weijing Liu, Fei Qin, Jie Cao, Yanjin Wang, Yujia Liu, Kaiyi Zhang, Jiangtao Gong, Ying...
Feynman: Knowledge-Infused Diagramming Agent for Scalable Visual Designs
Visual design is an essential application of state-of-the-art multi-modal AI systems. Improving these systems requires high-quality vision-language data at scale. Despite the abundance of internet ...
Zixin Wen, Yifu Cai, Kyle Lee, Sam Estep, Josh Sunshine, Aarti Singh, Yuejie Chi, Wode Ni
Swap-guided Preference Learning for Personalized Reinforcement Learning from Human Feedback
Reinforcement Learning from Human Feedback (RLHF) is a widely used approach to align large-scale AI systems with human values. However, RLHF typically assumes a single, universal reward, which over...
Gihoon Kim, Euntai Kim
Early Pruning for Public Transport Routing
Routing algorithms for public transport, particularly the widely used RAPTOR and its variants, often face performance bottlenecks during the transfer relaxation phase, especially on dense transfer ...
Andrii Rohovyi, Abdallah Abuaisha, Toby Walsh
Expert Pyramid Tuning: Efficient Parameter Fine-Tuning for Expertise-Driven Task Allocation
Parameter-Efficient Fine-Tuning (PEFT) has become a dominant paradigm for deploying LLMs in multi-task scenarios due to its extreme parameter efficiency. While Mixture-of-Experts (MoE) based LoRA v...
Jia-Chen Zhang, Zhen-Wei Yan, Yu-Jie Xiong, Chun-Ming Xia
From Woofs to Words: Towards Intelligent Robotic Guide Dogs with Verbal Communication
Assistive robotics is an important subarea of robotics that focuses on the well-being of people with disabilities. A robotic guide dog is an assistive quadruped robot that helps visually impaired p...
Yohei Hayamizu, David DeFazio, Hrudayangam Mehta, Zainab Altaweel, Jacqueline Choe, Chao Lin, Jak...
Pointwise mutual information bounded by stochastic Fisher information
We derive general upper bounds to pointwise mutual information in terms of stochastic Fisher information and show these bounds average to known results in the literature for bounds to mutual inform...
Pedro B. Melo
LMEB: Long-horizon Memory Embedding Benchmark
Memory embeddings are crucial for memory-augmented systems, such as OpenClaw, but their evaluation is underexplored in current text embedding benchmarks, which narrowly focus on traditional passage...
Xinping Zhao, Xinshuo Hu, Jiaxin Xu, Danyu Tang, Xin Zhang, Mengjia Zhou, Yan Zhong, Yao Zhou, Zi...
Hot Jupiter - Cold Jupiter: A complex sibling relation
A handful of planetary systems hosting a Hot Jupiter have been subsequently found to also host long-period giant planets. These ``cold Jupiters,'' giant planets residing beyond the snow line ($\sim...
Adriana Errico, Robert A. Wittenmyer, Jonathan Horner, Brad Carter, Valeria López
Speech-Worthy Alignment for Japanese SpeechLLMs via Direct Preference Optimization
SpeechLLMs typically combine ASR-trained encoders with text-based LLM backbones, leading them to inherit written-style output patterns unsuitable for text-to-speech synthesis. This mismatch is part...
Mengjie Zhao, Lianbo Liu, Yusuke Fujita, Hao Shi, Yuan Gao, Roman Koshkin, Yui Sudo
AgentDrift: Unsafe Recommendation Drift Under Tool Corruption Hidden by Ranking Metrics in LLM Agents
Tool-augmented LLM agents increasingly serve as multi-turn advisors in high-stakes domains, yet their evaluation relies on ranking-quality metrics that measure what is recommended but not whether i...
Zekun Wu, Adriano Koshiyama, Sahan Bulathwela, Maria Perez-Ortiz
Consistent and powerful CUSUM change-point test for panel data with changes in variance
This paper investigates change-point of variance in panel data models with time series of $α$-mixing. Based on the cumulative sum (CUSUM) method and the individual differences, we construct a CUSUM...
Wenzhi Yang, Yueting Xu, Xiaoping Shi, Qiong Li
Large Language Models as Delivery Rider: Generating Instant Food Delivery Riders' Routing Decision with LLM Agent Framework
The utilization of Large Language Models (LLMs) to power human-like agents has shown remarkable potential in simulating individual mobility pattern. However, a significant gap remains in modeling c...
Chengbo Zhang, Zuopeng Xiao
Reinforcement Learning for Diffusion LLMs with Entropy-Guided Step Selection and Stepwise Advantages
Reinforcement learning (RL) has been effective for post-training autoregressive (AR) language models, but extending these methods to diffusion language models (DLMs) is challenging due to intractab...
Vishnu Teja Kunde, Fatemeh Doudi, Mahdi Farahbakhsh, Dileep Kalathil, Krishna Narayanan, Jean-Fra...
Embedded Quantum Machine Learning in Embedded Systems: Feasibility, Hybrid Architectures, and Quantum Co-Processors
Embedded quantum machine learning (EQML) seeks to bring quantum machine learning (QML) capabilities to resource-constrained edge platforms such as IoT nodes, wearables, drones, and cyber-physical c...
Somdip Dey, Syed Muhammad Raza