arXiv subjects

Jun Liu

Publications and source records attributed to Jun Liu.

At least 217 records · Page 12Linked to original sources

arXiv2025

MARS: Multi-Agent Adaptive Reasoning with Socratic Guidance for Automated Prompt Optimization

Large language models (LLMs) typically operate in a question-answering paradigm, where the quality of the input prompt critically affects the response. Automated Prompt Optimization (APO) aims to overcome the cognitive biases of manually crafted prompts and explore a broader prompt design space. However, existing APO methods often suffer from rigid template structures and inefficient exploration in the prompt space. To this end, we propose a Multi-Agent Adaptive Reasoning with Socratic guidance framework (MARS) for APO. MARS consists of five complementary agents and formulates the optimization process as a Partially Observable Markov Decision Process (POMDP), enabling adaptive prompt refinement through explicit state modeling and interactive feedback. Specifically, a Planner agent generates flexible optimization trajectories, a Teacher-Critic-Student triad engages in Socratic-style dialogue to iteratively optimize the prompt based on pseudo-gradient signals in the text space, and a Target agent executes the prompt in downstream tasks to provide performance feedback. MARS integrates reasoning, feedback, and state transition into a unified hidden-state evolution process, improving both the effectiveness and interpretability of optimization. Extensive experiments on multiple datasets demonstrate that MARS outperforms existing APO methods in terms of optimization performance, search efficiency, and interpretability.

cs.CL↗

arXiv2025

MAPS: Multi-Agent Personality Shaping for Collaborative Reasoning

Collaborative reasoning with multiple agents offers the potential for more robust and diverse problem-solving. However, existing approaches often suffer from homogeneous agent behaviors and lack of reflective and rethinking capabilities. We propose Multi-Agent Personality Shaping (MAPS), a novel framework that enhances reasoning through agent diversity and internal critique. Inspired by the Big Five personality theory, MAPS assigns distinct personality traits to individual agents, shaping their reasoning styles and promoting heterogeneous collaboration. To enable deeper and more adaptive reasoning, MAPS introduces a Critic agent that reflects on intermediate outputs, revisits flawed steps, and guides iterative refinement. This integration of personality-driven agent design and structured collaboration improves both reasoning depth and flexibility. Empirical evaluations across three benchmarks demonstrate the strong performance of MAPS, with further analysis confirming its generalizability across different large language models and validating the benefits of multi-agent collaboration.

cs.AI↗

arXiv2025

Towards Learning and Verifying Maximal Lyapunov-Barrier Functions with a Zubov PDE Formulation

Verifying stability and safety guarantees for nonlinear systems has received considerable attention in recent years. This property serves as a fundamental building block for specifying more complex system behaviors and control objectives. However, estimating the domain of attraction under safety constraints and constructing a Lyapunov-barrier function remain challenging tasks for nonlinear systems. To address this problem, we propose a Zubov PDE formulation with a Dirichlet boundary condition for autonomous nonlinear systems and show that a physics-informed neural network solution, once formally verified, can serve as a Lyapunov-barrier function that jointly certifies stability and safety. This approach extends existing converse Lyapunov-barrier theorems by introducing a PDE-based framework with boundary conditions defined on the safe set, yielding a near-optimal certified under-approximation of the true safe domain of attraction.

math.DS↗

arXiv2025

Exploring Category-level Articulated Object Pose Tracking on SE(3) Manifolds

Articulated objects are prevalent in daily life and robotic manipulation tasks. However, compared to rigid objects, pose tracking for articulated objects remains an underexplored problem due to their inherent kinematic constraints. To address these challenges, this work proposes a novel point-pair-based pose tracking framework, termed \textbf{PPF-Tracker}. The proposed framework first performs quasi-canonicalization of point clouds in the SE(3) Lie group space, and then models articulated objects using Point Pair Features (PPF) to predict pose voting parameters by leveraging the invariance properties of SE(3). Finally, semantic information of joint axes is incorporated to impose unified kinematic constraints across all parts of the articulated object. PPF-Tracker is systematically evaluated on both synthetic datasets and real-world scenarios, demonstrating strong generalization across diverse and challenging environments. Experimental results highlight the effectiveness and robustness of PPF-Tracker in multi-frame pose tracking of articulated objects. We believe this work can foster advances in robotics, embodied intelligence, and augmented reality. Codes are available at https://github.com/mengxh20/PPFTracker.

cs.CV↗

arXiv2025

Every Activation Boosted: Scaling General Reasoner to 1 Trillion Open Language Foundation

We introduce Ling 2.0, a series reasoning-oriented language foundation built upon the principle that every activation boosts reasoning capability. Designed to scale from tens of billions to one trillion parameters under a unified Mixture-of-Experts (MoE) paradigm, Ling 2.0 emphasizes high sparsity, cross-scale consistency, and efficiency guided by empirical scaling laws. The series includes three non-thinking (instruct) models - Ling-mini-2.0, Ling-flash-2.0, and Ling-1T - ranging from 16B to 1T total parameters and achieving up to 7-fold active-compute efficiency compared with dense counterparts. Ling 2.0 integrates coordinated innovations across model architecture, pre-training, post-training, and infrastructure: a high-sparsity MoE with MTP for efficient reasoning, reasoning-oriented data and mid-training CoT activation, reinforcement-based fine-tuning (DFT, Evo-CoT), and full-scale FP8 training with fine-grained heterogeneous pipelines. At the trillion scale, Ling-1T establishes a new Pareto frontier of reasoning accuracy versus computational efficiency, demonstrating that sparse activation, when properly aligned with reasoning objectives, enables scalable and efficient intelligence. Collectively, Ling 2.0 provides a coherent, open, and efficient foundation for advancing future reasoning and thinking models, including the Ring series built upon the same base.

cs.CL↗

arXiv2025

An Automated Theorem Generator with Theoretical Foundation Based on Rectangular Standard Contradiction

Currently, there is a lack of rigorous theoretical system for systematically generating non-trivial and logically valid theorems. Addressing this critical gap, this paper conducts research to propose a novel automated theorem generation theory and tool. Based on the concept of standard contradiction which possesses unique deductive advantages, this paper defines and proves, for the first time, a new logical structure known as rectangular standard contradiction. Centered on this structure, a complete Automated Theorem Generation (ATG) theory is put forward. Theoretical proofs clarify two core properties of rectangular standard contradiction: first, it is a standard contradiction (necessarily unsatisfiable); second, it exhibits non-redundancy (the remaining clause set becomes satisfiable after removing any clause). Leveraging these properties, this paper proves that partitioning a rectangular standard contradiction into a premise subset $A$ and negation of its complement $H$, a valid theorem $A \vdash \neg H$ can be formed, and all such theorems are logically equivalent. To implement this theory, an efficient template-based ATG algorithm is designed, and a Rectangular Automated Theorem Generator is developed. This research enables machines to transition from "verifiers" to "discoverers", opening up new avenues for fundamental research in the fields of logic and artificial intelligence.

cs.LO↗

arXiv2025

Scaffolded Language Models with Language Supervision for Mixed-Autonomy: A Survey

This survey organizes the intricate literature on the design and optimization of emerging structures around post-trained LMs. We refer to this overarching structure as scaffolded LMs and focus on LMs that are integrated into multi-step processes with tools. We view scaffolded LMs as semi-parametric models wherein we train non-parametric variables, including the prompt, tools, and scaffold's code. In particular, they interpret instructions, use tools, and receive feedback all in language. Recent works use an LM as an optimizer to interpret language supervision and update non-parametric variables according to intricate objectives. In this survey, we refer to this paradigm as training of scaffolded LMs with language supervision. A key feature of non-parametric training is the ability to learn from language. Parametric training excels in learning from demonstration (supervised learning), exploration (reinforcement learning), or observations (unsupervised learning), using well-defined loss functions. Language-based optimization enables rich, interpretable, and expressive objectives, while mitigating issues like catastrophic forgetting and supporting compatibility with closed-source models. Furthermore, agents are increasingly deployed as co-workers in real-world applications such as Copilot in Office tools or software development. In these mixed-autonomy settings, where control and decision-making are shared between human and AI, users point out errors or suggest corrections. Accordingly, we discuss agents that continuously improve by learning from this real-time, language-based feedback and refer to this setting as streaming learning from language supervision.

cs.CL↗

arXiv2025

Resolvent-Type Data-Driven Learning of Generators for Unknown Continuous-Time Dynamical Systems

A semigroup characterization, or equivalently, a characterization by the generator, is a classical technique used to describe continuous-time nonlinear dynamical systems. In the realm of data-driven learning for an unknown nonlinear system, one must estimate the generator of the semigroup of the system's transfer operators (also known as the semigroup of Koopman operators) based on discrete-time observations and verify convergence to the true generator in an appropriate sense. As the generator encodes essential instantaneous transitional information of the system, challenges arise for some existing methods that rely on accurately estimating the time derivatives of the state with constraints on the observation rate. Recent literature develops a technique that avoids the use of time derivatives by employing the logarithm of a Koopman operator. However, the validity of this method has been demonstrated only within a restrictive function space and requires knowledge of the operator's spectral properties. In this paper, we propose a resolvent-type method for learning the system generator to relax the requirements on the observation frequency and overcome the constraints of taking operator logarithms. We also provide numerical examples to demonstrate its effectiveness in applications of system identification and constructing Lyapunov functions.

math.DS↗

arXiv2025

Harmony in Divergence: Towards Fast, Accurate, and Memory-efficient Zeroth-order LLM Fine-tuning

Large language models (LLMs) excel across various tasks, but standard first-order (FO) fine-tuning demands considerable memory, significantly limiting real-world deployment. Recently, zeroth-order (ZO) optimization stood out as a promising memory-efficient training paradigm, avoiding backward passes and relying solely on forward passes for gradient estimation, making it attractive for resource-constrained scenarios. However, ZO method lags far behind FO method in both convergence speed and accuracy. To bridge the gap, we introduce a novel layer-wise divergence analysis that uncovers the distinct update pattern of FO and ZO optimization. Aiming to resemble the learning capacity of FO method from the findings, we propose Divergence-driven Zeroth-Order (DiZO) optimization. DiZO conducts divergence-driven layer adaptation by incorporating projections to ZO updates, generating diverse-magnitude updates precisely scaled to layer-wise individual optimization needs. Our results demonstrate that DiZO significantly reduces the needed iterations for convergence without sacrificing throughput, cutting training GPU hours by up to 48\% on various datasets. Moreover, DiZO consistently outperforms the representative ZO baselines in fine-tuning RoBERTa-large, OPT-series, and Llama-series on downstream tasks and, in some cases, even surpasses memory-intensive FO fine-tuning. Our code is released at https://github.com/Skilteee/DiZO.

cs.LG↗

arXiv2025

High thermal conductivity of rutile-GeO$_2$ films grown by MOCVD: $52.9~\mathrm{W\,m^{-1}\,K^{-1}}$

Rutile germanium dioxide (r-GeO2) has recently emerged as a promising ultrawide-bandgap (UWBG) semiconductor owing to its wide bandgap (~4.4-5.1 eV), ambipolar doping potential, and high theoretical thermal conductivity. However, experimental data on the thermal conductivity of r-GeO2 epitaxial layers have not been reported, primarily due to challenges in phase control and surface roughness. Here, we report a high thermal conductivity of 52.9 +/- 6.6 W m^-1 K^-1 for high-quality (002) r-GeO2 films grown by metal-organic chemical vapor deposition (MOCVD) and characterized using time-domain thermoreflectance (TDTR). The phase control was achieved through a seed-driven stepwise crystallization (SDSC) approach, and the surface roughness was significantly reduced from 76 nm to 16 nm (locally as low as 1 A) via chemical mechanical polishing (CMP). These results highlight the promise of r-GeO2 as a UWBG oxide platform for power electronics applications.

cond-mat.mtrl-sci↗

arXiv2025

Towards Fine-Grained Vision-Language Alignment for Few-Shot Anomaly Detection

Few-shot anomaly detection (FSAD) methods identify anomalous regions with few known normal samples. Most existing methods rely on the generalization ability of pre-trained vision-language models (VLMs) to recognize potentially anomalous regions through feature similarity between text descriptions and images. However, due to the lack of detailed textual descriptions, these methods can only pre-define image-level descriptions to match each visual patch token to identify potential anomalous regions, which leads to the semantic misalignment between image descriptions and patch-level visual anomalies, achieving sub-optimal localization performance. To address the above issues, we propose the Multi-Level Fine-Grained Semantic Caption (MFSC) to provide multi-level and fine-grained textual descriptions for existing anomaly detection datasets with automatic construction pipeline. Based on the MFSC, we propose a novel framework named FineGrainedAD to improve anomaly localization performance, which consists of two components: Multi-Level Learnable Prompt (MLLP) and Multi-Level Semantic Alignment (MLSA). MLLP introduces fine-grained semantics into multi-level learnable prompts through automatic replacement and concatenation mechanism, while MLSA designs region aggregation strategy and multi-level alignment training to facilitate learnable prompts better align with corresponding visual regions. Experiments demonstrate that the proposed FineGrainedAD achieves superior overall performance in few-shot settings on MVTec-AD and VisA datasets.

cs.CV↗

arXiv2025

Revealing the Potential of Learnable Perturbation Ensemble Forecast Model for Tropical Cyclone Prediction

Tropical cyclones (TCs) are highly destructive and inherently uncertain weather systems. Ensemble forecasting helps quantify these uncertainties, yet traditional systems are constrained by high computational costs and limited capability to fully represent atmospheric nonlinearity. FuXi-ENS introduces a learnable perturbation scheme for ensemble generation, representing a novel AI-based forecasting paradigm. Here, we systematically compare FuXi-ENS with ECMWF-ENS using all 90 global TCs in 2018, examining their performance in TC-related physical variables, track and intensity forecasts, and the associated dynamical and thermodynamical fields. FuXi-ENS demonstrates clear advantages in predicting TC-related physical variables, and achieves more accurate track forecasts with reduced ensemble spread, though it still underestimates intensity relative to observations. Further dynamical and thermodynamical analyses reveal that FuXi-ENS better captures large-scale circulation, with moisture turbulent energy more tightly concentrated around the TC warm core, whereas ECMWF-ENS exhibits a more dispersed distribution. These findings highlight the potential of learnable perturbations to improve TC forecasting skill and provide valuable insights for advancing AI-based ensemble prediction of extreme weather events that have significant societal impacts.

cs.LG↗

arXiv2025

Hierarchical Optimization via LLM-Guided Objective Evolution for Mobility-on-Demand Systems

Online ride-hailing platforms aim to deliver efficient mobility-on-demand services, often facing challenges in balancing dynamic and spatially heterogeneous supply and demand. Existing methods typically fall into two categories: reinforcement learning (RL) approaches, which suffer from data inefficiency, oversimplified modeling of real-world dynamics, and difficulty enforcing operational constraints; or decomposed online optimization methods, which rely on manually designed high-level objectives that lack awareness of low-level routing dynamics. To address this issue, we propose a novel hybrid framework that integrates large language model (LLM) with mathematical optimization in a dynamic hierarchical system: (1) it is training-free, removing the need for large-scale interaction data as in RL, and (2) it leverages LLM to bridge cognitive limitations caused by problem decomposition by adaptively generating high-level objectives. Within this framework, LLM serves as a meta-optimizer, producing semantic heuristics that guide a low-level optimizer responsible for constraint enforcement and real-time decision execution. These heuristics are refined through a closed-loop evolutionary process, driven by harmony search, which iteratively adapts the LLM prompts based on feasibility and performance feedback from the optimization layer. Extensive experiments based on scenarios derived from both the New York and Chicago taxi datasets demonstrate the effectiveness of our approach, achieving an average improvement of 16% compared to state-of-the-art baselines.

cs.AI↗

arXiv2025

CuSfM: CUDA-Accelerated Structure-from-Motion

Efficient and accurate camera pose estimation forms the foundational requirement for dense reconstruction in autonomous navigation, robotic perception, and virtual simulation systems. This paper addresses the challenge via cuSfM, a CUDA-accelerated offline Structure-from-Motion system that leverages GPU parallelization to efficiently employ computationally intensive yet highly accurate feature extractors, generating comprehensive and non-redundant data associations for precise camera pose estimation and globally consistent mapping. The system supports pose optimization, mapping, prior-map localization, and extrinsic refinement. It is designed for offline processing, where computational resources can be fully utilized to maximize accuracy. Experimental results demonstrate that cuSfM achieves significantly improved accuracy and processing speed compared to the widely used COLMAP method across various testing scenarios, while maintaining the high precision and global consistency essential for offline SfM applications. The system is released as an open-source Python wrapper implementation, PyCuSfM, available at https://github.com/nvidia-isaac/pyCuSFM, to facilitate research and applications in computer vision and robotics.

cs.CV↗

arXiv2025

DRL: Discriminative Representation Learning with Parallel Adapters for Class Incremental Learning

With the excellent representation capabilities of Pre-Trained Models (PTMs), remarkable progress has been made in non-rehearsal Class-Incremental Learning (CIL) research. However, it remains an extremely challenging task due to three conundrums: increasingly large model complexity, non-smooth representation shift during incremental learning and inconsistency between stage-wise sub-problem optimization and global inference. In this work, we propose the Discriminative Representation Learning (DRL) framework to specifically address these challenges. To conduct incremental learning effectively and yet efficiently, the DRL's network, called Incremental Parallel Adapter (IPA) network, is built upon a PTM and increasingly augments the model by learning a lightweight adapter with a small amount of parameter learning overhead in each incremental stage. The adapter is responsible for adapting the model to new classes, it can inherit and propagate the representation capability from the current model through parallel connection between them by a transfer gate. As a result, this design guarantees a smooth representation shift between different incremental stages. Furthermore, to alleviate inconsistency and enable comparable feature representations across incremental stages, we design the Decoupled Anchor Supervision (DAS). It decouples constraints of positive and negative samples by respectively comparing them with the virtual anchor. This decoupling promotes discriminative representation learning and aligns the feature spaces learned at different stages, thereby narrowing the gap between stage-wise local optimization over a subset of data and global inference across all classes. Extensive experiments on six benchmarks reveal that our DRL consistently outperforms other state-of-the-art methods throughout the entire CIL period while maintaining high efficiency in both training and inference phases.

cs.CV↗

arXiv2025

Engineering Nonporous Polymer Hybrids with Suppressed Heat Conduction and Enhanced Flame Retardancy via Molecular and Filler Design

This study presents a new strategy for achieving ultralow thermal conductivity in nonporous polymer/organic filler hybrids by suppressing heat capacity through tailored atomic vibrations to enhance thermal insulation. Unlike conventional polymer/inorganic filler hybrids, these hybrids exhibit interfacial thermal resistance one to three orders of magnitude lower. Combined experiments and simulations uncover thermal transport mechanisms. These hybrids demonstrate enhanced flame retardancy. Please see the abstract in the attached PDF.

physics.app-ph↗

arXiv2025

Modeling AI-Driven Production and Competitiveness A Multi-Agent Economic Simulation of China and the United States

With the rapid development of artificial intelligence (AI) technology, socio-economic systems are entering a new stage of "human-AI co-creation." Building upon a previously established multi-level intelligent agent economic model, this paper conducts simulation-based comparisons of macroeconomic output evolution in China and the United States under different mechanisms-AI collaboration, network effects, and AI autonomous production. The results show that: (1) when AI functions as an independent productive entity, the overall growth rate of social output far exceeds that of traditional human-labor-based models; (2) China demonstrates clear potential for acceleration in both the expansion of intelligent agent populations and the pace of technological catch-up, offering the possibility of achieving technological convergence or even partial surpassing. This study provides a systematic, model-based analytical framework for understanding AI-driven production system transformation and shifts in international competitiveness, as well as quantitative insights for relevant policy formulation.

cs.AI↗

arXiv2025

Generative artificial intelligence improves projections of climate extremes

Climate change is amplifying extreme events, posing escalating risks to biodiversity, human health, and food security. GCMs are essential for projecting future climate, yet their coarse resolution and high computational costs constrain their ability to represent extremes. Here, we introduce FuXi-CMIPAlign, a generative deep learning framework for downscaling CMIP outputs. The model integrates Flow Matching for generative modeling with domain adaptation via MMD loss to align feature distributions between training data and inference data, thereby mitigating input discrepancies and improving accuracy, stability, and generalization across emission scenarios. FuXi-CMIPAlign performs spatial, temporal, and multivariate downscaling, enabling more realistic simulation of compound extremes such as TCs.

physics.ao-ph↗