Papers
Research papers from arXiv and related sources
FireRedASR2S: A State-of-the-Art Industrial-Grade All-in-One Automatic Speech Recognition System
We present FireRedASR2S, a state-of-the-art industrial-grade all-in-one automatic speech recognition (ASR) system. It integrates four modules in a unified pipeline: ASR, Voice Activity Detection (V...
Kaituo Xu, Yan Jia, Kai Huang, Junjie Chen, Wenpeng Li, Kun Liu, Feng-Long Xie, Xu Tang, Yao Hu
Designing Service Systems from Textual Evidence
Designing service systems requires selecting among alternative configurations -- choosing the best chatbot variant, the optimal routing policy, or the most effective quality control procedure. In m...
Ruicheng Ao, Hongyu Chen, Siyang Gao, Hanwei Li, David Simchi-Levi
Verbalizing LLM's Higher-order Uncertainty via Imprecise Probabilities
Despite the growing demand for eliciting uncertainty from large language models (LLMs), empirical evidence suggests that LLM behavior is not always adequately captured by the elicitation techniques...
Anita Yang, Krikamol Muandet, Michele Caprio, Siu Lun Chau, Masaki Adachi
Don't Let the Claw Grip Your Hand: A Security Analysis and Defense Framework for OpenClaw
Code agents powered by large language models can execute shell commands on behalf of users, introducing severe security vulnerabilities. This paper presents a two-phase security analysis of the Ope...
Zhengyang Shan, Jiayun Xin, Yue Zhang, Minghui Xu
Beyond Scalars: Evaluating and Understanding LLM Reasoning via Geometric Progress and Stability
Evaluating LLM reliability via scalar probabilities often fails to capture the structural dynamics of reasoning. We introduce TRACED, a framework that assesses reasoning quality through theoretical...
Xinyan Jiang, Ninghao Liu, Di Wang, Lijie Hu
Causal Concept Graphs in LLM Latent Space for Stepwise Reasoning
Sparse autoencoders can localize where concepts live in language models, but not how they interact during multi-step reasoning. We propose Causal Concept Graphs (CCG): a directed acyclic graph over...
Md Muntaqim Meherab, Noor Islam S. Mohammad, Faiza Feroz
Reactive Writers: How Co-Writing with AI Changes How We Engage with Ideas
Emerging experimental evidence shows that writing with AI assistance can change both the views people express in writing and the opinions they hold afterwards. Yet, we lack substantive understandin...
Advait Bhat, Marianne Aubin Le Quéré, Mor Naaman, Maurice Jakesch
Speech Codec Probing from Semantic and Phonetic Perspectives
Speech tokenizers are essential for connecting speech to large language models (LLMs) in multimodal systems. These tokenizers are expected to preserve both semantic and acoustic information for dow...
Xuan Shi, Chang Zeng, Tiantian Feng, Shih-Heng Wang, Jianbo Ma, Shrikanth Narayanan
Dynamic Knowledge Fusion for Multi-Domain Dialogue State Tracking
The performance of task-oriented dialogue models is strongly tied to how well they track dialogue states, which records and updates user information across multi-turn interactions. However, current...
Haoxiang Su, Ruiyu Fang, Liting Jiang, Xiaomeng Huang, Shuangyong Song
CREATE: Testing LLMs for Associative Creativity
A key component of creativity is associative reasoning: the ability to draw novel yet meaningful connections between concepts. We introduce CREATE, a benchmark designed to evaluate models' capacity...
Manya Wadhwa, Tiasa Singha Roy, Harvey Lederman, Junyi Jessy Li, Greg Durrett
Understanding the Use of a Large Language Model-Powered Guide to Make Virtual Reality Accessible for Blind and Low Vision People
As social virtual reality (VR) grows more popular, addressing accessibility for blind and low vision (BLV) users is increasingly critical. Researchers have proposed an AI "sighted guide" to help us...
Jazmin Collins, Sharon Y Lin, Tianqi Liu, Andrea Stevenson Won, Shiri Azenkot
Think Before You Lie: How Reasoning Improves Honesty
While existing evaluations of large language models (LLMs) measure deception rates, the underlying conditions that give rise to deceptive behavior are poorly understood. We investigate this questio...
Ann Yuan, Asma Ghandeharioun, Carter Blum, Alicia Machado, Jessica Hoffmann, Daphne Ippolito, Mar...
Towards a Neural Debugger for Python
Training large language models (LLMs) on Python execution traces grounds them in code execution and enables the line-by-line execution prediction of whole Python programs, effectively turning them ...
Maximilian Beck, Jonas Gehring, Jannik Kossen, Gabriel Synnaeve
Model Merging in the Era of Large Language Models: Methods, Applications, and Future Directions
Model merging has emerged as a transformative paradigm for combining the capabilities of multiple neural networks into a single unified model without additional training. With the rapid proliferati...
Mingyang Song, Mao Zheng
Adaptive Clinical-Aware Latent Diffusion for Multimodal Brain Image Generation and Missing Modality Imputation
Multimodal neuroimaging provides complementary insights for Alzheimer's disease diagnosis, yet clinical datasets frequently suffer from missing modalities. We propose ACADiff, a framework that synt...
Rong Zhou, Houliang Zhou, Yao Su, Brian Y. Chen, Yu Zhang, Lifang He, Alzheimer's Disease Neuroim...
AI-Enabled Data-driven Intelligence for Spectrum Demand Estimation
Accurately forecasting spectrum demand is a key component for efficient spectrum resource allocation and management. With the rapid growth in demand for wireless services, mobile network operators ...
Colin Brown, Mohamad Alkadamani, Halim Yanikomeroglu
Thinking to Recall: How Reasoning Unlocks Parametric Knowledge in LLMs
While reasoning in LLMs plays a natural role in math, code generation, and multi-hop factual questions, its effect on simple, single-hop factual questions remains unclear. Such questions do not req...
Zorik Gekhman, Roee Aharoni, Eran Ofek, Mor Geva, Roi Reichart, Jonathan Herzig
Stepping VLMs onto the Court: Benchmarking Spatial Intelligence in Sports
Sports have long attracted broad attention as they push the limits of human physical and cognitive capabilities. Amid growing interest in spatial intelligence for vision-language models (VLMs), spo...
Yuchen Yang, Yuqing Shao, Duxiu Huang, Linfeng Dong, Yifei Liu, Suixin Tang, Xiang Zhou, Yuanyuan...
A Survey on Cloud-Based 6G Deployments: Current Solutions, Future Directions and Open Challenges
The next generation of cellular networks is designed to provide ubiquitous connectivity to a wide range of devices. As Telecommunication Service Providers (TSPs) increasingly collaborate with publi...
Tolga O. Atalay, Alireza Famili, Amirreza Ghafoori, Angelos Stavrou
MSSR: Memory-Aware Adaptive Replay for Continual LLM Fine-Tuning
Continual fine-tuning of large language models (LLMs) is becoming increasingly crucial as these models are deployed in dynamic environments where tasks and data distributions evolve over time. Whil...
Yiyang Lu, Yu He, Jianlong Chen, Hongyuan Zha