Papers
Research papers from arXiv and related sources
Confidence-Calibrated Small-Large Language Model Collaboration for Cost-Efficient Reasoning
Large language models (LLMs) demonstrate superior reasoning capabilities compared to small language models (SLMs), but incur substantially higher costs. We propose COllaborative REAsoner (COREA), a...
Chuang Zhang, Zizhen Zhu, Yihao Wei, Bing Tian, Junyi Liu, Henan Wang, Xavier Wang, Yaxiao Liu
ErrorLLM: Modeling SQL Errors for Text-to-SQL Refinement
Despite the remarkable performance of large language models (LLMs) in text-to-SQL (SQL generation), correctly producing SQL queries remains challenging during initial generation. The SQL refinement...
Zijin Hong, Hao Chen, Zheng Yuan, Qinggang Zhang, Luyao Zhuang, Qing Liao, Feiran Huang, Yangqiu ...
A Generalist Model Including Evolved Star Mass and Age
Determining precise stellar ages and masses for evolved giants is crucial for Galactic archaeology but challenged by spectral degeneracies. Gaia's low-resolution XP spectra offer a unique opportuni...
Mengmeng Zhang, Yude Bu, Siqi Wang, Shanshan Li, Jiangchuan Zhang, Jingzhen Sun, Yuhang Zhang, Ke...
HyperParallel: A Supernode-Affinity AI Framework
The emergence of large-scale, sparse, multimodal, and agentic AI models has coincided with a shift in hardware toward supernode architectures that integrate hundreds to thousands of accelerators wi...
Xin Zhang, Beilei Sun, Teng Su, Qinghua Zhang, Chong Bao, Lei Chen, Xuefeng Jin
Understanding Parents' Desires in Moderating Children's Interactions with GenAI Chatbots through LLM-Generated Probes
This paper studies how parents want to moderate children's interactions with Generative AI chatbots, with the goal of informing the design of future GenAI parental control tools. We first used an L...
John Driscoll, Yulin Chen, Viki Shi, Izak Vucharatavintara, Yaxing Yao, Haojian Jin
Soft Semi-active Back Support Device with Adaptive Force Profiles using Variable-elastic Actuation and Weight Feedback
Portable active back support devices (BSDs) offer tunable assistance but are often bulky and heavy, limiting their usability. In contrast, passive BSDs are lightweight and compact but lack the abil...
Rohan Khatavkar, The Bach Nguyen, Inseung Kang, Hyunglae Lee, Jiefeng Sun
Scalar quasinormal modes of rotating black holes in parity-violating gravity
Recently, an exact rotating black hole solution in a parity-violating theory of gravity was obtained via a conformal transformation of the Kerr solution in general relativity, with parity-violating...
Hiroaki W. H. Tahara, Hayato Motohashi, Kazufumi Takahashi, Vicharit Yingcharoenrat
Order Is Not Layout: Order-to-Space Bias in Image Generation
We study a systematic bias in modern image generation models: the mention order of entities in text spuriously determines spatial layout and entity--role binding. We term this phenomenon Order-to-S...
Yongkang Zhang, Zonglin Zhao, Yuechen Zhang, Fei Ding, Pei Li, Wenxuan Wang
Large-Language-Model-Guided State Estimation for Partially Observable Task and Motion Planning
Robot planning in partially observable environments, where not all objects are known or visible, is a challenging problem, as it requires reasoning under uncertainty through partially observable Ma...
Yoonwoo Kim, Raghav Arora, Roberto Martín-Martín, Peter Stone, Ben Abbatematteo, Yoonchang Sung
Quantum anomaly for benchmarking quantum computing
Given the rapid advances in quantum computing hardware, establishing systematic strategies for verifying the correctness of quantum computations has become increasingly important. Exploiting the fa...
Tomoya Hayata, Arata Yamamoto
AI4S-SDS: A Neuro-Symbolic Solvent Design System via Sparse MCTS and Differentiable Physics Alignment
Automated design of chemical formulations is a cornerstone of materials science, yet it requires navigating a high-dimensional combinatorial space involving discrete compositional choices and conti...
Jiangyu Chen
Mathematicians in the age of AI
Recent developments show that AI can prove research-level theorems in mathematics, both formally and informally. This essay urges mathematicians to stay up-to-date with the technology, to consider ...
Jeremy Avigad
CONCUR: Benchmarking LLMs for Concurrent Code Generation
Leveraging Large Language Models (LLMs) for code generation has increasingly emerged as a common practice in the domain of software engineering. Relevant benchmarks have been established to evaluat...
Jue Huang, Tarek Mahmud, Corina Pasareanu, Guowei Yang
MAGE: Meta-Reinforcement Learning for Language Agents toward Strategic Exploration and Exploitation
Large Language Model (LLM) agents have demonstrated remarkable proficiency in learned tasks, yet they often struggle to adapt to non-stationary environments with feedback. While In-Context Learning...
Lu Yang, Zelai Xu, Minyang Xie, Jiaxuan Gao, Zhao Shok, Yu Wang, Yi Wu
MIND: Unified Inquiry and Diagnosis RL with Criteria Grounded Clinical Supports for Psychiatric Consultation
Large language models (LLMs) have advanced medical dialogue systems, yet psychiatric consultation poses substantially higher demands due to subjective ambiguity and comorbidity complexity: an agent...
Guoyi Li, Shihao Xu, Jiatong Ma, Yunyun Han, Jianhua Chen, Yafeng Deng
Local Shapley: Model-Induced Locality and Optimal Reuse in Data Valuation
The Shapley value provides a principled foundation for data valuation, but exact computation is #P-hard due to the exponential coalition space. Existing accelerations remain global and ignore a str...
Xuan Yang, Hsi-Wen Chen, Ming-Syan Chen, Jian Pei
Automated Analysis of Ripple-Scale Gravity Wave Structures in the Mesosphere Using Convolutional Neural Networks
The mesosphere and lower thermosphere (MLT), spanning approximately 80--100~km in altitude, is a region of intense dynamical activity where atmospheric gravity waves amplify due to decreasing air d...
Jiahui Hu, Alan Liu, Adriana Feener, Jing Li, Tao Li, Wenjun Dong
InEdit-Bench: Benchmarking Intermediate Logical Pathways for Intelligent Image Editing Models
Multimodal generative models have made significant strides in image editing, demonstrating impressive performance on a variety of static tasks. However, their proficiency typically does not extend ...
Zhiqiang Sheng, Xumeng Han, Zhiwei Zhang, Zenghui Xiong, Yifan Ding, Aoxiang Ping, Xiang Li, Tong...
Exploring Multiple Converged States of Network Configurations
Due to the policy-rich BGP, multiple stable forwarding states might exist for the same network topology and configuration, rendering the network convergence non-deterministic. This paper proves tha...
Shunyu Yang, Dan Wang, Peng Zhang
Empirical Evaluation of No Free Lunch Violations in Permutation-Based Optimization
The No Free Lunch (NFL) theorem guarantees equal average performance only under uniform sampling of a function space closed under permutation (c.u.p.). We ask when this averaging ceases to reflect ...
Grzegorz Sroka