arXiv subjects

Liangjian Wen

Publications and source records attributed to Liangjian Wen.

At least 19 recordsLinked to original sources

arXiv2026

Pay More Attention To Text In High-Resolution MLLMs

Failures of high-resolution MLLMs are commonly attributed to a visual problem, motivating zooming, cropping, and related visual interventions to recover fine-grained evidence or suppress interference. Yet recent studies suggest that relevant visual evidence is already encoded in intermediate representations, indicating that visual-side improvements alone insufficient. This raises a natural question: does the remaining bottleneck lie in the text that guides visual search? We identify a previously overlooked linguistic bottleneck: questions formulated for answering do not necessarily specify the visual evidence required for localization. To address this mismatch, we introduce EviSpec, a training-free compiler that derives complementary evidence specifications while preserving the original question for final reasoning. We further validate it through matched-control experiments that isolate the roles of evidence specification and localization. With the search budget fixed, structured evidence specifications yield an 8.6% relative gain over generic requests. With evidence geometry matched, the evidence localized by EviSpec yields a 14.8% relative gain over random evidence. Together, these controls isolate the benefit of specifying what evidence to seek rather than merely expanding visual access. Across all five MLLMs, EviSpec consistently improves upon the corresponding baseline on each of the three benchmarks, yielding average relative gains of \textbf{10.4%, 8.8%, and 12.4%} on V\textsuperscript{*}Bench, HR-Bench-4K, and HR-Bench-8K, respectively. Beyond high-resolution reasoning, EviSpec also achieves state-of-the-art performance on VQA and hallucination-focused benchmarks.

cs.CV↗

arXiv2026

Dependency, Compression, and Synergy: A Unified Information-Theoretic View of Multimodal Learning

Recent advances in multimodal foundation models have intensified the need to understand how different modalities share, preserve, and complement information. Mutual Information (MI), the Information Bottleneck (IB), and Partial Information Decomposition (PID) provide complementary perspectives, yet existing studies often treat them as isolated tools. This survey presents an information-theoretic perspective connecting these principles as progressively refined views of multimodal information processing: MI characterizes inter-modal dependency, IB explains task-oriented information preservation under compression, and PID decomposes preserved information into redundancy, uniqueness, and synergy. We review 170 recent studies (2018--2026) and 12 foundational works, organizing multimodal learning around four challenges: cross-modal alignment, information-efficient fusion, interaction-type characterization, and scaling to multimodal foundation models. Rather than using application domains as primary taxonomy axes, we interpret healthcare, robotics, recommendation systems, affective computing, and wireless communications as empirical validations of these information principles. Beyond taxonomy, we organize existing multimodal paradigms within a single information-theoretic coordinate system -- the Generalized Multimodal Information Lagrangian -- in which they occupy exact or approximate parameter corners, and whose unoccupied regions name candidate method families the literature has not yet built. We further discuss how emerging multimodal foundation models instantiate these principles at scale and identify open challenges including scalable information estimation in high-dimensional settings, standardized evaluation across information-theoretic methods, combinatorial complexity of multimodal PID, and the transition from post-hoc information analysis toward information-aware multimodal learning.

cs.IT↗

arXiv2026

Long-Delayed Afterpulse Measurement of JUNO 20-inch Photomultiplier Tubes

In large-scale liquid scintillator detectors such as the Jiangmen Underground Neutrino Observatory (JUNO), high-intensity events like cosmic muons induce photomultiplier tube (PMT) afterpulses that can interfere with the analysis of delayed physics signals. To systematically evaluate this instrumental background, we present a dedicated measurement of long-delayed afterpulses in two types of JUNO 20-inch PMTs: a dynode-based PMT and a microchannel-plate (MCP) PMT. The afterpulse time profiles were first characterized within a direct 1.8~ms waveform window and were further extended to 20~ms using a sliding-window readout strategy. Distinct long-delayed components are observed, revealing a strong dependence on the PMT multiplication structure. The dynode PMT exhibits a broad afterpulse component peaking at approximately 260~$μ$s, whereas the MCP-PMT shows a pronounced peak around 90~$μ$s, an additional component around 550~$μ$s, and a much smaller, broadly distributed millisecond-scale component. For the microsecond-scale components, the afterpulse yield per primary photoelectron is at the $10^{-3}$ level in the selected delayed windows and increases approximately linearly with the primary light intensity. The accumulated delayed activity can therefore become non-negligible following high-intensity events. These quantitative findings provide critical inputs for PMT response characterization and for the accurate modeling of delayed correlated backgrounds in high-precision neutrino experiments.

hep-ex↗

arXiv2026

An eightfold equivalence-preserving speedup of the JUNO OMILREC vertex and energy reconstruction

The Jiangmen Underground Neutrino Observatory (JUNO) reconstructs each event's vertex and energy with OMILREC, a maximum-likelihood fit that scans all $17{,}612$ large photomultiplier tubes (LPMTs) in every Minuit function evaluation, about $470$ times per event. This inner loop dominates the reconstruction CPU cost. Profiling shows that the production algorithm is latency-bound, sustaining only $9.9%$ of scalar floating-point peak because of virtual-function dispatch, ROOT-histogram pointer chasing, and repeated computation. We apply staged \emph{equivalence-preserving} optimizations: flattened data layouts, vectorizable geometry, hoisting of Minuit-invariant work, per-event precomputation, fit-phase loop splitting and indexing, and reduced-precision fast paths. Each stage is checked against a frozen reference from the unmodified code. The optimized implementation achieves single-thread speedups of $8.06\times$ ($1524.8 \rightarrow 189.2$~ms/event) on an Intel Xeon Platinum~8358P and $5.22\times$ ($705.1 \rightarrow 134.9$~ms/event) on an AMD~EPYC~9654, increasing to $8.6\times$ ($177.7$~ms/event) after further optimization. The likelihood remains bit-identical through the first seven releases and later agrees within a relative drift of $1.3\times10^{-14}$, below the $10^{-13}$ contract. For typical events, reconstructed vertex and energy agree with the baseline within $4$~mm and $7$~keV; a few boundary cases reach different valid minima owing to an improved minimizer seed. An eight-metric physics-acceptance test also passes on about $861{,}000$ $^{68}$Ge calibration events. Developed with assistance from an AI coding agent operating under these verification gates, this workflow offers a transferable template for accelerating likelihood-based reconstruction in large neutrino and collider detectors without changing physics output.

physics.ins-det↗

arXiv2026

Rethinking Incompleteness: Formalizing Protocol Divergence and Train-Once Learning for Robust IMVC

Standard IMVC evaluation retrains separate models for different missing-data configurations. We show that this paradigm obscures a fundamental vulnerability: missing rate alone is insufficient to characterize data incompleteness. Specifically, we show that protocols with identical nominal missing rates can differ by up to $50\times$ in their proportion of fully observed samples, inducing drastically different learning regimes. We formalize this phenomenon as incompleteness divergence, providing measures that capture structural disparities across missing-data protocols. We further prove that for a broad class of reconstruction-based objectives, learning becomes structurally ill-posed when the proportion of complete samples falls below a critical threshold, leading to near-random performance. To bypass this theoretical bound, we propose CRAFT (Complete-data Robust Attention-masked Fusion Transformer). CRAFT shifts the burden of robustness from the loss function to the architecture via two key properties: (i) per-sample independence, which removes reliance on complete-sample co-occurrence, and (ii) mask-aware variable-length fusion, which aggregates only observed views through attention masking. This design allows a single model, trained once on complete data, to generalize to diverse missing patterns at inference time without retraining. Extensive experiments on seven benchmarks show that CRAFT matches or outperforms per-configuration baselines while reducing training overhead by $8.8\times$, demonstrating that robustness to missing data can be achieved as an inherent architectural property. Code (CRAFT) and our imvc-audit toolkit are available at https://anonymous.4open.science/r/CRAFT-BF80/ and https://anonymous.4open.science/r/imvc-audit-8263/.

cs.LG↗

arXiv2026

Web-CogReasoner: Towards Multimodal Knowledge-Induced Cognitive Reasoning for Web Agents

Multimodal large-scale models have significantly advanced the development of web agents, enabling perception and interaction with digital environments akin to human cognition. In this paper, we argue that web agents must first acquire sufficient knowledge to effectively engage in cognitive reasoning. Therefore, we decompose a web agent's capabilities into two essential stages: knowledge content learning and cognitive processes. To formalize this, we propose Web-CogKnowledge Framework, categorizing knowledge as Factual, Conceptual, and Procedural. In this framework, knowledge content learning corresponds to the agent's processes of Memorizing and Understanding, which rely on the first two knowledge types, representing the "what" of learning. Conversely, cognitive processes correspond to Exploring, grounded in Procedural knowledge, defining the "how" of reasoning and action. To facilitate knowledge acquisition, we construct the Web-CogDataset, a structured resource curated from 14 real-world websites, designed to systematically instill core knowledge necessary for web agent. This dataset serves as the agent's conceptual grounding-the "nouns" upon which comprehension is built-as well as the basis for learning how to reason and act. Building on this foundation, we operationalize these processes through a novel knowledge-driven Chain-of-Thought (CoT) reasoning framework, developing and training our proposed agent, the Web-CogReasoner. Extensive experimentation reveals its significant superiority over existing models, especially in generalizing to unseen tasks where structured knowledge is decisive. To enable rigorous evaluation, we introduce the Web-CogBench, a comprehensive evaluation suite designed to assess and compare agent performance across the delineated knowledge domains and cognitive capabilities. Our code and data is open sourced at https://github.com/Gnonymous/Web-CogReasoner

cs.CL↗

arXiv2026

PMDformer: Patch-Mean Decoupling Information Transformer for Long-term Forecasting

Long-term time series forecasting (LTSF) plays a crucial role in fields such as energy management, finance, and traffic prediction. Transformer-based models have adopted patch-based strategies to capture long-range dependencies, but accurately modeling shape similarities across patches and variables remains challenging due to scale differences. To address this, we introduce patch-mean decoupling (PMD), which separates the trend and residual shape information by subtracting the mean of each patch, preserving the original structure and ensuring that the attention mechanism captures true shape similarities. Futhermore, to more effectively model long-range dependencies and capture cross-variable relationships, we propose Trend Restoration Attention (TRA) and Proximal Variable Attention (PVA). The former module reintegrates the decoupled trend from PMD while calculating attention output. And the latter focuses cross-variable attention on the most relevant, recent time segments to avoid overfitting on outdated correlations. Combining these components, we propose PMDformer, a model designed to effectively capture shape similarity in long-term forecasting scenarios. Extensive experiments indicate that PMDformer outperforms existing state-of-the-art methods in stability and accuracy across multiple LTSF benchmarks. The code is available at https://github.com/aohu1105/PMDformer.

cs.AI↗

arXiv2026

AAPA: Adversarially Anchored Preference Alignment for Post-Training of Large Language Models

Post-training alignment of large language models often combines supervised fine-tuning (SFT) on expert demonstrations with reinforcement learning (RL) from preference or verifiable feedback. SFT provides a useful behavioral anchor but can overfit to static demonstrations, whereas RL encourages exploration but may drift from expert behavior or exploit imperfect rewards. We propose \textbf{AAPA} (\emph{Adversarially Anchored Preference Alignment}), a plug-in framework that augments existing post-training objectives with a sentence-level adversarial anchoring signal. AAPA compares policy rollouts with offline, pre-collected expert responses using a fixed lightweight discriminator, and therefore requires neither online teacher inference nor discriminator co-training during policy optimization. The same anchoring term can be added to SFT, GRPO, and CHORD while preserving their original training pipelines. Experiments on instruction-following benchmarks show that AAPA consistently improves the corresponding base objectives across model scales. In particular, the staged AAPA configuration improves over a strong GRPO baseline by 5.77\% on \texttt{Qwen3-0.6B} and 3.75\% on \texttt{Qwen3-4B}. Further analyses on response length, log-probability distributions, and discriminator variants suggest that adversarial anchoring provides a stable semantic grounding signal for preference optimization. Code is available at \url{https://github.com/IsFaqq/AAPA}.

cs.AI↗

arXiv2026

The Alpha Illusion: Reported Alpha from LLM Trading Agents Should Not Be Treated as Deployment Evidence

End-to-end LLM trading agents have moved quickly from research curiosity to a small ecosystem of named systems, including FinCon, FinMem, TradingAgents, FinAgent, QuantAgent, and FLAG-Trader. Several of these report headline Sharpe ratios that would be material if read at face value on a deployment desk, and associated benchmarks such as FinBen report trading-task Sharpe statistics in the same range. The gap between architecture research and deployment claim has been crossed too freely on both sides of the academia--industry divide. We take a position on that gap: reported alpha from end-to-end LLM trading agents should not be treated as deployment evidence. Before such returns can support claims of deployable trading capability, they must survive structural validity tests for temporal integrity, real-world frictions, counterfactual robustness, predictive calibration, numerical execution, and multi-agent disaggregation. Current public evidence cannot yet distinguish robust predictive ability from temporal contamination, unmodeled frictions, short-window Sharpe uncertainty, narrative fitting, and parametric priors. The problem is not only evaluative but structural. Language confidence is not tradable probability, narrative reasoning is not numerical execution, and model priors may become undisclosed implicit factor exposures. We contribute a minimum reporting protocol suite, P1--P6, with tiered applicability by claim strength, and a conservative modular alternative that uses LLMs as auditable information interfaces upstream of independent calibration, risk, and execution modules. Code and reproduction harness: \url{https://github.com/hj1650782738/Trading}.

cs.CE↗

arXiv2026

A Methanol-mediated Room-Temperature Synthesis of Tellurium-Loaded Liquid Scintillators for Neutrinoless Double Beta Decay Search

This study establishes a methanol-mediated room-temperature synthesis approach for tellurium-diol (Te-diol) compounds for use in tellurium-loaded liquid scintillator (Te-LS). The synthesis involves the direct reaction of telluric acid with diols (e.g., 1,2-hexanediol) in methanol (MeOH) under ambient conditions (25$\pm$5\textdegree C), with the key features of lower energy consumption and enhanced safety compared with high-temperature azeotropic distillation method. Mechanistic studies reveal that MeOH serves not merely as a solvent but also exhibits a catalytic effect, playing a dual role in this water-free, heterogeneous room-temperature synthesis. The Te-diol compounds enable fabrication of high-performance Te samples exhibiting exceptional optical transparency (attenuation length = 20.1$\pm$1.1 m at $λ$=430 nm for 1\% Te mass loading), which is reported here for the first time. Furthermore, the Te-LS achieves long-term spectral stability approaching or exceeding one year for both 1\% and 3\% Te mass loadings, and demonstrates a light yield comparable those of both the azeotropic distillation method and the SNO+ collaboration's Type I loading method, albeit modestly lower than that of their Type II method. The developed protocol offers the potential for a more energy efficient alternative for large-scale Te-LS production, particularly valuable for next-generation neutrinoless double-beta decay experiments.

physics.ins-det↗

arXiv2026

InfMasking: Unleashing Synergistic Information by Contrastive Multimodal Interactions

In multimodal representation learning, synergistic interactions between modalities not only provide complementary information but also create unique outcomes through specific interaction patterns that no single modality could achieve alone. Existing methods may struggle to effectively capture the full spectrum of synergistic information, leading to suboptimal performance in tasks where such interactions are critical. This is particularly problematic because synergistic information constitutes the fundamental value proposition of multimodal representation. To address this challenge, we introduce InfMasking, a contrastive synergistic information extraction method designed to enhance synergistic information through an Infinite Masking strategy. InfMasking stochastically occludes most features from each modality during fusion, preserving only partial information to create representations with varied synergistic patterns. Unmasked fused representations are then aligned with masked ones through mutual information maximization to encode comprehensive synergistic information. This infinite masking strategy enables capturing richer interactions by exposing the model to diverse partial modality combinations during training. As computing mutual information estimates with infinite masking is computationally prohibitive, we derive an InfMasking loss to approximate this calculation. Through controlled experiments, we demonstrate that InfMasking effectively enhances synergistic information between modalities. In evaluations on large-scale real-world datasets, InfMasking achieves state-of-the-art performance across seven benchmarks. Code is released at https://github.com/brightest66/InfMasking.

cs.LG↗

arXiv2025

Fluorescence time profile measurement of LAB based liquid scintillator in response to medium relativistic ion particles

Liquid scintillator is widely used in particle physics experiments due to its high light yield, good timing resolution, scalability and low cost. Certain liquid scintillators exhibit pulse shape discrimination capabilities because of difference in fluorescence timing properties induced by different particles. Its fluoresence timing properties have been measured mostly for radioactive decay sources at MeV energies. We present a novel measurement of fluorescence time properties of LAB based liquid scintillator in response to high-energy ions of hydrogen (Z = 1), helium (Z = 2) and Krypton at around 200-300 MeV/u for the first time. We compared the results to those from radioactive sources and observed a distinct $dE/dX$ dependence, regardless of the particle type. These findings are essential for physics searches such as the diffuse supernova neutrino background in large liquid scintillator detectors like JUNO, and are also critical towards understanding the underlying scintillation timing mechanism.

physics.ins-det↗

arXiv2025

Disentangling Homophily and Heterophily in Multimodal Graph Clustering

Multimodal graphs, which integrate unstructured heterogeneous data with structured interconnections, offer substantial real-world utility but remain insufficiently explored in unsupervised learning. In this work, we initiate the study of multimodal graph clustering, aiming to bridge this critical gap. Through empirical analysis, we observe that real-world multimodal graphs often exhibit hybrid neighborhood patterns, combining both homophilic and heterophilic relationships. To address this challenge, we propose a novel framework -- \textsc{Disentangled Multimodal Graph Clustering (DMGC)} -- which decomposes the original hybrid graph into two complementary views: (1) a homophily-enhanced graph that captures cross-modal class consistency, and (2) heterophily-aware graphs that preserve modality-specific inter-class distinctions. We introduce a \emph{Multimodal Dual-frequency Fusion} mechanism that jointly filters these disentangled graphs through a dual-pass strategy, enabling effective multimodal integration while mitigating category confusion. Our self-supervised alignment objectives further guide the learning process without requiring labels. Extensive experiments on both multimodal and multi-relational graph datasets demonstrate that DMGC achieves state-of-the-art performance, highlighting its effectiveness and generalizability across diverse settings. Our code is available at https://github.com/Uncnbb/DMGC.

cs.AI↗

arXiv2025

Neutrino type identification for atmospheric neutrinos in a large homogeneous liquid scintillation detector

Atmospheric neutrino oscillations are important to the study of neutrino properties, including the neutrino mass ordering problem. A good capability to identify neutrinos' flavor and neutrinos against antineutrinos is crucial in such measurements. In this paper, we present a machine-learning-based approach for identifying atmospheric neutrino events in a large homogeneous liquid scintillator detector. This method identifies features of PMT waveforms that reflect event topologies and uses them as input to machine learning models. In addition, neutron-capture information is utilized to achieve neutrino versus antineutrino discrimination. Preliminary performances based on Monte Carlo simulations are presented, which demonstrate such a detector's potential in future measurements of atmospheric neutrinos such as the one planned for the JUNO experiment.

hep-ex↗

arXiv2025

GazeCLIP: Enhancing Gaze Estimation Through Text-Guided Multimodal Learning

Visual gaze estimation, with its wide-ranging application scenarios, has garnered increasing attention within the research community. Although existing approaches infer gaze solely from image signals, recent advances in visual-language collaboration have demonstrated that the integration of linguistic information can significantly enhance performance across various visual tasks. Leveraging the remarkable transferability of large-scale Contrastive Language-Image Pre-training (CLIP) models, we address the open and urgent question of how to effectively apply linguistic cues to gaze estimation. In this work, we propose GazeCLIP, a novel gaze estimation framework that deeply explores text-face collaboration. Specifically, we introduce a meticulously designed linguistic description generator to produce text signals enriched with coarse directional cues. Furthermore, we present a CLIP-based backbone adept at characterizing text-face pairs for gaze estimation, complemented by a fine-grained multimodal fusion module that models the intricate interrelationships between heterogeneous inputs. Extensive experiments on three challenging datasets demonstrate the superiority of GazeCLIP, which achieves state-of-the-art accuracy. Our findings underscore the potential of using visual-language collaboration to advance gaze estimation and open new avenues for future research in multimodal learning for visual tasks. The implementation code and the pre-trained model will be made publicly available.

cs.CV↗

arXiv2024

Machine-Learning based photon counting for PMT waveforms and its application to the improvement of the energy resolution in large liquid scintillator detectors

Photomultiplier tubes (PMTs) are widely used in particle experiments for photon detection. PMT waveform analysis is crucial for high-precision measurements of the position and energy of incident particles in liquid scintillator (LS) detectors. A key factor contributing to the energy resolution in large liquid scintillator detectors with PMTs is the charge smearing of PMTs. This paper presents a machine-learning-based photon counting method for PMT waveforms and its application to the energy reconstruction, using the JUNO experiment as an example. The results indicate that leveraging the photon counting information from the machine learning model can partially mitigate the impact of PMT charge smearing and lead to a relative 2.0% to 2.8% improvement on the energy resolution in the energy range of [1, 9] MeV.

physics.ins-det↗

arXiv2024

TimeCNN: Refining Cross-Variable Interaction on Time Point for Time Series Forecasting

Time series forecasting is extensively applied across diverse domains. Transformer-based models demonstrate significant potential in modeling cross-time and cross-variable interaction. However, we notice that the cross-variable correlation of multivariate time series demonstrates multifaceted (positive and negative correlations) and dynamic progression over time, which is not well captured by existing Transformer-based models. To address this issue, we propose a TimeCNN model to refine cross-variable interactions to enhance time series forecasting. Its key innovation is timepoint-independent, where each time point has an independent convolution kernel, allowing each time point to have its independent model to capture relationships among variables. This approach effectively handles both positive and negative correlations and adapts to the evolving nature of variable relationships over time. Extensive experiments conducted on 12 real-world datasets demonstrate that TimeCNN consistently outperforms state-of-the-art models. Notably, our model achieves significant reductions in computational requirements (approximately 60.46%) and parameter count (about 57.50%), while delivering inference speeds 3 to 4 times faster than the benchmark iTransformer model

cs.LG↗

arXiv2024

A practical approach of measuring $^{238}$U and $^{232}$Th in liquid scintillator to sub-ppq level using ICP-MS

Liquid scintillator (LS) is commonly utilized in experiments seeking rare events due to its high light yield, transparency, and radiopurity. The concentration of $^{238}$U and $^{232}$Th in LS consistently remains below 1 ppq (10$^{-15}$ g/g), and the current screening result is based on a minimum 20-ton detector. Inductively coupled plasma mass (ICP-MS) spectroscopy is well-regarded for its high sensitivity to trace $^{238}$U and $^{232}$Th. This study outlines a method for detecting $^{238}$U and $^{232}$Th in LS at the sub-ppq level using ICP-MS, involving the enrichment of $^{238}$U/$^{232}$Th from the LS through acid extraction. With meticulous cleanliness control, $^{238}$U/$^{232}$Th in approximately 2 kg of LS is concentrated by acid extraction with 0.4 (0.3) pg $^{238}$U ($^{232}$Th) contamination. Three standard adding methods are employed to assess recovery efficiency, including radon daughter, 2,5-diphenyloxazole (PPO), and natural non-existent $^{233}$U/$^{229}$Th. The method detection limit at a 99% confidence level of this approach can reach approximately 0.2-0.3 ppq for $^{238}$U/$^{232}$Th with nearly 100% recovery efficiency.

physics.ins-det↗