Papers
Research papers from arXiv and related sources
Privacy-Preserving End-to-End Full-Duplex Speech Dialogue Models
End-to-end full-duplex speech models feed user audio through an always-on LLM backbone, yet the speaker privacy implications of their hidden representations remain unexamined. Following the VoicePr...
Nikita Kuzmin, Tao Zhong, Jiajun Deng, Yingke Zhu, Tristan Tsoi, Tianxiang Cao, Simon Lui, Kong A...
MERLIN: Building Low-SNR Robust Multimodal LLMs for Electromagnetic Signals
The paradigm of Multimodal Large Language Models (MLLMs) offers a promising blueprint for advancing the electromagnetic (EM) domain. However, prevailing approaches often deviate from the native MLL...
Junyu Shen, Zhendong She, Chenghanyu Zhang, Yuchuang Sun, Luqing Luo, Dingwei Tan, Zonghao Guo, B...
Evidence-Driven Reasoning for Industrial Maintenance Using Heterogeneous Data
Industrial maintenance platforms contain rich but fragmented evidence, including free-text work orders, heterogeneous operational sensors or indicators, and structured failure knowledge. These sour...
Fearghal O'Donncha, Nianjun Zhou, Natalia Martinez, James T Rayfield, Fenno F. Heath, Abigail Lan...
RexDrug: Reliable Multi-Drug Combination Extraction through Reasoning-Enhanced LLMs
Automated Drug Combination Extraction (DCE) from large-scale biomedical literature is crucial for advancing precision medicine and pharmacological research. However, existing relation extraction me...
Zhijun Wang, Ling Luo, Dinghao Pan, Huan Zhuang, Lejing Yu, Yuanyuan Sun, Hongfei Lin
An explainable hybrid deep learning-enabled intelligent fault detection and diagnosis approach for automotive software systems validation
Advancements in data-driven machine learning have emerged as a pivotal element in supporting automotive software systems (ASSs) engineering across various levels of the V-development process. Durin...
Mohammad Abboush, Ehab Ghannoum, Andreas Rausch
Covenant-72B: Pre-Training a 72B LLM with Trustless Peers Over-the-Internet
Recently, there has been increased interest in globally distributed training, which has the promise to both reduce training costs and democratize participation in building large-scale foundation mo...
Joel Lidin, Amir Sarfi, Erfan Miahi, Quentin Anthony, Shivam Chauhan, Evangelos Pappas, Benjamin ...
The Differential Effects of Agreeableness and Extraversion on Older Adults' Perceptions of Conversational AI Explanations in Assistive Settings
Large Language Model-based Voice Assistants (LLM-VAs) are increasingly deployed in assistive settings for older adults, yet little is known about how an agent's personality shapes user perceptions ...
Niharika Mathur, Hasibur Rahman, Smit Desai
Learning Hierarchical Knowledge in Text-Rich Networks with Taxonomy-Informed Representation Learning
Hierarchical knowledge structures are ubiquitous across real-world domains and play a vital role in organizing information from coarse to fine semantic levels. While such structures have been widel...
Yunhui Liu, Yongchao Liu, Yinfeng Chen, Chuntao Hong, Tao Zheng, Tieke He
Gender Bias in MT for a Genderless Language: New Benchmarks for Basque
Large language models (LLMs) and machine translation (MT) systems are increasingly used in our daily lives, but their outputs can reproduce gender bias present in the training data. Most resources ...
Amaia Murillo, Olatz-Perez-de-Viñaspre, Naiara Perez
Gradually Excavating External Knowledge for Implicit Complex Question Answering
Recently, large language models (LLMs) have gained much attention for the emergence of human-comparable capabilities and huge potential. However, for open-domain implicit question-answering problem...
Chang Liu, Xiaoguang Li, Lifeng Shang, Xin Jiang, Qun Liu, Edmund Y. Lam, Ngai Wong
UniGround: Universal 3D Visual Grounding via Training-Free Scene Parsing
Understanding and localizing objects in complex 3D environments from natural language descriptions, known as 3D Visual Grounding (3DVG), is a foundational challenge in embodied AI, with broad impli...
Jiaxi Zhang, Yunheng Wang, Wei Lu, Taowen Wang, Weisheng Xu, Shuning Zhang, Yixiao Feng, Yuetong ...
EvoScientist: Towards Multi-Agent Evolving AI Scientists for End-to-End Scientific Discovery
The increasing adoption of Large Language Models (LLMs) has enabled AI scientists to perform complex end-to-end scientific discovery tasks requiring coordination of specialized roles, including ide...
Yougang Lyu, Xi Zhang, Xinhao Yi, Yuyue Zhao, Shuyu Guo, Wenxiang Hu, Jan Piotrowski, Jakub Kalis...
An improved measurement of $η^\prime\rightarrow e^{+}e^{-}ω$
Using a sample of $(10087 \pm 44) \times 10^{6}$ $J/ψ$ events collected with the BESIII detector, an improved measurement of the decay $η^{\prime}\rightarrow e^{+}e^{-}ω$, with $ω\rightarrowπ^{+}π^...
BESIII Collaboration, M. Ablikim, M. N. Achasov, P. Adlarson, X. C. Ai, C. S. Akondi, R. Alibert...
UIS-Digger: Towards Comprehensive Research Agent Systems for Real-world Unindexed Information Seeking
Recent advancements in LLM-based information-seeking agents have achieved record-breaking performance on established benchmarks. However, these agents remain heavily reliant on search-engine-indexe...
Chang Liu, Chuqiao Kuang, Tianyi Zhuang, Yuxin Cheng, Huichi Zhou, Xiaoguang Li, Lifeng Shang
SAMoE-VLA: A Scene Adaptive Mixture-of-Experts Vision-Language-Action Model for Autonomous Driving
Recent advances in Vision-Language-Action (VLA) models have shown promising capabilities in autonomous driving by leveraging the understanding and reasoning strengths of Large Language Models(LLMs)...
Zihan You, Hongwei Liu, Chenxu Dang, Zhe Wang, Sining Ang, Aoqi Wang, Yan Wang
Invisible Safety Threat: Malicious Finetuning for LLM via Steganography
Understanding and addressing potential safety alignment risks in large language models (LLMs) is critical for ensuring their safe and trustworthy deployment. In this paper, we highlight an insidiou...
Guangnian Wan, Xinyin Ma, Gongfan Fang, Xinchao Wang
TrianguLang: Geometry-Aware Semantic Consensus for Pose-Free 3D Localization
Localizing objects and parts from natural language in 3D space is essential for robotics, AR, and embodied AI, yet existing methods face a trade-off between the accuracy and geometric consistency o...
Bryce Grant, Aryeh Rothenberg, Atri Banerjee, Peng Wang
Toward Robust LLM-Based Judges: Taxonomic Bias Evaluation and Debiasing Optimization
Large language model (LLM)-based judges are widely adopted for automated evaluation and reward modeling, yet their judgments are often affected by judgment biases. Accurately evaluating these biase...
Hongli Zhou, Hui Huang, Rui Zhang, Kehai Chen, Bing Xu, Conghui Zhu, Tiejun Zhao, Muyun Yang
DSH-Bench: A Difficulty- and Scenario-Aware Benchmark with Hierarchical Subject Taxonomy for Subject-Driven Text-to-Image Generation
Significant progress has been achieved in subject-driven text-to-image (T2I) generation, which aims to synthesize new images depicting target subjects according to user instructions. However, evalu...
Zhenyu Hu, Qing Wang, Te Cao, Luo Liao, Longfei Lu, Liqun Liu, Shuang Li, Hang Chen, Mengge Xue, ...
EAGLE-Pangu: Accelerator-Safe Tree Speculative Decoding on Ascend NPUs
Autoregressive decoding remains a primary bottleneck in large language model (LLM) serving, motivating speculative decoding methods that reduce expensive teacher-model invocations by verifying mult...
Chang Han, Yijie Hu, Jingling Liu