arXiv subjects

Jun Wang

Publications and source records attributed to Jun Wang.

At least 325 records · Page 18Linked to original sources

arXiv2025

Conformal Temporal Logic Planning using Large Language Models

This paper addresses planning problems for mobile robots. We consider missions that require accomplishing multiple high-level sub-tasks, expressed in natural language (NL), in a temporal and logical order. To formally define the mission, we treat these sub-tasks as atomic predicates in a Linear Temporal Logic (LTL) formula. We refer to this task specification framework as LTL-NL. Our goal is to design plans, defined as sequences of robot actions, accomplishing LTL-NL tasks. This action planning problem cannot be solved directly by existing LTL planners because of the NL nature of atomic predicates. To address it, we propose HERACLEs, a hierarchical neuro-symbolic planner that relies on a novel integration of (i) existing symbolic planners generating high-level task plans determining the order at which the NL sub-tasks should be accomplished; (ii) pre-trained Large Language Models (LLMs) to design sequences of robot actions based on these task plans; and (iii) conformal prediction acting as a formal interface between (i) and (ii) and managing uncertainties due to LLM imperfections. We show, both theoretically and empirically, that HERACLEs can achieve user-defined mission success rates. Finally, we provide comparative experiments demonstrating that HERACLEs outperforms LLM-based planners that require the mission to be defined solely using NL. Additionally, we present examples demonstrating that our approach enhances user-friendliness compared to conventional symbolic approaches.

cs.RO↗

arXiv2025

xGen-MM (BLIP-3): A Family of Open Large Multimodal Models

This paper introduces BLIP-3, an open framework for developing Large Multimodal Models (LMMs). The framework comprises meticulously curated datasets, a training recipe, model architectures, and a resulting suite of LMMs. We release 4B and 14B models, including both the pre-trained base model and the instruction fine-tuned ones. Our models undergo rigorous evaluation across a range of tasks, including both single and multi-image benchmarks. Our models demonstrate competitive performance among open-source LMMs with similar model sizes. Our resulting LMMs demonstrate competitive performance among open-source LMMs with similar model sizes, with the ability to comprehend interleaved image-text inputs. Our training code, models, and all datasets used in this work, including the three largescale datasets we create and the preprocessed ones, will be open-sourced to better support the research community.

cs.CV↗

arXiv2025

Agent4FaceForgery: Multi-Agent LLM Framework for Realistic Face Forgery Detection

Face forgery detection faces a critical challenge: a persistent gap between offline benchmarks and real-world efficacy,which we attribute to the ecological invalidity of training data.This work introduces Agent4FaceForgery to address two fundamental problems: (1) how to capture the diverse intents and iterative processes of human forgery creation, and (2) how to model the complex, often adversarial, text-image interactions that accompany forgeries in social media. To solve this,we propose a multi-agent framework where LLM-poweredagents, equipped with profile and memory modules, simulate the forgery creation process. Crucially, these agents interact in a simulated social environment to generate samples labeled for nuanced text-image consistency, moving beyond simple binary classification. An Adaptive Rejection Sampling (ARS) mechanism ensures data quality and diversity. Extensive experiments validate that the data generated by our simulationdriven approach brings significant performance gains to detectors of multiple architectures, fully demonstrating the effectiveness and value of our framework.

cs.CV↗

arXiv2025

Kolb-Based Experiential Learning for Generalist Agents with Human-Level Kaggle Data Science Performance

Human expertise emerges through iterative cycles of interaction, reflection, and internal model updating, which are central to cognitive theories such as Kolb's experiential learning and Vygotsky's zone of proximal development. In contrast, current AI systems, particularly LLM agents, rely on static pre-training or rigid workflows, lacking mechanisms for continual adaptation. Recent studies identified early cognitive traits in LLM agents (reflection, revision, and self-correction) suggesting foundational elements of human-like experiential learning. Thus the key question: Can we design LLM agents capable of structured, cognitively grounded learning similar to human processes? In response, we propose a computational framework of Kolb's learning cycle with Vygotsky's ZPD for autonomous agents. Our architecture separates extrinsic (environment interaction) and intrinsic (internal reflection/abstraction) functions, enabling cognitively grounded scaffolded learning, where the agent initially learns within structured environments, followed by open-ended generalisation. This approach empowers agents to master complex tasks ; domains that traditional fine-tuning or simple reflective methods could not tackle effectively. Its potential is powerfully demonstrated via direct comparison with humans in real-world Kaggle data science competitions. Learning fully automated data science code generation across 81 tasks, our system, Agent K, demonstrated the ability to perform the entire workflow autonomously, achieving an Elo-MMR score of 1694, beyond median score of the Kaggle Masters (the top 2% among 200,000 users) of our study. With 9 gold, 8 silver, and 12 bronze medals level performance - including 4 gold and 4 silver on prize-awarding competitions - Agent K is the 1st AI system to successfully integrate Kolb- and Vygotsky-inspired human cognitive learning, marking a major step toward generalist AI.

cs.LG↗

arXiv2025

JUNO 20-inch PMT and electronics system characterization using large pulses of PMT dark counts at the Pan-Asia testing platform

The main goal of the JUNO experiment is to determine the neutrino mass ordering with a 20kt liquid-scintillator detector. The 20-inch PMT and its 1F3 (one for three) electronics are crucial to realize the excellent energy resolution of at least 3% at 1MeV. The knowledge on the PMT and 1F3 electronics response is critical for detector performance understanding. A study of the JUNO 20-inch PMT and 1F3 electronics system characterization is presented using large pulses of PMT dark count at the Pan-Asia testing platform in China. Thanks to its broad amplitude range and high rate, the large pulse signals are also used to investigate the PMT after pulse response.

physics.ins-det↗

arXiv2025

Channel Polarization under Channel Noise with Memory

The channel polarization behavior of polar codes under noise with memory is investigated. By introducing a genie-aided channel model, we first show that the polarized subchannels still converge to extremal channels under the standard polar coding framework. More importantly, we explicitly quantify the gap between the mutual information achieved by ignoring memory effects and the actual capacity attained after sufficient polarization. It is proven that the channel capacity remains achievable even without prior knowledge of the channel noise. Furthermore, we demonstrate that the polarization rate is slower than that in the binary-input memoryless channel (BMC) case, provided that the channel transition function satisfies certain conditions. In particular, the Bhattacharyya parameter is asymptotically upper-bounded and lower-bounded by a polynomial function and an exponential function with respect to the block length, respectively.

cs.IT↗

arXiv2025

Rapid Construction of Joint Pulsar Timing Array Datasets: The Lite Method

The International Pulsar Timing Array (IPTA)'s second data release (IPTA DR2) combines decades of observations of 65 millisecond pulsars from 7 radio telescopes. IPTA datasets should be the most sensitive datasets to nanohertz gravitational waves (GWs), but take years to assemble, often excluding valuable recent data. To address this, we introduce the IPTA "Lite" analysis, where a Figure of Merit is used to select an optimal PTA dataset to analyze for each pulsar, enabling immediate access to new data and preliminary results prior to full combination. We test the capabilities of the Lite analysis using IPTA DR2, finding that "DR2 Lite" can be used to detect the common red noise process with an amplitude of $A = 4.8^{+1.8}_{-1.8} \times 10^{-15}$ at $γ= 13/3$. This amplitude is slightly large in comparison to the combined analysis, and likely biased high as DR2 Lite is more sensitive to systematic errors from individual pulsars than the full dataset. Furthermore, although there is no strong evidence for Hellings-Downs correlations in IPTA DR2, we still find the full dataset is better at resolving Hellings-Downs correlations than DR2 Lite. Alongside the Lite analysis, we also find that analyzing a subset of pulsars from IPTA DR2, available at a hypothetical "early" stage of combination (EDR2), yields equally competitive results as the full dataset. Looking ahead, the Lite method will enable rapid synthesis of the latest PTA data, offering preliminary GW constraints before the superior full dataset combinations are available.

astro-ph.HE↗

arXiv2025

Cutoff Rate Bounds and Constellation Shaping under Mixed Gaussian-Impulsive Noise

Mixed noise, composed of white Gaussian noise (WGN) and impulsive noise (IN), appears in numerous communication scenarios and can severely degrade system performance. In this paper, we optimize the transmitted constellation under mixed noise based on a theoretical analysis of the cutoff rate (CR). First, starting from the passband model of the mixed noise, we derive its corresponding baseband representation. Then, the baseband model is employed to obtain closed-form lower and upper bounds of the CR. A piecewise linear approximation is applied to derive efficient bounds by exploiting the algebraic properties of the integral terms. These bounds are then used as criteria to optimize the transmitted constellation points in both geometric positions and probabilistic distributions. The projected gradient method is employed to solve the optimization problem, and the convergence and properties of the solutions are analyzed. Numerical results demonstrate that the proposed CR bounds are tight and exhibit the expected asymptotic behavior. Furthermore, the optimized constellation scheme achieves a significant rate improvement compared to baselines.

eess.SP↗

arXiv2025

Quantized Large Language Models in Biomedical Natural Language Processing: Evaluation and Recommendation

Large language models have demonstrated remarkable capabilities in biomedical natural language processing, yet their rapid growth in size and computational requirements present a major barrier to adoption in healthcare settings where data privacy precludes cloud deployment and resources are limited. In this study, we systematically evaluated the impact of quantization on 12 state-of-the-art large language models, including both general-purpose and biomedical-specific models, across eight benchmark datasets covering four key tasks: named entity recognition, relation extraction, multi-label classification, and question answering. We show that quantization substantially reduces GPU memory requirements-by up to 75%-while preserving model performance across diverse tasks, enabling the deployment of 70B-parameter models on 40GB consumer-grade GPUs. In addition, domain-specific knowledge and responsiveness to advanced prompting methods are largely maintained. These findings provide significant practical and guiding value, highlighting quantization as a practical and effective strategy for enabling the secure, local deployment of large yet high-capacity language models in biomedical contexts, bridging the gap between technical advances in AI and real-world clinical translation.

cs.CL↗

arXiv2025

BOSC: A Backdoor-based Framework for Open Set Synthetic Image Attribution

Synthetic image attribution addresses the problem of tracing back the origin of images produced by generative models. Extensive efforts have been made to explore unique representations of generative models and use them to attribute a synthetic image to the model that produced it. Most of the methods classify the models or the architectures among those in a closed set without considering the possibility that the system is fed with samples produced by unknown architectures. With the continuous progress of AI technology, new generative architectures continuously appear, thus driving the attention of researchers towards the development of tools capable of working in open-set scenarios. In this paper, we propose a framework for open set attribution of synthetic images, named BOSC (Backdoor-based Open Set Classification), that relies on the concept of backdoor attacks to design a classifier with rejection option. BOSC works by purposely injecting class-specific triggers inside a portion of the images in the training set to induce the network to establish a matching between class features and trigger features. The behavior of the trained model with respect to triggered samples is then exploited at test time to perform sample rejection using an ad-hoc score. Experiments show that the proposed method has good performance, always surpassing the state-of-the-art. Robustness against image processing is also very good. Although we designed our method for the task of synthetic image attribution, the proposed framework is a general one and can be used for other image forensic applications.

cs.CV↗

arXiv2025

I2TTS: Image-indicated Immersive Text-to-speech Synthesis with Spatial Perception

Controlling the style and characteristics of speech synthesis is crucial for adapting the output to specific contexts and user requirements. Previous Text-to-speech (TTS) works have focused primarily on the technical aspects of producing natural-sounding speech, such as intonation, rhythm, and clarity. However, they overlook the fact that there is a growing emphasis on spatial perception of synthesized speech, which may provide immersive experience in gaming and virtual reality. To solve this issue, in this paper, we present a novel multi-modal TTS approach, namely Image-indicated Immersive Text-to-speech Synthesis (I2TTS). Specifically, we introduce a scene prompt encoder that integrates visual scene prompts directly into the synthesis pipeline to control the speech generation process. Additionally, we propose a reverberation classification and refinement technique that adjusts the synthesized mel-spectrogram to enhance the immersive experience, ensuring that the involved reverberation condition matches the scene accurately. Experimental results demonstrate that our model achieves high-quality scene and spatial matching without compromising speech naturalness, marking a significant advancement in the field of context-aware speech synthesis. Project demo page: https://spatialTTS.github.io/ Index Terms-Speech synthesis, scene prompt, spatial perception

cs.SD↗

arXiv2025

Deep Research Agents: A Systematic Examination And Roadmap

The rapid progress of Large Language Models (LLMs) has given rise to a new category of autonomous AI systems, referred to as Deep Research (DR) agents. These agents are designed to tackle complex, multi-turn informational research tasks by leveraging a combination of dynamic reasoning, adaptive long-horizon planning, multi-hop information retrieval, iterative tool use, and the generation of structured analytical reports. In this paper, we conduct a detailed analysis of the foundational technologies and architectural components that constitute Deep Research agents. We begin by reviewing information acquisition strategies, contrasting API-based retrieval methods with browser-based exploration. We then examine modular tool-use frameworks, including code execution, multimodal input processing, and the integration of Model Context Protocols (MCPs) to support extensibility and ecosystem development. To systematize existing approaches, we propose a taxonomy that differentiates between static and dynamic workflows, and we classify agent architectures based on planning strategies and agent composition, including single-agent and multi-agent configurations. We also provide a critical evaluation of current benchmarks, highlighting key limitations such as restricted access to external knowledge, sequential execution inefficiencies, and misalignment between evaluation metrics and the practical objectives of DR agents. Finally, we outline open challenges and promising directions for future research. A curated and continuously updated repository of DR agent research is available at: {https://github.com/ai-agents-2030/awesome-deep-research-agent}.

cs.AI↗

arXiv2025

On the Fermat-type partial differential-difference equations on $\mathbb{C}^n$

Assume that $n$ is a positive integer, $p_{j}$ ($j=1,2, \cdots, 6)$ are polynomials, $p$ is an irreducible polynomial, and $f$ is an entire function on $\mathbb{C}^{n}.$ Let $ L(f)=\sum_{j=1}^s q_{t_j}f_{z_{t_j}}$ and $\overline{f}(z)=f(z_{1}+c_{1}, \ldots, z_{n}+c_{n})$, where $q_{t_j}$ ($j=1,2, \cdots, s\le n$) are non-zero polynomials on $\mathbb{C}^{n}$ and $c=(c_{1}, \ldots, c_{n})\in \mathbb{C}^{n}\setminus\{0\}$. We show the structures of all entire solutions to the non-linear partial differential-difference equation $$(p_{1} L(f)+p_{2}\overline{f}+p_5 f)^{2}+(p_{3}L(f)+p_{4}\overline{f}+p_6 f)^{2}=p.$$ The partial differential-difference equation is called a Fermat-type partial differential-difference equation (PDDE). Further, we find many sufficient conditions and/or necessary conditions for the existence, as well as the concrete representations, of entire solutions to the Fermat-type PDDE. We also demonstrate several examples on $\mathbb{C}^2$ with non-constant coefficients to verify that all representations in our theorems exist and are accurate and that the entire solutions to the Fermat-type PDDEs could have finite or infinite growth order. Our theorems unify and extend previous results (see, e.g., [2, 3, 10, 12, 32]).

math.CV↗

arXiv2025

Decoupled Global-Local Alignment for Improving Compositional Understanding

Contrastive Language-Image Pre-training (CLIP) has achieved success on multiple downstream tasks by aligning image and text modalities. However, the nature of global contrastive learning limits CLIP's ability to comprehend compositional concepts, such as relations and attributes. Although recent studies employ global hard negative samples to improve compositional understanding, these methods significantly compromise the model's inherent general capabilities by forcibly distancing textual negative samples from images in the embedding space. To overcome this limitation, we introduce a Decoupled Global-Local Alignment (DeGLA) framework that improves compositional understanding while substantially mitigating losses in general capabilities. To optimize the retention of the model's inherent capabilities, we incorporate a self-distillation mechanism within the global alignment process, aligning the learnable image-text encoder with a frozen teacher model derived from an exponential moving average. Under the constraint of self-distillation, it effectively mitigates the catastrophic forgetting of pretrained knowledge during fine-tuning. To improve compositional understanding, we first leverage the in-context learning capability of Large Language Models (LLMs) to construct about 2M high-quality negative captions across five types. Subsequently, we propose the Image-Grounded Contrast (IGC) loss and Text-Grounded Contrast (TGC) loss to enhance vision-language compositionally. Extensive experimental results demonstrate the effectiveness of the DeGLA framework. Compared to previous state-of-the-art methods, DeGLA achieves an average enhancement of 3.5% across the VALSE, SugarCrepe, and ARO benchmarks. Concurrently, it obtains an average performance improvement of 13.0% on zero-shot classification tasks across eleven datasets. Our code will be released at https://github.com/xiaoxing2001/DeGLA

cs.CV↗

arXiv2025

Memento: Fine-tuning LLM Agents without Fine-tuning LLMs

In this paper, we introduce a novel learning paradigm for Adaptive Large Language Model (LLM) agents that eliminates the need for fine-tuning the underlying LLMs. Existing approaches are often either rigid, relying on static, handcrafted reflection workflows, or computationally intensive, requiring gradient updates of LLM model parameters. In contrast, our method enables low-cost continual adaptation via memory-based online reinforcement learning. We formalise this as a Memory-augmented Markov Decision Process (M-MDP), equipped with a neural case-selection policy to guide action decisions. Past experiences are stored in an episodic memory, either differentiable or non-parametric. The policy is continually updated based on environmental feedback through a memory rewriting mechanism, whereas policy improvement is achieved through efficient memory reading (retrieval). We instantiate our agent model in the deep research setting, namely \emph{Memento}, which attains top-1 on GAIA validation ($87.88\%$ Pass@$3$) and $79.40\%$ on the test set. It reaches $66.6\%$ F1 and $80.4\%$ PM on the DeepResearcher dataset, outperforming the state-of-the-art training-based method, while case-based memory adds $4.7\%$ to $9.6\%$ absolute points on out-of-distribution tasks. Our approach offers a scalable and efficient pathway for developing generalist LLM agents capable of continuous, real-time learning without gradient updates, advancing machine learning towards open-ended skill acquisition and deep research scenarios. The code is available at https://github.com/Agent-on-the-Fly/Memento.

cs.LG↗

arXiv2025

Causal Language in Observational Studies: Sociocultural Backgrounds and Team Composition

The use of causal language in observational studies has raised concerns about overstatement in scientific communication. While some argue that such language should be reserved for randomized controlled trials, others contend that rigorous causal inference methods can justify causal claims in observational research. Ideally, causal language should align with the strength of the underlying evidence. However, through the analysis of over 90,000 abstracts from observational studies using computational linguistic and regression methods, we found that causal language are more common in work by less experienced authors, smaller research teams, male last authors, and researchers from countries with higher uncertainty avoidance indices. Our findings suggest that the use of causal language is not solely driven by the strength of evidence, but also by the sociocultural backgrounds of authors and their team composition. This work provides a new perspective for understanding systematic variations in scientific communication and emphasizes the importance of recognizing these human factors when evaluating scientific claims.

physics.soc-ph↗

arXiv2025

Game-Theoretic Multiagent Reinforcement Learning

Tremendous advances have been made in multiagent reinforcement learning (MARL). MARL corresponds to the learning problem in a multiagent system in which multiple agents learn simultaneously. It is an interdisciplinary field of study with a long history that includes game theory, machine learning, stochastic control, psychology, and optimization. Despite great successes in MARL, there is a lack of a self-contained overview of the literature that covers game-theoretic foundations of modern MARL methods and summarizes the recent advances. The majority of existing surveys are outdated and do not fully cover the recent developments since 2010. In this work, we provide a monograph on MARL that covers both the fundamentals and the latest developments on the research frontier. The goal of this monograph is to provide a self-contained assessment of the current state-of-the-art MARL techniques from a game-theoretic perspective. We expect this work to serve as a stepping stone for both new researchers who are about to enter this fast-growing field and experts in the field who want to obtain a panoramic view and identify new directions based on recent advances.

cs.MA↗

arXiv2025

Dark Count Rate Stability of JUNO 20-inch PMTs in Mass Testing

The Jiangmen Underground Neutrino Observatory (JUNO) is an ambitious multipurpose neutrino experiment designed to determine the neutrino mass ordering, with an impressive energy resolution goal of at least 3% at 1 MeV. To achieve a photon detection coverage of approximately 75%, JUNO will utilize two types of 20-inch photomultiplier tubes (PMTs): the large PMT (LPMT) and the microchannel plate PMT (MCP-PMT). A significant concern in high-precision neutrino measurements is the dark count rate (DCR) of PMTs, which introduces noise that can adversely affect energy measurement accuracy. During the mass testing phase of the JUNO 20-inch PMTs, comprehensive measurements of the DCR were undertaken. These measurements not only captured the DCR values of individual PMTs but also examined the stability and temperature dependence of the DCR at an operating gain of (1x10^7). This paper presents a detailed characterization of the DCR of the JUNO 20-inch PMTs, investigating factors such as cooling time, temperature variations, and long-term stability using the JUNO Pan-Asia PMT testing facilities. The results reveal distinct DCR characteristics between the two types of PMTs, providing valuable insights into the nature of DCR and its implications for JUNO's scientific objectives. In addition to performance characterization, we implemented a monitoring system to track DCR stability over time. Notably, several spikes in DCR were identified, prompting a preliminary investigation into their causes. Potential factors contributing to these spikes, such as flasher events, were explored using coincidence rate analysis and complementary imaging techniques. The findings from this study are crucial for optimizing the performance of PMTs in JUNO, ultimately aiding the experiment in achieving its goals related to neutrino physics.

physics.ins-det↗