Papers
Research papers from arXiv and related sources
Adaptive Auxiliary Prompt Blending for Target-Faithful Diffusion Generation
Diffusion-based text-to-image (T2I) models have made remarkable progress in generating photorealistic and semantically rich images. However, when the target concepts lie in low-density regions of t...
Kwanyoung Lee, SeungJu Cha, Yebin Ahn, Hyunwoo Oh, Sungho Koh, Dong-Jin Kim
ADAPT: Attention Driven Adaptive Prompt Scheduling and InTerpolating Orthogonal Complements for Rare Concepts Generation
Generating rare compositional concepts in text-to-image synthesis remains a challenge for diffusion models, particularly for attributes that are uncommon in the training data. While recent approach...
Kwanyoung Lee, Hyunwoo Oh, SeungJu Cha, Sungho Koh, Dong-Jin Kim
Spectral reconstruction techniques, their shortcomings and relevance to the electric conductivity coefficient
Spectral reconstruction is a well studied numerically ill-posed problem which arises due to the relation of the Euclidean correlator to the spectral function via an inhomogeneous Fredholm equation ...
C. Andratschke, B. B. Brandt, E. Garnacho-Velasco, L. Pannullo, S. Singh, A. Dean M. Valois
Performance Testing of ChaCha20-Poly1305 for Internet of Things and Industrial Control System devices
Industrial Control Systems (ICS), and many simple Internet of Things (IoT) devices, commonly communicate using unencrypted or unauthenticated protocols. For ICS this is an historical carryover sinc...
Kristján Orri Ragnarsson, Jacky Mallett
UGID: Unified Graph Isomorphism for Debiasing Large Language Models
Large language models (LLMs) exhibit pronounced social biases. Output-level or data-optimization--based debiasing methods cannot fully resolve these biases, and many prior works have shown that bia...
Zikang Ding, Junchi Yao, Junhao Li, Yi Zhang, Wenbo Jiang, Hongbo Liu, Lijie Hu
Anatomical Heterogeneity in Transformer Language Models
Current transformer language models are trained with uniform computational budgets across all layers, implicitly assuming layer homogeneity. We challenge this assumption through empirical analysis ...
Tomasz Wietrzykowski
Implicit Patterns in LLM-Based Binary Analysis
Binary vulnerability analysis is increasingly performed by LLM-based agents in an iterative, multi-pass manner, with the model as the core decision-maker. However, how such systems organize explora...
Qiang Li, XiangRui Zhang, Haining Wang
A Pipelined Collaborative Speculative Decoding Framework for Efficient Edge-Cloud LLM Inference
Recent advancements and widespread adoption of Large Language Models (LLMs) in both industry and academia have catalyzed significant demand for LLM serving. However, traditional cloud services incu...
Yida Zhang, Zhiyong Gao, Shuaibing Yue, Jie Li, Rui Wang
From Inference Efficiency to Embodied Efficiency: Revisiting Efficiency Metrics for Vision-Language-Action Models
Vision-Language-Action (VLA) models have recently enabled embodied agents to perform increasingly complex tasks by jointly reasoning over visual, linguistic, and motor modalities. However, we find ...
Zhuofan Li, Hongkun Yang, Zhenyang Chen, Yangxuan Chen, Yingyan, Lin, Chaojian Li
On Optimizing Multimodal Jailbreaks for Spoken Language Models
As Spoken Language Models (SLMs) integrate speech and text modalities, they inherit the safety vulnerabilities of their LLM backbone and an expanded attack surface. SLMs have been previously shown ...
Aravind Krishnan, Karolina Stańczak, Dietrich Klakow
DaPT: A Dual-Path Framework for Multilingual Multi-hop Question Answering
Retrieval-augmented generation (RAG) systems have made significant progress in solving complex multi-hop question answering (QA) tasks in the English scenario. However, RAG systems inevitably face ...
Yilin Wang, Yuchun Fan, Jiaoyang Li, Ziming Zhu, Yongyu Mu, Qiaozhi He, Tong Xiao, Jingbo Zhu
Follow the Rules (or Not): Community Norms and AI-Generated Support in Online Health Communities
Generative AI (GenAI) is increasingly being integrated into the online ecosystem, including online health communities (OHCs), where people with diverse health conditions exchange social support. Fo...
Shravika Mittal, Erin Kasson, Layna Paraboschi, Eleanor Laufenberg, Jiawei Zhou, Patricia A. Cava...
Serendipity by Design: Evaluating the Impact of Cross-domain Mappings on Human and LLM Creativity
Are large language models (LLMs) creative in the same way humans are, and can the same interventions increase creativity in both? We evaluate a promising but largely untested intervention for creat...
Qiawen Ella Liu, Marina Dubova, Henry Conklin, Takumi Harada, Thomas L. Griffiths
A Dataset and Resources for Identifying Patient Health Literacy Information from Clinical Notes
Health literacy is a critical determinant of patient outcomes, yet current screening tools are not always feasible and differ considerably in the number of items, question format, and dimensions of...
Madeline Bittner, Dina Demner-Fushman, Yasmeen Shabazz, Davis Bartels, Dukyong Yoon, Brad Quitada...
Multi-Modal Building Change Detection for Large-Scale Small Changes: Benchmark and Baseline
Change detection in optical remote sensing imagery is susceptible to illumination fluctuations, seasonal changes, and variations in surface land-cover materials. Relying solely on RGB imagery often...
Ye Wang, Wei Lu, Zhihui You, Keyan Chen, Tongfei Liu, Kaiyu Li, Hongruixuan Chen, Qingling Shu, S...
A conservative, discontinuous Galerkin, tracer transport scheme using compatible finite elements
This paper outlines a conservative transport scheme for scalar tracers within a compatible finite element model for geophysical fluid equations. Instead of using the advective transport equation fo...
Timothy C. Andrews, Thomas M. Bendall
CAMO: A Conditional Neural Solver for the Multi-objective Multiple Traveling Salesman Problem
Robotic systems often require a team of robots to collectively visit multiple targets while optimizing competing objectives, such as total travel cost and makespan. This setting can be formulated a...
Fengxiaoxiao Li, Xiao Mao, Mingfeng Fan, Yifeng Zhang, Yi Li, Tanishq Duhan, Guillaume Sartoretti
Parallelograms Strike Back: LLMs Generate Better Analogies than People
Four-term word analogies (A:B::C:D) are classically modeled geometrically as ''parallelograms,'' yet recent work suggests this model poorly captures how humans produce analogies, with simple local-...
Qiawen Ella Liu, Raja Marjieh, Jian-Qiao Zhu, Adele E. Goldberg, Thomas L. Griffiths
Fair Decoder Baselines and Rigorous Finite-Size Scaling for Bivariate Bicycle Codes on the Quantum Erasure Channel
Fair threshold estimation for bivariate bicycle (BB) codes on the quantum erasure channel runs into two recurring problems: decoder-baseline unfairness and the conflation of finite-size pseudo-thre...
Tushar Pandey
Hardness of High-Dimensional Linear Classification
We establish new exponential in dimension lower bounds for the Maximum Halfspace Discrepancy problem, which models linear classification. Both are fundamental problems in computational geometry and...
Alexander Munteanu, Simon Omlor, Jeff M. Phillips