arXiv subjects

Tong Li

Publications and source records attributed to Tong Li.

At least 19 recordsLinked to original sources

arXiv2026

Can Image Agents Complete Visual Commissions? A Benchmark and Modular Framework

Visual commissions require image agents to integrate heterogeneous source materials, preserve requirements across dependent stages, and produce coordinated deliverables. Existing evaluations examine specific capabilities and execution settings, leaving end-to-end commission completion less understood. We introduce Visual Commission Bench (VCB), comprising 600 tasks across 12 categories and three complementary tiers, from capability-focused tasks to complete commissions. VCB uses 5,039 requirement checks and separate visual quality ratings to assess content correctness, visual realization, constraint preservation, and delivery completeness without prescribing an internal workflow. We present V-Protocol, a reference agent that dynamically composes reusable task, cognitive, and expression modules at inference time. Task modules organize delivery, cognitive modules derive content, and expression modules guide visual realization. The modules exchange structured intermediate artifacts, while a shared execution harness tracks artifact revisions and dependencies, manages tool execution, and checks completion. With the same controller and image generator as the agent baselines, V-Protocol achieves 69.0\% strict task success on VCB, compared with 42.0\% for SCOPE. On Mind-Bench, strict accuracy increases from 39.2\% to 45.4\%.

cs.CV↗

arXiv2026

VDE Bench: Evaluating The Capability of Image Editing Models to Modify Visual Documents

Image editing models can modify visual content through natural language, but editing dense documents requires precise local changes amid tightly coupled text, tables, and layout. We introduce VDE Bench, an evaluation resource for studying instruction-guided editing of Chinese and English document images. VDE Bench contains 3,506 instruction-guided image editing samples, including 1,578 text-region edits and 1,928 table-region edits. The benchmark pairs editing instructions and reference images with annotated editing regions and structured OCR outputs. Its evaluation protocol combines region-level and full-page measurements to assess textual correctness, structural fidelity, and visual content preservation. By focusing on the interaction between local edits and their surrounding document context, VDE Bench complements existing visual text editing benchmarks and provides a resource for diagnosing document-specific editing failures.

cs.CV↗

arXiv2026

RAG-CSI: Global Local Retrieval via Joint State and Dynamics Matching for CSI Prediction

Channel state information (CSI) prediction forecasts future channel states from historical observations, supporting transceiver design and resource allocation with reduced measurement overhead. However, existing deep learning predictors mainly encode channel knowledge in model parameters, which can limit their ability to represent diverse patterns of channel dynamics across scenes. In this paper, we propose RAG-CSI, a retrieval-enhanced Transformer framework that augments prediction with relevant historical channel knowledge. Specifically, we construct a global--local CSI knowledge store containing representative observations across scenes and historical observations from the current serving scene. We further develop joint state--dynamics retrieval (JSDR), which jointly characterizes channel states, phase dynamics, and amplitude dynamics to retrieve relevant CSI sequences. A Transformer predictor then uses cross-attention to fuse the retrieved knowledge with the current CSI history and predict future CSI with limited additional model parameters. Experiments on a multi-scene CSI dataset show overall improvements exceeding 10\% across all five evaluation metrics over the best baseline for each metric, including a 15.42\% reduction in normalized mean squared error.

eess.SP↗

arXiv2026

Beyond Trajectory Statistics: Community-Consistent Human Mobility Generation via Evolving User-Location Graphs

Human mobility data are fundamental to Web-based location services and broader urban applications, and mobility generation provides synthetic trajectories when real data are costly or inaccessible. Although recent mobility generators have incorporated collective mobility patterns, they primarily focus on individual trajectories and aggregate population dynamics, leaving evolving community structures formed by user-location interactions insufficiently modeled. In this paper, we study community-consistent human mobility generation. To this end, we formulate mobility generation as the generation of dynamic user-location graphs to model community structures and propose MOTION, a Multi-agent framework for cOmmuniTy-consIstent human mObility geNeration. MOTION consists of user agents, location agents, and a global manager agent. MOTION first detects coherent communities from historical mobility using the Leiden algorithm and extracts community-conditioned interaction priors to guide the generation process. Guided by these priors, the user agents plan mobility, search destination candidates, and infer user movements from the individual view. In parallel, selectively activated location agents infer likely user arrivals from the community view. The manager coordinates both views, diagnoses interactions causing deviations, and attributes targeted reflection signals to revise user decisions, location attraction, and source-user selection. Experiments on two real-world datasets show that MOTION outperforms baselines by at least 4.05% across reported metrics of individual trajectories, population and flow distributions, and community and graph structures. Further analyses confirm its robustness, privacy preservation, and downstream utility. The code is available at https://anonymous.4open.science/r/MOTION-04C4.

cs.AI↗

arXiv2026

Structured Time-Frequency Representation for Channel Prediction

Accurate CSI forecasting is essential for mitigating channel aging and supporting reliable downlink transmission in high-mobility wireless systems. In FDD systems, forecasting future DL CSI from historical UL observations requires joint temporal extrapolation and cross-band inference. However, defining historical UL as the input and future DL as the target does not specify how elapsed time and UL-to-DL band separation should be represented in a pretrained predictor's positional space. FAR-CSI establishes an FDD-aware representation of channel forecasting within a joint temporal and operating-band positional field. Within this field, historical UL observations and future DL targets occupy segregated regions according to their temporal and operating-band roles, preserving the distinction between observed UL context and unobserved DL prediction targets. This representation is instantiated through a unified structured routing rule that governs encoder positional assignment, decoder-field reconstruction, and future-DL target selection, ensuring the same FDD geometry is preserved from contextual encoding to prediction readout. Under matched backbone, initialization, and training conditions, FDD-aware routing reduces NMSE by 21.44\% relative to generic routing. Across the evaluated FDD baselines, FAR-CSI achieves higher CSI prediction accuracy and MRT-based spectral efficiency, while retaining its predictive advantage across mobility conditions, prediction horizons, reduced training-data regimes, and noisy historical observations.

cs.IT↗

arXiv2026

Spatial Heuristic Strategy based Diffusion Reinforcement Learning for Online 3D Bin Packing

Traditional heuristic methods have accumulated mature experience in core objectives, such as space utilization and layout compactness of 3D bin packing, relying on artificially designed rule-based logic. However, they exhibit obvious limitations in generalization ability and adaptability to dynamic scenarios. Diffusion reinforcement learning, which integrates the spatial search capability of reinforcement learning and the data distribution modeling capability of diffusion learning, has achieved certain progress in action distribution modeling and decision compliance constraints. Nevertheless, there remain issues including insufficient perception of the spatial topological structure in 3D bin packing and limited layout optimization capability. To address these problems, we propose a diffusion reinforcement learning method integrated with spatial heuristic strategies, which combines classical bin packing heuristic rules with a diffusion reinforcement learning framework. Specifically, it compresses the action space through heuristic action pre-screening, introduces a graph neural network to model the spatial structure, and designs a composite reward function incorporating flatness to suppress spatial fragmentation, thereby realizing the organic integration of prior knowledge and adaptive optimization. Experimental results demonstrate that the pro

cs.AI↗

arXiv2026

Estimating treatment effects with a unified semi-parametric difference-in-differences approach

Difference-in-differences (DID) approaches estimate causal effects with observational data before and after an intervention. DID traditionally estimates the average treatment effect among the treated and assumes parallel trends in outcome means. With skewed outcomes, a transformation is often needed to compare means; however, transformations may be difficult to choose and results may be sensitive to the choice and must be interpreted on the transformed scale. Recent DID methods estimate alternative treatment effects that offer additional insights. However, each estimator requires a different parallel trends assumption. We introduce a new DID method that estimates average, quantile, probability, and novel Mann-Whitney treatment effects among the treated with a single unifying parallel trends assumption. The method uses a semi-parametric cumulative probability model (CPM): a linear model for a latent variable on covariates, where the latent variable results from an unspecified transformation of the outcome. Our approach makes a single parallel trends assumption on the expectation of the latent variable conditional on covariates. Hence, we avoid specifying outcome transformations and separate estimand-specific assumptions. We introduce the method; describe identification, estimation, and inference; conduct simulations evaluating its performance; and apply it to assess the impact of Medicaid expansion on CD4 count among people with HIV.

stat.ME↗

arXiv2026

TEAR: Table Extraction with Attribute Recommendation from Texts via Large Language Models

Table extraction from texts is an important task for information systems, and recent approaches that prompt large language models (LLMs) with instructions have drawn great attention for their strong performance. Existing works have assumed the input texts to be table descriptions or specialized documents. However, these efforts have largely overlooked another prevalent category of texts, commonly found in news reports and social media: naturally occurring texts. Extracting tabular information from such texts poses two distinct challenges. First, high variability and the absence of explicit structural cues make fixed heuristic LLM prompts limited in precisely delineating extraction boundaries. Second, manually predefined schemas cannot capture open-ended, unseen attributes in naturally occurring text. In this paper, we propose a framework, TEAR, to address these challenges. It comprises two synergistic workflows: a Table Extraction Workflow that dynamically adapts instructions to overcome the limitation of heuristic instructions, and an Attribute Recommendation Workflow that discovers new attributes from texts to complement the heuristic schema. To our knowledge, TEAR is the first framework that supports automated text-driven attribute recommendation, enabling exploratory schema design for table extraction. To evaluate TEAR, we establish the benchmark for table extraction and attribute recommendation on naturally occurring texts, including two real-world datasets, manual annotations, appropriate metrics, and baseline comparisons. Experiments show that TEAR achieves state-of-the-art performance on both tasks, and the recommended attributes effectively enhance extraction performance in exploratory scenarios.

cs.DB↗

arXiv2026

AttenIR: Aligning Dense Visual Attention with Mesh Warping for Unsupervised Image Retargeting

Image retargeting aims to resize images while preserving salient content free from distortion and stretching. Recent learning-based solutions reduce reliance on traditional hand-crafted features and optimization procedures, leading to more efficient and generalizable performance. Nevertheless, existing approaches still struggle to preserve global structure and content fidelity. To address these limitations, we propose AttenIR, an unsupervised image retargeting framework requiring no manual labels, based on content-aware mesh warping, which ef- fectively couples dense visual attention with sparse mesh constraints. We for- mulate the mesh deformation as a vertex displacement regression task. Guided by saliency priors, our method jointly optimizes scale, structure, and geometry preservation losses. By combining dense visual attention with semantic features, it achieves robust, unsupervised retargeting without manual annotations. Our primary contributions include (1) a lightweight unsupervised method for image retargeting that ensures content fidelity and preserves global structure, and (2) a coarse-to-fine projection strategy to align dense visual attention priors with sparse mesh constraints, enabling content-aware deformation at the pixel level. Experiments demonstrate that our method achieves competitive and superior performance compared with both traditional and state-of-the-art learning-based methods.

cs.CV↗

arXiv2026

Chordal Codes: Code Construction and Efficient Gaussian-Elimination Decoding

Maximum-likelihood decoding of linear codes over erasure channels can be considered as solving a linear system of a column submatrix of the parity-check matrix. In practice, Gaussian elimination is usually applied, and its computational cost depends on the structure of the matrix, especially the sparsity and the fill-in generated during the elimination. The \emph{chordal graph}, or \emph{triangulated graph}, first introduced by C. Berge, has a so-called \emph{perfect elimination ordering}, indicating that if the primal graph of a matrix is a chordal graph, then there exists a perfect elimination ordering such that a special class of fill-in under Gaussian elimination following this ordering will be avoided. In this paper, we introduce \emph{chordal codes}, i.e., codes equipped with parity-check matrices such that the primal graphs of the parity-check matrices are chordal. We prove that, for a chordal code, the decoding submatrix associated with any erasure pattern retains a chordal primal graph. So, the complexity of chordal elimination (Gaussian elimination following the perfect elimination ordering applied to the chordal code decoding) will be smaller than decoding a random code by Gaussian elimination. Also, we provide an upper bound on the complexity of chordal elimination.

cs.IT↗

arXiv2026

How Reliable Are Large Language Models for Soil Organic Carbon Assessment? An Australian Benchmark

Soil organic carbon (SOC) is an indicator of agricultural soil condition and carbon storage, but numerical outputs from large language models (LLMs) require validation before use in monitoring or management. We evaluated seven general-purpose LLM configurations on three direct-response tasks: estimating 0--10 cm SOC concentrations for 308 Australian paddocks under two information conditions, calculating SOC stock in 120 matched scenarios, and comparing 300 paddock pairs. References were measured SOC records or deterministic calculations; response validity, repeated-call dispersion and estimated API cost were assessed separately. Additional measured soil attributes reduced concentration mean absolute error by 13--62\% across configurations, although high-SOC underprediction and paddock-specific errors persisted. Six configurations were highly accurate in stock calculations using equation-native units without coarse fragments, but accuracy declined with physically equivalent alternative units. Pairwise accuracy was 90.5--94.6\% overall and 59.1--70.9\% for 52 closely separated pairs; some configurations were sensitive to presentation order. Nearly all outputs were parseable, without necessarily being correct. The benchmark identifies three distinct requirements for AI-mediated SOC assessment: agreement with measured concentrations, unit-consistent stock calculations and reliable discrimination between sites. These findings support task-specific validation and auditable calculations, rather than unverified use of LLM outputs as ecological evidence.

cs.PF↗

arXiv2026

Probing the chromo-electric dipole moment of top quark near the toponium production threshold at LHC

The recent observation of an excess near the kinematic $t\bar{t}$ production threshold by the CMS and ATLAS collaborations suggests the existence of a color-singlet and $S$-wave quasi-bound state of top quark. Due to the non-relativistic nature of top and anti-top quarks in this threshold region, toponium production provides an ideal system to probe the anomalous dipole moments of the top quark. In this work, we investigate the impact of chromo-electric dipole moment (CEDM) in $t\bar{t}$-gluon vertex on toponium production at the LHC. We implement the enhanced near-threshold production of the spin-0 color-singlet toponium state $η_t$ via gluon fusion. The resonant toponium contribution is then combined with the continuum $t\bar{t}$ production amplitude, including the interference effects induced by the top CEDM. Furthermore, we construct a set of asymmetries based on the angular distributions of charged leptons in the leptonic decay channel of $t\bar{t}$. Finally, we derive the expected exclusion limit on the top quark CEDM parameter $d_t^g$ using these lepton angular asymmetries.

hep-ph↗

arXiv2026

Fast and Memory Efficient Offload Training Framework with Hybrid XPU Computation

With the ever-growing size of deep learning models, GPU memory is prone to being insufficient during training. A prominent approach is ZeRO-Offload, which moves the optimizer states to CPU memory and performs parameter update using CPU. However, the deficiencies of ZeRO-Offload include low GPU utilization, imperfect overlapping of communication and computation, and inflexible offloading. In this paper, we leverage Direct Host Access (DHA) on the GPU that can compute data in CPU memory, forming a novel hybrid on-GPU and DHA. We design and implement MemFerry consisting of an execution scheduler and a shadow model. The scheduler strategically chooses layers of parameters for DHA computation and transmits the remaining parameters to GPU memory simultaneously to shorten forward propagation time, and further loads DHA parameters to GPU memory to reduce backward propagation time. The shadow model presents a unified memory abstraction for the parameter partitions stored separately in GPU and CPU memories. To further reduce GPU memory usage, we present MemFerry along with its dynamic programming algorithm that offloads gradients to CPU memory via DHA. We further extend MemFerry to emerging scale-up domains with ScaleUp-MemFerry, which exploits otherwise underutilized accelerator interconnect bandwidth to assist host-to-accelerator data movement through adaptive multi-path transfer. Our experiments show that \system trains up to $1.68\times$ faster and MemFerry can train $1.52\times$ larger model compared to ZeRO-Offload on a single GPU, and increase training speed by at least $28.1\%$ when scaling to data parallelism on 8 GPUs. We further extend the design to a Huawei CloudMatrix384 scale-Up node with up to 8 NPUs, and our ScaleUp-MemFerry reduces the end-to-end iteration time by up to $20.7\%$ over DeepSpeed.

cs.DC↗

arXiv2026

ANT: A Multi-Granularity Network Traffic Dataset and Benchmark for Agents Behavior Auditing

The growing adoption of large language model (LLM) agents creates a need for network administrators and security teams to audit agent behavior within organizational networks without inspecting private user content. Network traffic offers an observable source of evidence, but how much it reveals about agent tasks and operations remains unclear. Existing traffic datasets lack the joint task and stage annotations needed to evaluate this question. We introduce ANT (Agent Network Traffic), a dataset providing agent behavior information at risk, scenario, and behavior primitive granularities alongside network traffic. ANT contains 3,114 execution episodes across 20 tasks and five scenarios, comprising 276,417 bidirectional flows and 40,049 behavior primitive segments organized into 47 macro groups. We establish a benchmark for agent risk identification, scenario recognition, and behavior primitive classification using 13 representative traffic analysis baselines. The results show that existing methods recover useful but uneven behavioral signals. They struggle to identify risk when malicious workflows resemble benign tasks and to distinguish scenarios with similar traffic patterns. Primitive classification is more reliable for frequent macro groups and those with distinctive traffic patterns than for rare or semantically similar groups. ANT provides a common basis for developing more precise auditing and forensic analysis of agent behavior from network traffic. Our data and code are available at https://anonymous.4open.science/r/ant-main-suite-7BC0/.

cs.AI↗

arXiv2026

InfoAgent: Traceable Generation and Repair of Evidence-Grounded Infographics

Reliable infographic generation requires facts, symbols, and visual relations to remain consistent through rendering and revision. Correcting one element also requires tracking its supporting evidence and the dependencies affected by the change. We present \textbf{InfoAgent}, a training-free framework for \emph{evidence-bound visual-symbolic program synthesis}. Its Infographic Visual Description (IVD) records factual payloads, evidence provenance, execution routes, and verification obligations in a typed dependency graph. Retrieved design priors guide compilation, and layered execution combines raster synthesis with editable symbolic and binding objects while retaining their traces. Dependency-aware repair localizes corrections, rechecks affected dependencies, and requires protected obligations to remain satisfied under the declared checkers. Unresolved obligations remain explicit. On IGenBench, InfoAgent achieves 93.0 Q-ACC and 59.0 I-ACC. We also introduce InfoGraphicBench-Evidence, where complete-checklist pass rates on 200 test requests increase from 21.5\% for Same-IVD Prompt to 23.5\% for the initial layered output and 28.5\% after repair, using the same evidence and initial IVD. On 120 audited repair cases, localized repair edits 12.4\% of the canvas on average, compared with 67.3\% for global regeneration.

cs.CV↗

arXiv2026

NetLexicon: Learning Discrete Behavioral Representations for Encrypted Web Traffic Analysis

Encrypted Web traffic analysis requires effective representations of observable communication behavior. Existing pretraining methods often adapt NLP/CV objectives and sequence architectures, motivating learning objectives that capture traffic-specific interaction patterns. We present NetLexicon, a discrete pretraining framework that learns reusable behavioral states from unlabeled traffic. It converts contextual traffic windows into discrete states through vector quantization, constructing a compact traffic lexicon. We design two complementary pretraining objectives. State Transition Prediction (STP) forecasts subsequent sequence structure and packet features from observed history, while Statistical Feature Alignment (SFA) grounds learned states in window-level traffic statistics. Together, they guide the lexicon to capture recurring communication behaviors and their evolution. We evaluate NetLexicon on four benchmarks covering Web application identification, service type identification, and malware detection. NetLexicon improves Macro-F1 by up to 25.5 percentage points over the strongest baseline on each benchmark and reduces fine-tuning time per epoch by up to 23.6 times relative to the evaluated baselines. Further analysis shows that the learned discrete states capture recognizable patterns in packet size, timing, and data transfer. These results demonstrate that incorporating observable behavioral structure into pretraining supports effective, efficient, and interpretable representations for encrypted traffic analysis.

cs.NI↗

arXiv2026

Searching for long-lived ALPs with a laser-assisted optical dump

The feeble interactions of light axion-like particles (ALPs) render them long-lived. Probing long-lived ALPs therefore demands facilities with a macroscopic decay volume to match their potentially long decay lengths, such as high-intensity beam dump experiments. An optical dump setup was proposed by utilizing hard photons from the collision of a high-energy electron beam and a high-intensity laser pulse. In this work, we revisit the probe of long-lived ALPs with MeV$\sim$ GeV mass via a laser-assisted optical dump. We consider the low-energy effective Lagrangian for ALPs incorporating the ALP-photon and ALP-fermion interactions. The scope of optical dump searches is extended to both the ALP-photon coupling induced Primakoff process and the Compton-like scattering via the ALP-electron coupling. We also investigate the correlation between Primakoff process and Compton scattering, and exhibit the interplay of two ALP couplings in light of optical dump experiment.

hep-ph↗

arXiv2026

Testing for Monotone Equilibrium Strategies in Games of Incomplete Information

This paper develops a unified framework for testing monotonicity of Bayesian Nash equilibrium strategies in unobserved types in games of incomplete information. We show that, under symmetric independent private types, monotonicity of differentiable equilibrium strategies is equivalent to monotonicity of a quasi-inverse strategy identified from observed actions. This allows the problem to be reformulated as testing a countable set of moment inequalities involving unconditional expectations. We propose a Cramer-von Mises-type statistic with bootstrap critical values. The method accommodates covariates and game heterogeneity. Monte Carlo simulations demonstrate finite-sample performance, and an application to procurement auctions illustrates cartel detection.

econ.EM↗