Papers
Research papers from arXiv and related sources
AgentRM: An OS-Inspired Resource Manager for LLM Agent Systems
Large Language Model (LLM) agent systems have experienced rapid adoption across diverse domains, yet they suffer from critical user experience problems that limit their practical deployment. Throug...
Jianshu She
The elusive cyclotron line in 4U 1901+03: hidden, yet present
Context. Cyclotron resonant scattering features (CRSFs) in accreting X-ray pulsars are often difficult to detect, especially when shallow or variable. Recent studies have shown that combining spect...
Elena Ambrosi, Antonino D' Aì, Giancarlo Cusumano, Carlo Ferrigno, Ekaterina Sokolova-Lapa, Dimit...
Breaking the Tuning Barrier: Zero-Hyperparameters Yield Multi-Corner Analysis Via Learned Priors
Yield Multi-Corner Analysis validates circuits across 25+ Process-Voltage-Temperature corners, resulting in a combinatorial simulation cost of $O(K \times N)$ where $K$ denotes corners and $N$ exce...
Wei W. Xing, Kaiqi Huang, Jiazhan Liu, Hong Qiu, Shan Shen
Human-in-the-Loop LLM Grading for Handwritten Mathematics Assessments
Providing timely and individualised feedback on handwritten student work is highly beneficial for learning but difficult to achieve at scale. This challenge has become more pressing as generative A...
Arne Vanhoyweghen, Vincent Holst, Melika Mobini, Lukas Van de Voorde, Tibo Vanleke, Bert Verbrugg...
3DTCR: A Physics-Based Generative Framework for Vortex-Following 3D Reconstruction to Improve Tropical Cyclone Intensity Forecasting
Tropical cyclone (TC) intensity forecasting remains challenging as current numerical and AI-based weather models fail to satisfactorily represent extreme TC structure and intensity. Although intens...
Jun Liu, Xiaohui Zhong, Kai Zheng, Jiarui Li, Yifei Li, Tao Zhou, Wenxu Qian, Shun Dai, Ruian Tie...
Mending the Holes: Mitigating Reward Hacking in Reinforcement Learning for Multilingual Translation
Large Language Models (LLMs) have demonstrated remarkable capability in machine translation on high-resource language pairs, yet their performance on low-resource translation still lags behind. Exi...
Yifeng Liu, Siqi Ouyang, Yatish Hosmane Revanasiddappa, Lei Li
Before and After ChatGPT: Revisiting AI-Based Dialogue Systems for Emotional Support
Mental health remains a major public health concern, while access to timely psychological support is often limited. AI-based dialogue systems have emerged as promising tools to address these barrie...
Daeun Lee, Dongje Yoo, Migyeong Yang, Jihyun An, Christine B. Cha, Jinyoung Han
Interpretable Semantic Gradients in SSD: A PCA Sweep Approach and a Case Study on AI Discourse
Supervised Semantic Differential (SSD) is a mixed quantitative-interpretive method that models how text meaning varies with continuous individual-difference variables by estimating a semantic gradi...
Hubert Plisiecki, Maria Leniarska, Jan Piotrowski, Marcin Zajenkowski
Interrogating Design Homogenization in Web Vibe Coding
Generative AI is known for its tendency to homogenize, often reproducing dominant style conventions found in training data. However, it remains unclear how these homogenizing effects extend to comp...
Donghoon Shin, Alice Gao, Rock Yuren Pang, Jaewook Lee, Katharina Reinecke, Emily Tseng
PISmith: Reinforcement Learning-based Red Teaming for Prompt Injection Defenses
Prompt injection poses serious security risks to real-world LLM applications, particularly autonomous agents. Although many defenses have been proposed, their robustness against adaptive attacks re...
Chenlong Yin, Runpeng Geng, Yanting Wang, Jinyuan Jia
SAW: Toward a Surgical Action World Model via Controllable and Scalable Video Generation
A surgical world model capable of generating realistic surgical action videos with precise control over tool-tissue interactions can address fundamental challenges in surgical AI and simulation -- ...
Sampath Rapuri, Lalithkumar Seenivasan, Dominik Schneider, Roger Soberanis-Mukul, Yufan He, Hao D...
ARL-Tangram: Unleash the Resource Efficiency in Agentic Reinforcement Learning
Agentic reinforcement learning (RL) has emerged as a transformative workload in cloud clusters, enabling large language models (LLMs) to solve complex problems through interactions with real world....
Bangjun Xiao, Yihao Zhao, Xiangwei Deng, Shihua Yu, Yuxing Xiang, Huaqiu Liu, Qiying Wang, Liang ...
Structured Distillation for Personalized Agent Memory: 11x Token Reduction with Retrieval Preservation
Long conversations with an AI agent create a simple problem for one user: the history is useful, but carrying it verbatim is expensive. We study personalized agent memory: one user's conversation h...
Sydney Lewis
Dependency-Aware Parallel Decoding via Attention for Diffusion LLMs
Parallel decoding for diffusion LLMs (dLLMs) is difficult because each denoising step provides only token-wise marginal distributions, while unmasking multiple tokens simultaneously requires accoun...
Bumjun Kim, Dongjae Jeon, Moongyu Jeon, Albert No
Is Human Annotation Necessary? Iterative MBR Distillation for Error Span Detection in Machine Translation
Error Span Detection (ESD) is a crucial subtask in Machine Translation (MT) evaluation, aiming to identify the location and severity of translation errors. While fine-tuning models on human-annotat...
Boxuan Lyu, Haiyue Song, Zhi Qu
Generative Horcrux: Designing AI Carriers for Afterlife Selves
As generative AI technologies rapidly advance, AI agents are gaining the ability not only to collect data and perform tasks but also to respond to environments and evolve over time. This shift open...
Zhen-Chi Lai, Yu-Ting Cheng, Pei-Ying Lin, Chiao-Wei Ho, Janet Yi-Ching Huang
Delta1 with LLM: symbolic and neural integration for credible and explainable reasoning
Neuro-symbolic reasoning increasingly demands frameworks that unite the formal rigor of logic with the interpretability of large language models (LLMs). We introduce an end to end explainability by...
Yang Xu, Jun Liu, Shuwei Chen, Chris Nugent, Hailing Guo
Can Fairness Be Prompted? Prompt-Based Debiasing Strategies in High-Stakes Recommendations
Large Language Models (LLMs) can infer sensitive attributes such as gender or age from indirect cues like names and pronouns, potentially biasing recommendations. While several debiasing methods ex...
Mihaela Rotar, Theresia Veronika Rampisela, Maria Maistro
MotionAnymesh: Physics-Grounded Articulation for Simulation-Ready Digital Twins
Converting static 3D meshes into interactable articulated assets is crucial for embodied AI and robotic simulation. However, existing zero-shot pipelines struggle with complex assets due to a criti...
WenBo Xu, Liu Liu, Li Zhang, Dan Guo, RuoNan Liu
Photonic Exponential Approximation via Cascaded TFLN Microring Resonators toward Softmax
The rapid growth of large-scale AI models has intensified energy consumption and data-movement challenges in modern datacenters. Photonic accelerators offer a promising path by executing the line...
Hyoseok Park, Yeonsang Park