arXiv subjects

Xiao Liu

Publications and source records attributed to Xiao Liu.

At least 145 records · Page 8Linked to original sources

arXiv2025

DeepDive: Advancing Deep Search Agents with Knowledge Graphs and Multi-Turn RL

Augmenting large language models (LLMs) with browsing tools substantially improves their potential as deep search agents to solve complex, real-world tasks. Yet, open LLMs still perform poorly in such settings due to limited long-horizon reasoning capacity with browsing tools and the lack of sufficiently difficult supervised data. To address these challenges, we present DeepDive to advance deep search agents. First, we propose a strategy to automatically synthesize complex, difficult, and hard-to-find questions from open knowledge graphs. Second, we apply end-to-end multi-turn reinforcement learning (RL) to enhance LLMs' long-horizon reasoning with deep search. To encourage diversity and reduce redundancy, we design a redundancy penalty that discourages repeated similar queries. Experiments show that DeepDive-32B achieves a new open-source competitive result on BrowseComp, outperforming WebSailor, DeepSeek-R1-Browse, and Search-o1. We demonstrate that multi-turn RL training improves deep search ability and significantly contributes to the performance improvements across multiple benchmarks. We observe that DeepDive enables test-time scaling of tool calls and parallel sampling. All datasets, models, and code are publicly available at https://github.com/THUDM/DeepDive.

cs.CL↗

arXiv2025

CFVBench: A Comprehensive Video Benchmark for Fine-grained Multimodal Retrieval-Augmented Generation

Multimodal Retrieval-Augmented Generation (MRAG) enables Multimodal Large Language Models (MLLMs) to generate responses with external multimodal evidence, and numerous video-based MRAG benchmarks have been proposed to evaluate model capabilities across retrieval and generation stages. However, existing benchmarks remain limited in modality coverage and format diversity, often focusing on single- or limited-modality tasks, or coarse-grained scene understanding. To address these gaps, we introduce CFVBench, a large-scale, manually verified benchmark constructed from 599 publicly available videos, yielding 5,360 open-ended QA pairs. CFVBench spans high-density formats and domains such as chart-heavy reports, news broadcasts, and software tutorials, requiring models to retrieve and reason over long temporal video spans while maintaining fine-grained multimodal information. Using CFVBench, we systematically evaluate 7 retrieval methods and 14 widely-used MLLMs, revealing a critical bottleneck: current models (even GPT5 or Gemini) struggle to capture transient yet essential fine-grained multimodal details. To mitigate this, we propose Adaptive Visual Refinement (AVR), a simple yet effective framework that adaptively increases frame sampling density and selectively invokes external tools when necessary. Experiments show that AVR consistently enhances fine-grained multimodal comprehension and improves performance across all evaluated MLLMs

cs.CL↗

arXiv2025

Fire-EnSF: Wildfire Spread Data Assimilation using Ensemble Score Filter

As wildfires become increasingly destructive and expensive to control, effective management of active wildfires requires accurate, real-time fire spread predictions. To enhance the forecasting accuracy of active fires, data assimilation plays a vital role by integrating observations (such as remote-sensing data) and fire predictions generated from numerical models. This paper provides a comprehensive investigation on the application of a recently proposed diffusion-model-based filtering algorithm -- the Ensemble Score Filter (EnSF) -- to the data assimilation problem for real-time active wildfire spread predictions. Leveraging a score-based generative diffusion model, EnSF has been shown to have superior accuracy for high-dimensional nonlinear filtering problems, making it an ideal candidate for the filtering problems of wildfire spread models. Technical details are provided, and our numerical investigations demonstrate that EnSF provides superior accuracy, stability, and computational efficiency, establishing it as a robust and practical method for wildfire data assimilation. Our code has been made publicly available.

cs.LG↗

arXiv2025

EpiCoder: Encompassing Diversity and Complexity in Code Generation

Existing methods for code generation use code snippets as seed data, restricting the complexity and diversity of the synthesized data. In this paper, we introduce a novel feature tree-based synthesis framework, which revolves around hierarchical code features derived from high-level abstractions of code. The feature tree is constructed from raw data and refined iteratively to increase the quantity and diversity of the extracted features, which captures and recognizes more complex patterns and relationships within the code. By adjusting the depth and breadth of the sampled subtrees, our framework provides precise control over the complexity of the generated code, enabling functionalities that range from function-level operations to multi-file scenarios. We fine-tuned widely-used base models to obtain EpiCoder series, achieving state-of-the-art performance on multiple benchmarks at both the function and file levels. In particular, empirical evidence indicates that our approach shows significant potential in the synthesizing of repository-level code data. Our code and data are publicly available at https://github.com/microsoft/EpiCoder.

cs.CL↗

arXiv2025

Teaching Your Models to Understand Code via Focal Preference Alignment

Preference learning extends the performance of Code LLMs beyond traditional supervised fine-tuning by leveraging relative quality comparisons. In existing approaches, a set of n candidate solutions is evaluated based on test case success rates, with the candidate demonstrating a higher pass rate being labeled as positive and its counterpart with a lower pass rate as negative. However, because this approach aligns entire failing code blocks rather than pinpointing specific errors, it lacks the granularity necessary to capture meaningful error-correction relationships. As a result, the model is unable to learn more informative error-correction patterns. To address these issues, we propose Target-DPO, a new preference alignment framework that mimics human iterative debugging to refine Code LLMs. Target-DPO explicitly locates error regions and aligns the corresponding tokens via a tailored DPO algorithm. To facilitate it, we introduce the CodeFlow dataset, where samples are iteratively refined until passing tests, with modifications capturing error corrections. Extensive experiments show that a diverse suite of Code LLMs equipped with Target-DPO achieves significant performance gains in code generation and improves on challenging tasks like BigCodeBench. In-depth analysis reveals that Target-DPO yields fewer errors. Code, model and datasets are in: https://github.com/JieWu02/Target-DPO.

cs.CL↗

arXiv2025

LSMTCR: A Scalable Multi-Architecture Model for Epitope-Specific T Cell Receptor de novo Design

Designing full-length, epitope-specific TCR α\b{eta} remains challenging due to vast sequence space, data biases and incomplete modeling of immunogenetic constraints. We present LSMTCR, a scalable multi-architecture framework that separates specificity from constraint learning to enable de novo, epitope-conditioned generation of paired, full-length TCRs. A diffusion-enhanced BERT encoder learns time-conditioned epitope representations; conditional GPT decoders, pretrained on CDR3\b{eta} and transferred to CDR3α, generate chain-specific CDR3s under cross-modal conditioning with temperature-controlled diversity; and a gene-aware Transformer assembles complete α/\b{eta} sequences by predicting V/J usage to ensure immunogenetic fidelity. Across GLIPH, TEP, MIRA, McPAS and our curated dataset, LSMTCR achieves higher predicted binding than baselines on most datasets, more faithfully recovers positional and length grammars, and delivers superior, temperature-tunable diversity. For α-chain generation, transfer learning improves predicted binding, length realism and diversity over representative methods. Full-length assembly from known or de novo CDR3s preserves k-mer spectra, yields low edit distances to references, and, in paired α/\b{eta} co-modelling with epitope, attains higher pTM/ipTM than single-chain settings. LSMTCR outputs diverse, gene-contextualized, full-length TCR designs from epitope input alone, enabling high-throughput screening and iterative optimization.

cs.CE↗

arXiv2025

AgentRL: Scaling Agentic Reinforcement Learning with a Multi-Turn, Multi-Task Framework

Recent advances in large language models (LLMs) have sparked growing interest in building generalist agents that can learn through online interactions. However, applying reinforcement learning (RL) to train LLM agents in multi-turn, multi-task settings remains challenging due to lack of scalable infrastructure and stable training algorithms. In this work, we present the AgentRL framework for scalable multi-turn, multi-task agentic RL training. On the infrastructure side, AgentRL features a fully-asynchronous generation-training pipeline for efficient multi-turn RL. To support heterogeneous environment development in multi-task RL, we design a unified function-call based API interface, containerized environment development, and a centralized controller. On the algorithm side, we propose cross-policy sampling to encourage model exploration in multi-turn settings and task advantage normalization to stabilize multi-task training. Experiments show that AgentRL, trained on open LLMs across five agentic tasks, significantly outperforms GPT-5, Clause-Sonnet-4, DeepSeek-R1, and other open-source LLM agents. Multi-task training with AgentRL matches the best results among all task-specific models. AgentRL is open-sourced at https://github.com/THUDM/AgentRL. The algorithm and framework are adopted in building \textsc{\href{https://autoglm.zhipuai.cn}{AutoGLM}}.

cs.AI↗

arXiv2025

AgentBench: Evaluating LLMs as Agents

The potential of Large Language Model (LLM) as agents has been widely acknowledged recently. Thus, there is an urgent need to quantitatively \textit{evaluate LLMs as agents} on challenging tasks in interactive environments. We present AgentBench, a multi-dimensional benchmark that consists of 8 distinct environments to assess LLM-as-Agent's reasoning and decision-making abilities. Our extensive test over \num API-based and open-sourced (OSS) LLMs shows that, while top commercial LLMs present a strong ability of acting as agents in complex environments, there is a significant disparity in performance between them and many OSS competitors that are no larger than 70B. We identify the typical reasons of failures in environments and LLMs, showing that poor long-term reasoning, decision-making, and instruction following abilities are the main obstacles for developing usable LLM agents. Improving instruction following and training on high quality multi-round alignment data could improve agent performance. And different from existing assumptions, training on code present ambivalent impacts on different agent tasks. Datasets, environments, and an integrated evaluation package for AgentBench are released at https://github.com/THUDM/AgentBench.

cs.AI↗

arXiv2025

BlockFUL: Enabling Unlearning in Blockchained Federated Learning

Unlearning in Federated Learning (FL) presents significant challenges, as models grow and evolve with complex inheritance relationships. This complexity is amplified when blockchain is employed to ensure the integrity and traceability of FL, where the need to edit multiple interlinked blockchain records and update all inherited models complicates the process.In this paper, we introduce Blockchained Federated Unlearning (BlockFUL), a novel framework with a dual-chain structure comprising a live chain and an archive chain for enabling unlearning capabilities within Blockchained FL. BlockFUL introduces two new unlearning paradigms, i.e., parallel and sequential paradigms, which can be effectively implemented through gradient-ascent-based and re-training-based unlearning methods. These methods enhance the unlearning process across multiple inherited models by enabling efficient consensus operations and reducing computational costs. Our extensive experiments validate that these methods effectively reduce data dependency and operational overhead, thereby boosting the overall performance of unlearning inherited models within BlockFUL on CIFAR-10 and Fashion-MNIST datasets using AlexNet, ResNet18, and MobileNetV2 models.

cs.CR↗

arXiv2025

Anti-hyperuniform Critical States of Active Topological Defects

Topological defects are fundamental to the collective dynamics of non-equilibrium systems and in active matter, mediating spontaneous flows, dynamic self-organization, and emergent pattern formation. Here, we reveal critical states in active nematics, marked by slowed defect density relaxation, amplified fluctuations, and heightened sensitivity to activity. Near criticality, defect interactions become long-ranged, scaling with system size, and the system enters an anti-hyperuniform regime with giant number fluctuations of topological defects and defect clustering. This transition reflects a dual scaling behavior: fluctuations are uniform at small scales but become anti-hyperuniform at larger scales, \tm{as supported by experimental measurements on large-field-of-view endothelial monolayers. We find that these anti-hyperuniform states with multiscale defect density fluctuations are robust to varying parameters, introducing frictional damping, and changing boundary conditions.} Finally, we show that the observed anti-hyperuniformity originates from defect clustering, distinguishing this transition from defect-unbinding or phase separation processes. Beyond fundamental implications for non-equilibrium systems, these results may inform biological contexts where topological defects are integral to processes such as morphogenesis and collective cellular self-organization.

cond-mat.soft↗

arXiv2025

High-Precision and High-Efficiency Trajectory Tracking for Excavators Based on Closed-Loop Dynamics

The complex nonlinear dynamics of hydraulic excavators, such as time delays and control coupling, pose significant challenges to achieving high-precision trajectory tracking. Traditional control methods often fall short in such applications due to their inability to effectively handle these nonlinearities, while commonly used learning-based methods require extensive interactions with the environment, leading to inefficiency. To address these issues, we introduce EfficientTrack, a trajectory tracking method that integrates model-based learning to manage nonlinear dynamics and leverages closed-loop dynamics to improve learning efficiency, ultimately minimizing tracking errors. We validate our method through comprehensive experiments both in simulation and on a real-world excavator. Comparative experiments in simulation demonstrate that our method outperforms existing learning-based approaches, achieving the highest tracking precision and smoothness with the fewest interactions. Real-world experiments further show that our method remains effective under load conditions and possesses the ability for continual learning, highlighting its practical applicability. For implementation details and source code, please refer to https://github.com/ZiqingZou/EfficientTrack.

cs.RO↗

arXiv2025

Leg-Arm Coordinated Operation for Curtain Wall Installation

With the acceleration of urbanization, the number of high-rise buildings and large public facilities is increasing, making curtain walls an essential component of modern architecture with widespread applications. Traditional curtain wall installation methods face challenges such as variable on-site terrain, high labor intensity, low construction efficiency, and significant safety risks. Large panels often require multiple workers to complete installation. To address these issues, based on a hexapod curtain wall installation robot, we design a hierarchical optimization-based whole-body control framework for coordinated arm-leg planning tailored to three key tasks: wall installation, ceiling installation, and floor laying. This framework integrates the motion of the hexapod legs with the operation of the folding arm and the serial-parallel manipulator. We conduct experiments on the hexapod curtain wall installation robot to validate the proposed control method, demonstrating its capability in performing curtain wall installation tasks. Our results confirm the effectiveness of the hierarchical optimization-based arm-leg coordination framework for the hexapod robot, laying the foundation for its further application in complex construction site environments.

cs.RO↗

arXiv2025

Adapting Projection-Based Reduced-Order Models using Projected Gaussian Process

Projection-based model reduction is among the most widely adopted methods for constructing parametric Reduced-Order Models (ROM). Utilizing the snapshot data from solving full-order governing equations, the Proper Orthogonal Decomposition (POD) computes the optimal basis modes that represent the data, and a ROM can be constructed in the low-dimensional vector subspace spanned by the POD basis. For parametric governing equations, a potential challenge arises when there is a need to update the POD basis to adapt ROM that accurately capture the variation of a system's behavior over its parameter space (in design, control, uncertainty quantification, digital twins applications, etc.). In this paper, we propose a Projected Gaussian Process (pGP) and formulate the problem of adapting the POD basis as a supervised statistical learning problem, for which the goal is to learn a mapping from the parameter space to the Grassmann manifold that contains the optimal subspaces. A mapping is firstly established between the Euclidean space and the horizontal space of an orthogonal matrix that spans a reference subspace in the Grassmann manifold. A second mapping from the horizontal space to the Grassmann manifold is established through the Exponential/Logarithm maps between the manifold and its tangent space. Finally, given a new parameter, the conditional distribution of a vector can be found in the Euclidean space using the Gaussian Process (GP) regression, and such a distribution is then projected to the Grassmann manifold that enables us to predict the optimal subspace for the new parameter. As a statistical learning approach, the proposed pGP allows us to optimally estimate (or tune) the model parameters from data and quantify the statistical uncertainty associated with the prediction. The advantages of the proposed pGP are demonstrated by numerical experiments.

stat.ML↗

arXiv2025

Realizing the Haldane Model in Thermal Atoms

Topological materials hold great promise for developing next-generation devices with transport properties that remain resilient in the presence of local imperfections. However, their susceptibility to thermal noise has posed a major challenge. In particular, the Haldane model, a cornerstone in topological physics, generally requires cryogenic temperatures for experimental realization, limiting both the investigation of topologically robust quantum phenomena and their practical applications. In this work, we demonstrate a room-temperature realization of the Haldane model using atomic ensembles in momentum-space superradiance lattices, a platform intrinsically resistant to thermal noise. The topological phase transition is revealed through the superradiant emission contrast between two timed Dicke states in the lattice. Crucially, the thermal resilience of this platform allows us to access a deep modulation regime, where topological transitions to high Chern number phases emerge -- going beyond the traditional Haldane model. Our results not only deepen the understanding of exotic topological phases, but also offer a robust, reconfigurable, and room-temperature-compatible platform that connects quantum simulation to real-world quantum technologies.

quant-ph↗

arXiv2025

Can Machines Imitate Humans? Integrative Turing-like tests for Language and Vision Demonstrate a Narrowing Gap

As AI becomes increasingly embedded in daily life, ascertaining whether an agent is human is critical. We systematically benchmark AI's ability to imitate humans in three language tasks (image captioning, word association, conversation) and three vision tasks (color estimation, object detection, attention prediction), collecting data from 636 humans and 37 AI agents. Next, we conducted 72,191 Turing-like tests with 1,916 human judges and 10 AI judges. Current AIs are approaching the ability to convincingly impersonate humans and deceive human judges in both language and vision. Even simple AI judges outperformed humans in distinguishing AI from human responses. Imitation ability showed minimal correlation with conventional AI performance metrics, suggesting that passing as human is an important independent evaluation criterion. The large-scale Turing datasets and metrics introduced here offer valuable benchmarks for assessing human-likeness in AI and highlight the importance of rigorous, quantitative imitation tests for AI development.

cs.CV↗

arXiv2025

Sparse Sensor Allocation for Inverse Problems of Detecting Sparse Leaking Emission Sources

This paper investigates the sparse optimal allocation of sensors for detecting sparse leaking emission sources. Because of the non-negativity of emission rates, uncertainty associated with parameters in the forward model, and sparsity of leaking emission sources, the classical linear Gaussian Bayesian inversion setup is limited and no closed-form solutions are available. By incorporating the non-negativity constraints on emission rates, relaxing the Gaussian distributional assumption, and considering the parameter uncertainties associated with the forward model, this paper provides comprehensive investigations, technical details, in-depth discussions and implementation of the optimal sensor allocation problem leveraging a bilevel optimization framework. The upper-level problem determines the optimal sensor locations by minimizing the Integrated Mean Squared Error (IMSE) of the estimated emission rates over uncertain wind conditions, while the lower-level problem solves an inverse problem that estimates the emission rates. Two algorithms, including the repeated Sample Average Approximation (rSAA) and the Stochastic Gradient Descent based bilevel approximation (SBA), are thoroughly investigated. It is shown that the proposed approach can further reduce the IMSE of the estimated emission rates starting from various initial sensor deployment generated by existing approaches. Convergence analysis is performed to obtain the performance guarantee, and numerical investigations show that the proposed approach can allocate sensors according to the parameters and output of the forward model. Computationally efficient code with GPU acceleration is available on GitHub so that the approach readily applicable.

stat.AP↗

arXiv2025

Optimal Sensor Allocation with Multiple Linear Dispersion Processes

This paper considers the optimal sensor allocation for estimating the emission rates of multiple sources in a two-dimensional spatial domain. Locations of potential emission sources are known (e.g., factory stacks), and the number of sources is much greater than the number of sensors that can be deployed, giving rise to the optimal sensor allocation problem. In particular, we consider linear dispersion forward models, and the optimal sensor allocation is formulated as a bilevel optimization problem. The outer problem determines the optimal sensor locations by minimizing the overall Mean Squared Error of the estimated emission rates over various wind conditions, while the inner problem solves an inverse problem that estimates the emission rates. Two algorithms, including the repeated Sample Average Approximation and the Stochastic Gradient Descent based bilevel approximation, are investigated in solving the sensor allocation problem. Convergence analysis is performed to obtain the performance guarantee, and numerical examples are presented to illustrate the proposed approach.

stat.CO↗

arXiv2025

VPO: Aligning Text-to-Video Generation Models with Prompt Optimization

Video generation models have achieved remarkable progress in text-to-video tasks. These models are typically trained on text-video pairs with highly detailed and carefully crafted descriptions, while real-world user inputs during inference are often concise, vague, or poorly structured. This gap makes prompt optimization crucial for generating high-quality videos. Current methods often rely on large language models (LLMs) to refine prompts through in-context learning, but suffer from several limitations: they may distort user intent, omit critical details, or introduce safety risks. Moreover, they optimize prompts without considering the impact on the final video quality, which can lead to suboptimal results. To address these issues, we introduce VPO, a principled framework that optimizes prompts based on three core principles: harmlessness, accuracy, and helpfulness. The generated prompts faithfully preserve user intents and, more importantly, enhance the safety and quality of generated videos. To achieve this, VPO employs a two-stage optimization approach. First, we construct and refine a supervised fine-tuning (SFT) dataset based on principles of safety and alignment. Second, we introduce both text-level and video-level feedback to further optimize the SFT model with preference learning. Our extensive experiments demonstrate that VPO significantly improves safety, alignment, and video quality compared to baseline methods. Moreover, VPO shows strong generalization across video generation models. Furthermore, we demonstrate that VPO could outperform and be combined with RLHF methods on video generation models, underscoring the effectiveness of VPO in aligning video generation models. Our code and data are publicly available at https://github.com/thu-coai/VPO.

cs.CV↗