arXiv subjects

Jun Wang

Publications and source records attributed to Jun Wang.

At least 451 records · Page 25Linked to original sources

arXiv2025

Ultralong-lived Coherent States in Eu$^{3+}$:Y$_2$O$_3$ Optical Ceramics for Quantum Memories

Rare earth ions (REI) in solid materials are among the leading systems for quantum technology applications. However, developing practical REI quantum devices with long-lived coherent states remains challenging due to great growth difficulties of high-quality REI materials and a lack of comprehensive understanding of REI's decoherence mechanisms. Here we realize a record optical coherence time of 421.5 $\pm$ 10.5 $μ$s for the $^7$F$_0\rightarrow^5$D$_0$ transition and more than 30 hours lifetime for the $^7$F$_0$ hyperfine spin states in Eu$^{3+}$:Y$_2$O$_3$ optical ceramics. We report the elimination of two-level-system induced optical decoherence in short-range ordered crystals. Meanwhile, a new decoherence mechanism caused by new kinds of perturbing magnetic centers is identified below 1.5 K. We further demonstrate the coherent light storage over 5 $μ$s by using the atomic frequency comb protocol. These results open up prospects for the realization of practical quantum memories and large scale quantum communications with REI optical ceramics.

quant-ph↗

arXiv2025

ThinkBench: Dynamic Out-of-Distribution Evaluation for Robust LLM Reasoning

Evaluating large language models (LLMs) poses significant challenges, particularly due to issues of data contamination and the leakage of correct answers. To address these challenges, we introduce ThinkBench, a novel evaluation framework designed to evaluate LLMs' reasoning capability robustly. ThinkBench proposes a dynamic data generation method for constructing out-of-distribution (OOD) datasets and offers an OOD dataset that contains 2,912 samples drawn from reasoning tasks. ThinkBench unifies the evaluation of reasoning models and non-reasoning models. We evaluate 16 LLMs and 4 PRMs under identical experimental conditions and show that most of the LLMs' performance are far from robust and they face a certain level of data leakage. By dynamically generating OOD datasets, ThinkBench effectively provides a reliable evaluation of LLMs and reduces the impact of data contamination.

cs.CL↗

arXiv2025

DistRL: An Asynchronous Distributed Reinforcement Learning Framework for On-Device Control Agents

On-device control agents, especially on mobile devices, are responsible for operating mobile devices to fulfill users' requests, enabling seamless and intuitive interactions. Integrating Multimodal Large Language Models (MLLMs) into these agents enhances their ability to understand and execute complex commands, thereby improving user experience. However, fine-tuning MLLMs for on-device control presents significant challenges due to limited data availability and inefficient online training processes. This paper introduces DistRL, a novel framework designed to enhance the efficiency of online RL fine-tuning for mobile device control agents. DistRL employs centralized training and decentralized data acquisition to ensure efficient fine-tuning in the context of dynamic online interactions. Additionally, the framework is backed by our tailor-made RL algorithm, which effectively balances exploration with the prioritized utilization of collected data to ensure stable and robust training. Our experiments show that, on average, DistRL delivers a 3X improvement in training efficiency and enables training data collection 2.4X faster than the leading synchronous multi-machine methods. Notably, after training, DistRL achieves a 20% relative improvement in success rate compared to state-of-the-art methods on general Android tasks from an open benchmark, significantly outperforming existing approaches while maintaining the same training time. These results validate DistRL as a scalable and efficient solution, offering substantial improvements in both training efficiency and agent performance for real-world, in-the-wild device control tasks.

cs.LG↗

arXiv2025

MMRAG: Multi-Mode Retrieval-Augmented Generation with Large Language Models for Biomedical In-Context Learning

Objective: To optimize in-context learning in biomedical natural language processing by improving example selection. Methods: We introduce a novel multi-mode retrieval-augmented generation (MMRAG) framework, which integrates four retrieval strategies: (1) Random Mode, selecting examples arbitrarily; (2) Top Mode, retrieving the most relevant examples based on similarity; (3) Diversity Mode, ensuring variation in selected examples; and (4) Class Mode, selecting category-representative examples. This study evaluates MMRAG on three core biomedical NLP tasks: Named Entity Recognition (NER), Relation Extraction (RE), and Text Classification (TC). The datasets used include BC2GM for gene and protein mention recognition (NER), DDI for drug-drug interaction extraction (RE), GIT for general biomedical information extraction (RE), and HealthAdvice for health-related text classification (TC). The framework is tested with two large language models (Llama2-7B, Llama3-8B) and three retrievers (Contriever, MedCPT, BGE-Large) to assess performance across different retrieval strategies. Results: The results from the Random mode indicate that providing more examples in the prompt improves the model's generation performance. Meanwhile, Top mode and Diversity mode significantly outperform Random mode on the RE (DDI) task, achieving an F1 score of 0.9669, a 26.4% improvement. Among the three retrievers tested, Contriever outperformed the other two in a greater number of experiments. Additionally, Llama 2 and Llama 3 demonstrated varying capabilities across different tasks, with Llama 3 showing a clear advantage in handling NER tasks. Conclusion: MMRAG effectively enhances biomedical in-context learning by refining example selection, mitigating data scarcity issues, and demonstrating superior adaptability for NLP-driven healthcare applications.

cs.CL↗

arXiv2025

Coherency Improved Explainable Recommendation via Large Language Model

Explainable recommender systems are designed to elucidate the explanation behind each recommendation, enabling users to comprehend the underlying logic. Previous works perform rating prediction and explanation generation in a multi-task manner. However, these works suffer from incoherence between predicted ratings and explanations. To address the issue, we propose a novel framework that employs a large language model (LLM) to generate a rating, transforms it into a rating vector, and finally generates an explanation based on the rating vector and user-item information. Moreover, we propose utilizing publicly available LLMs and pre-trained sentiment analysis models to automatically evaluate the coherence without human annotations. Extensive experimental results on three datasets of explainable recommendation show that the proposed framework is effective, outperforming state-of-the-art baselines with improvements of 7.3\% in explainability and 4.4\% in text quality.

cs.IR↗

arXiv2025

Retrieval-Augmented Process Reward Model for Generalizable Mathematical Reasoning

While large language models (LLMs) have significantly advanced mathematical reasoning, Process Reward Models (PRMs) have been developed to evaluate the logical validity of reasoning steps. However, PRMs still struggle with out-of-distribution (OOD) challenges. This paper identifies key OOD issues, including step OOD, caused by differences in reasoning patterns across model types and sizes, and question OOD, which arises from dataset shifts between training data and real-world problems. To address these issues, we introduce Retrieval-Augmented Process Reward Model (RetrievalPRM), a novel framework designed to tackle these OOD issues. By utilizing a two-stage retrieval-enhanced mechanism, RetrievalPRM retrieves semantically similar questions and steps as a warmup, enhancing PRM's ability to evaluate target steps and improving generalization and reasoning consistency across different models and problem types. Our extensive experiments demonstrate that RetrievalPRM outperforms existing baselines across multiple real-world datasets. Our open-source contributions include a retrieval-enhanced dataset, a tuning framework for PRM training, and the RetrievalPRM model, establishing a new standard for PRM performance.

cs.AI↗

arXiv2025

Activation-aware Probe-Query: Effective Key-Value Retrieval for Long-Context LLMs Inference

Recent advances in large language models (LLMs) have showcased exceptional performance in long-context tasks, while facing significant inference efficiency challenges with limited GPU memory. Existing solutions first proposed the sliding-window approach to accumulate a set of historical \textbf{key-value} (KV) pairs for reuse, then further improvements selectively retain its subsets at each step. However, due to the sparse attention distribution across a long context, it is hard to identify and recall relevant KV pairs, as the attention is distracted by massive candidate pairs. Additionally, we found it promising to select representative tokens as probe-Query in each sliding window to effectively represent the entire context, which is an approach overlooked by existing methods. Thus, we propose \textbf{ActQKV}, a training-free, \textbf{Act}ivation-aware approach that dynamically determines probe-\textbf{Q}uery and leverages it to retrieve the relevant \textbf{KV} pairs for inference. Specifically, ActQKV monitors a token-level indicator, Activation Bias, within each context window, enabling the proper construction of probe-Query for retrieval at pre-filling stage. To accurately recall the relevant KV pairs and minimize the irrelevant ones, we design a dynamic KV cut-off mechanism guided by information density across layers at the decoding stage. Experiments on the Long-Bench and $\infty$ Benchmarks demonstrate its state-of-the-art performance with competitive inference quality and resource efficiency.

cs.CL↗

arXiv2025

STaR-SQL: Self-Taught Reasoner for Text-to-SQL

Generating step-by-step "chain-of-thought" rationales has proven effective for improving the performance of large language models on complex reasoning tasks. However, applying such techniques to structured tasks, such as text-to-SQL, remains largely unexplored. In this paper, we introduce Self-Taught Reasoner for text-to-SQL (STaR-SQL), a novel approach that reframes SQL query generation as a reasoning-driven process. Our method prompts the LLM to produce detailed reasoning steps for SQL queries and fine-tunes it on rationales that lead to correct outcomes. Unlike traditional methods, STaR-SQL dedicates additional test-time computation to reasoning, thereby positioning LLMs as spontaneous reasoners rather than mere prompt-based agents. To further scale the inference process, we incorporate an outcome-supervised reward model (ORM) as a verifier, which enhances SQL query accuracy. Experimental results on the challenging Spider benchmark demonstrate that STaR-SQL significantly improves text-to-SQL performance, achieving an execution accuracy of 86.6%. This surpasses a few-shot baseline by 31.6% and a baseline fine-tuned to predict answers directly by 18.0%. Additionally, STaR-SQL outperforms agent-like prompting methods that leverage more powerful yet closed-source models such as GPT-4. These findings underscore the potential of reasoning-augmented training for structured tasks and open the door to extending self-improving reasoning models to text-to-SQL generation and beyond.

cs.CL↗

arXiv2025

Direct Value Optimization: Improving Chain-of-Thought Reasoning in LLMs with Refined Values

We introduce Direct Value Optimization (DVO), an innovative reinforcement learning framework for enhancing large language models in complex reasoning tasks. Unlike traditional methods relying on preference labels, DVO utilizes value signals at individual reasoning steps, optimizing models via a mean squared error loss. The key benefit of DVO lies in its fine-grained supervision, circumventing the need for labor-intensive human annotations. Target values within the DVO are estimated using either Monte Carlo Tree Search or an outcome value model. Our empirical analysis on both mathematical and commonsense reasoning tasks shows that DVO consistently outperforms existing offline preference optimization techniques, even with fewer training steps. These findings underscore the importance of value signals in advancing reasoning capabilities and highlight DVO as a superior methodology under scenarios lacking explicit human preference information.

cs.CL↗

arXiv2025

Boost, Disentangle, and Customize: A Robust System2-to-System1 Pipeline for Code Generation

Large language models (LLMs) have demonstrated remarkable capabilities in various domains, particularly in system 1 tasks, yet the intricacies of their problem-solving mechanisms in system 2 tasks are not sufficiently explored. Recent research on System2-to-System1 methods surge, exploring the System 2 reasoning knowledge via inference-time computation and compressing the explored knowledge into System 1 process. In this paper, we focus on code generation, which is a representative System 2 task, and identify two primary challenges: (1) the complex hidden reasoning processes and (2) the heterogeneous data distributions that complicate the exploration and training of robust LLM solvers. To tackle these issues, we propose a novel BDC framework that explores insightful System 2 knowledge of LLMs using a MC-Tree-Of-Agents algorithm with mutual \textbf{B}oosting, \textbf{D}isentangles the heterogeneous training data for composable LoRA-experts, and obtain \textbf{C}ustomized problem solver for each data instance with an input-aware hypernetwork to weight over the LoRA-experts, offering effectiveness, flexibility, and robustness. This framework leverages multiple LLMs through mutual verification and boosting, integrated into a Monte-Carlo Tree Search process enhanced by reflection-based pruning and refinement. Additionally, we introduce the DisenLora algorithm, which clusters heterogeneous data to fine-tune LLMs into composable Lora experts, enabling the adaptive generation of customized problem solvers through an input-aware hypernetwork. This work lays the groundwork for advancing LLM capabilities in complex reasoning tasks, offering a novel System2-to-System1 solution.

cs.AI↗

arXiv2025

Utilizing Effective Dynamic Graph Learning to Shield Financial Stability from Risk Propagation

Financial risks can propagate across both tightly coupled temporal and spatial dimensions, posing significant threats to financial stability. Moreover, risks embedded in unlabeled data are often difficult to detect. To address these challenges, we introduce GraphShield, a novel approach with three key innovations: Enhanced Cross-Domain Infor mation Learning: We propose a dynamic graph learning module to improve information learning across temporal and spatial domains. Advanced Risk Recognition: By leveraging the clustering characteristics of risks, we construct a risk recognizing module to enhance the identification of hidden threats. Risk Propagation Visualization: We provide a visualization tool for quantifying and validating nodes that trigger widespread cascading risks. Extensive experiments on two real-world and two open-source datasets demonstrate the robust performance of our framework. Our approach represents a significant advancement in leveraging artificial intelligence to enhance financial stability, offering a powerful solution to mitigate the spread of risks within financial networks.

q-fin.RM↗

arXiv2025

HammerBench: Fine-Grained Function-Calling Evaluation in Real Mobile Device Scenarios

Evaluating the performance of LLMs in multi-turn human-agent interactions presents significant challenges, particularly due to the complexity and variability of user behavior. In this paper, we introduce HammerBench, a novel benchmark framework for assessing LLMs' function-calling capabilities in real-world, multi-turn dialogues. HammerBench simulates diverse mobile assistant use cases, incorporating imperfect instructions, dynamic question-answer trajectories, intent and argument shifts, and the indirect use of external information through pronouns. To construct this benchmark, we curate a comprehensive dataset derived from popular mobile app functionalities and anonymized user logs, complemented by a cost-effective data generation pipeline leveraging open-source models. HammerBench is further augmented with fine-grained interaction snapshots and metrics, enabling detailed evaluation of function-calling performance across individual conversational turns. We demonstrate the effectiveness of HammerBench by evaluating several leading LLMs and uncovering key performance trends. Our experiments reveal that different types of parameter name errors are a significant source of failure across different interaction scenarios, highlighting critical areas for further improvement in LLM robustness for mobile assistant applications.

cs.CL↗

arXiv2025

Estimating the Lateral Motion States of an Underwater Robot by Propeller Wake Sensing Using an Artificial Lateral Line

The artificial lateral line (ALL), comprising distributed flow sensors, has been successful in sensing motion states of bioinspired underwater robots like robotic fish. However, its application to robots driven by rotating propellers remains unexplored due to the complexity of propeller wake flow. This paper investigates the feasibility of using ALL to sense propeller wake for underwater robot leader-follower formation. To estimate the lateral motion states of a leader propeller, this paper designs a multi-output deep learning network that extracts temporal and spatial features from distributed pressure measurements of propeller wake. Extensive experiments are conducted on a designed testbed, the results of which validate the effectiveness of the proposed propeller wake sensing method.

cs.RO↗

arXiv2025

A Tutorial on LLM Reasoning: Relevant Methods behind ChatGPT o1

OpenAI o1 has shown that applying reinforcement learning to integrate reasoning steps directly during inference can significantly improve a model's reasoning capabilities. This result is exciting as the field transitions from the conventional autoregressive method of generating answers to a more deliberate approach that models the slow-thinking process through step-by-step reasoning training. Reinforcement learning plays a key role in both the model's training and decoding processes. In this article, we present a comprehensive formulation of reasoning problems and investigate the use of both model-based and model-free approaches to better support this slow-thinking framework.

cs.AI↗

arXiv2025

Intensity-Spatial Dual Masked Autoencoder for Multi-Scale Feature Learning in Chest CT Segmentation

In the field of medical image segmentation, challenges such as indistinct lesion features, ambiguous boundaries,and multi-scale characteristics have long revailed. This paper proposes an improved method named Intensity-Spatial Dual Masked AutoEncoder (ISD-MAE). Based on the tissue-contrast semi-masked autoencoder, a Masked AutoEncoder (MAE) branch is introduced to perform intensity masking and spatial masking operations on chest CT images for multi-scale feature learning and segmentation tasks. The model utilizes a dual-branch structure and contrastive learning to enhance the ability to learn tissue features and boundary details. Experiments are conducted on multiple 2D and 3D datasets. The results show that ISD-MAE significantly outperforms other methods in 2D pneumonia and mediastinal tumor segmentation tasks. For example, the Dice score reaches 90.10% on the COVID19 LESION dataset, and the performance is relatively stable. However, there is still room for improvement on 3D datasets. In response to this, improvement directions are proposed, including optimizing the loss function, using enhanced 3D convolution blocks, and processing datasets from multiple perspectives.Our code is available at:https://github.com/prowontheus/ISD-MAE.

eess.IV↗

arXiv2025

Enhancing RAG with Active Learning on Conversation Records: Reject Incapables and Answer Capables

Retrieval-augmented generation (RAG) is a key technique for leveraging external knowledge and reducing hallucinations in large language models (LLMs). However, RAG still struggles to fully prevent hallucinated responses. To address this, it is essential to identify samples prone to hallucination or guide LLMs toward correct responses, which experts then annotate to develop high-quality datasets for refining LLMs. However, the growing scarcity of such datasets makes their creation challenging. This paper proposes using the vast amount of conversations from widespread LLM usage to build these datasets, training LLMs to avoid hallucination-prone questions while accurately responding to manageable ones. Given the impracticality of expert-annotating all conversation records, the paper introduces AL4RAG, which uses active learning to select the most suitable conversation samples for annotation, optimizing performance within an annotation budget. Additionally, recognizing that traditional active learning methods are not fully compatible with RAG due to unsuitable distance metrics, we develop a novel sample distance measurement for RAG active learning. Extensive experiments show that our method consistently outperforms baselines across multiple metrics.

cs.CL↗

arXiv2025

On uniqueness of functions in the extended Selberg class with moving targets

We study the question of when two functions L_1,L_2 in the extended Selberg class are identical in terms of the zeros of L_i-h(i=1,2). Here, the meromorphic function h is called moving target. With the assumption on the growth order of h, we prove that L_1\equiv L_2 if L_1-h and L_2-h have the same zeros counting multiplicities. Moreover, we also construct some examples to show that the assumption is necessary. Compared with the known methods in the literature of this area, we developed a new strategy which is based on the transcendental directions first proposed in the study of distribution of Julia set in complex dynamical system. This may be of independent interest.

math.CV↗

arXiv2025

Lightweight Neural App Control

This paper introduces a novel mobile phone control architecture, Lightweight Multi-modal App Control (LiMAC), for efficient interactions and control across various Android apps. LiMAC takes as input a textual goal and a sequence of past mobile observations, such as screenshots and corresponding UI trees, to generate precise actions. To address the computational constraints inherent to smartphones, we introduce a small Action Transformer (AcT) integrated with a fine-tuned vision-language model (VLM) for real-time decision-making and task execution. We evaluate LiMAC on two open-source mobile control datasets, demonstrating the superior performance of our small-form-factor approach against fine-tuned versions of open-source VLMs, such as Florence2 and Qwen2-VL. It also significantly outperforms prompt engineering baselines utilising closed-source foundation models like GPT-4o. More specifically, LiMAC increases the overall action accuracy by up to 19% compared to fine-tuned VLMs, and up to 42% compared to prompt-engineering baselines.

cs.AI↗