Papers
Research papers from arXiv and related sources
LSAI: A Large Small AI Model Codesign Framework for Agentic Robot Scenarios
The development of Artificial Intelligence (AI) has enabled agentic robots an appealing paradigm for various applications, such as research and rescue in complex environment. In this context, the n...
Longyu Zhou, Supeng Leng, Tianhao Liang, Jianping Yao
CurvZO: Adaptive Curvature-Guided Sparse Zeroth-Order Optimization for Efficient LLM Fine-Tuning
Fine-tuning large language models (LLMs) with backpropagation achieves high performance but incurs substantial memory overhead, limiting scalability on resource-constrained hardware. Zeroth-order (...
Shuo Wang, Ziyu Chen, Ming Tang
Charmed baryon decays at Belle and Belle II
Belle and Belle II experiments have collected $e^+e^-$ collision data with center-of-mass energies at or near the $Υ(4S)$ resonance. Using total $1.4\,\mathrm{ab}^{-1}$ combined dataset, we present...
Jaeyoung Kim
Probing How Scalable Table Data Enhances General Long-Context Reasoning
As real-world tasks grow increasingly complex, long-context reasoning has become a core capability for Large Language Models (LLMs). However, few studies explore which data types are effective for ...
Huaibing Xie, Guoliang Zhao, Yang Liu, Shihan Dou, Siming Huang, Yanling Xiao, Shaolei Wang, Yiti...
When Exploration Comes for Free with Mixture-Greedy: Do we need UCB in Diversity-Aware Multi-Armed Bandits?
Efficient selection among multiple generative models is increasingly important in modern generative AI, where sampling from suboptimal models is costly. This problem can be formulated as a multi-ar...
Bahar Dibaei Nia, Farzan Farnia
Compensating Visual Insufficiency with Stratified Language Guidance for Long-Tail Class Incremental Learning
Long-tail class incremental learning (LT CIL) remains highly challenging because the scarcity of samples in tail classes not only hampers their learning but also exacerbates catastrophic forgetting...
Xi Wang, Xu Yang, Donghao Sun, Cheng Deng
Comprehensive Dosimetric Verification and Positional Sensitivity Analysis in Brachytherapy: A Unified ESAPI Tool for HDR and LDR Treatments
This study presents the development and validation of an independent software tool based on the Varian Eclipse Scripting API (ESAPI) for multi-modal brachytherapy Quality Assurance (QA). The tool a...
J. A. Valgoma
Data-Free Layer-Adaptive Merging via Fisher Information for Long-to-Short Reasoning LLMs
Model merging has emerged as a practical approach to combine capabilities of specialized large language models (LLMs) without additional training. In the Long-to-Short (L2S) scenario, merging a bas...
Tian Xia
Rethinking Token Reduction for Large Vision-Language Models
Large Vision-Language Models (LVLMs) excel in visual understanding and reasoning, but the excessive visual tokens lead to high inference costs. Although recent token reduction methods mitigate this...
Yi Wang, Haofei Zhang, Qihan Huang, Anda Cao, Gongfan Fang, Wei Wang, Xuan Jin, Jie Song, Mingli ...
A Job I Like or a Job I Can Get: Designing Job Recommender Systems Using Field Experiments
Recommendation systems (RSs) are increasingly used to guide job seekers on online platforms, yet the algorithms currently deployed are typically optimized for predictive objectives such as clicks, ...
Guillaume Bied, Philippe Caillou, Bruno Crépon, Christophe Gaillac, Elia Pérennes, Michèle Sebag
Structured Visual Narratives Undermine Safety Alignment in Multimodal Large Language Models
Multimodal Large Language Models (MLLMs) extend text-only LLMs with visual reasoning, but also introduce new safety failure modes under visually grounded instructions. We study comic-template jailb...
Rui Yang Tan, Yujia Hu, Roy Ka-Wei Lee
MIND: Multi-agent inference for negotiation dialogue in travel planning
While Multi-Agent Debate (MAD) research has advanced, its efficacy in coordinating complex stakeholder interests such as travel planning remains largely unexplored. To bridge this gap, we propose M...
Hunmin Do, Taejun Yoon, Kiyong Jung
Reasoning Provenance for Autonomous AI Agents: Structured Behavioral Analytics Beyond State Checkpoints and Execution Traces
As AI agents transition from human-supervised copilots to autonomous platform infrastructure, the ability to analyze their reasoning behavior across populations of investigations becomes a pressing...
Neelmani Vispute
AI Token Futures Market: Commoditization of Compute and Derivatives Contract Design
As large language models (LLMs) and vision-language-action models (VLAs) become widely deployed, the tokens consumed by AI inference are evolving into a new type of commodity. This paper systematic...
Yicai Xing
Mirage The Illusion of Visual Understanding
Multimodal AI systems have achieved remarkable performance across a broad range of real-world tasks, yet the mechanisms underlying visual-language reasoning remain surprisingly poorly understood. W...
Mohammad Asadi, Jack W. O'Sullivan, Fang Cao, Tahoura Nedaee, Kamyar Fardi, Fei-Fei Li, Ehsan Ade...
Is AI Ready for Multimodal Hate Speech Detection? A Comprehensive Dataset and Benchmark Evaluation
Hate speech online targets individuals or groups based on identity attributes and spreads rapidly, posing serious social risks. Memes, which combine images and text, have emerged as a nuanced vehic...
Rui Xing, Qi Chai, Jie Ma, Jing Tao, Pinghui Wang, Shuming Zhang, Xinping Wang, Hao Wang
Optimizing Multi-Agent Weather Captioning via Text Gradient Descent: A Training-Free Approach with Consensus-Aware Gradient Fusion
Generating interpretable natural language captions from weather time series data remains a significant challenge at the intersection of meteorological science and natural language processing. While...
Shixu Liu
Combined thermographic measurement and heat-flux compensation methods for aerodynamic heating evaluation in hypersonic flight
Novel thermographic measurement and heat-flux compensation methods combined for evaluating aerodynamic heating in hypersonic flight were developed using high-speed thermography. A hypersonic spheri...
Kento Inokuma, Aiko Yakeno, Yoshiyuki Watanabe, Kiyonobu Ohtani
TAMTRL: Teacher-Aligned Reward Reshaping for Multi-Turn Reinforcement Learning in Long-Context Compression
The rapid progress of large language models (LLMs) has led to remarkable performance gains across a wide range of tasks. However, when handling long documents that exceed the model's context window...
Li Wang, Yandong Wang, Xin Yu, Kui Zhang, Tianhao Peng, Wenjun Wu
OmniFM: Toward Modality-Robust and Task-Agnostic Federated Learning for Heterogeneous Medical Imaging
Federated learning (FL) has become a promising paradigm for collaborative medical image analysis, yet existing frameworks remain tightly coupled to task-specific backbones and are fragile under het...
Meilin Liu, Jiaying Wang, Jing Shan