Showing 1–50 of 116 results for author: Wan, B

Physics-informed neural network for inverse modeling of granular flows

Authors: Bing Wan, Bidan Zhao, Junwu Wang

Abstract: Granular flows are ubiquitous in natural and industrial systems, yet their complex dynamics remain difficult to characterize. For inverse problems involving unknown inlet, outlet, and wall boundary conditions, where CFD simulations are challenging, reconstructing complete flow fields from sparse observations constitutes a challenging inverse problem. In this study, a physics-informed neural networ… ▽ More Granular flows are ubiquitous in natural and industrial systems, yet their complex dynamics remain difficult to characterize. For inverse problems involving unknown inlet, outlet, and wall boundary conditions, where CFD simulations are challenging, reconstructing complete flow fields from sparse observations constitutes a challenging inverse problem. In this study, a physics-informed neural network framework driven by both physical mechanisms and measurement data is developed to reconstruct the steady-state full-field distribution of granular flows in a pipe. The proposed approach integrates sparse measurement data with governing equations and constitutive relations and is trained using high-fidelity datasets generated by CFD solutions of a continuum model. The framework incorporates a dimensionless loss formulation, physics-informed initialization, dynamic global weighting, and a locally weighted granular temperature data-loss strategy. These treatments enable accurate reconstruction of the complete flow-field evolution. This work establishes a robust methodological framework for flow-field reconstruction in complex granular flow systems. △ Less

Submitted 19 August, 2026; originally announced August 2026.

Data-Driven Generation of Compact Quasi-Isodynamic Stellarators

Authors: Yang Han, Hanlin Chen. Shuai Cao, Zhiyuan Lu, Dehong Chen, Guosheng Xu, Baonian Wan

Abstract: Stellarator design explores a vast space of three-dimensional plasma boundaries, only a small fraction of which yields usable equilibria. Data-driven models can narrow this search by learning from existing optimized configurations. Building on the ConStellaration database, we extend conditional boundary generation to four-field-period QI configurations, focusing on the sparsely sampled low-aspect-… ▽ More Stellarator design explores a vast space of three-dimensional plasma boundaries, only a small fraction of which yields usable equilibria. Data-driven models can narrow this search by learning from existing optimized configurations. Building on the ConStellaration database, we extend conditional boundary generation to four-field-period QI configurations, focusing on the sparsely sampled low-aspect-ratio regime. The approach learns the common geometric structure of known QI equilibria and then adapts it using a small high-fidelity compact dataset, allowing target magnetic properties to guide generation beyond the original data distribution. This adaptation reduces the compact-domain test loss by approximately 87% and yields converged ultra-compact candidates consistent with the prescribed conditions. Several candidates show favorable confinement indicators, and one provides a useful seed for further QI optimization and finite-beta assessment. The method therefore serves as a data-informed front end to high-fidelity physics and optimization. △ Less

Submitted 11 August, 2026; originally announced August 2026.

Comments: 23 pages, 12 figures, and 2 tables

LAVA: Logic-Aware Validation and Augmentation Framework for Large-Scale Financial Document Auditing

Authors: Ruoqi Shu, Xuhui Wang, Isaac Wang, Yanming Mai, Bo Wan

Abstract: Financial document validation in production, such as payroll auditing, tax compliance, and loan underwriting, demands exceptional accuracy, consistency, and reproducibility under strict enterprise constraints. In practice, documents arrive with heterogeneous layouts and formats, semantically rich and context-dependent content, and embedded business rules that current pipelines struggle to process… ▽ More Financial document validation in production, such as payroll auditing, tax compliance, and loan underwriting, demands exceptional accuracy, consistency, and reproducibility under strict enterprise constraints. In practice, documents arrive with heterogeneous layouts and formats, semantically rich and context-dependent content, and embedded business rules that current pipelines struggle to process reliably. We introduce LAVA (Logic-Aware Validation and Augmentation), a modular, backbone-agnostic pipeline built on multimodal large language models, that integrates a four-stage design: document-rule retrieval, layout-preserving information extraction, auxiliary metadata enrichment, and auditable symbolic/arithmetic verification. LAVA supports robust rule grounding, fine-grained error attribution, and consistent, traceable end-to-end execution, capabilities essential for high-stakes deployment. Evaluated on a large real-world benchmark with diverse financial documents and dozens of expert-curated validation rules, LAVA outperforms baselines in hallucination control and edge-case handling while maintaining efficient token usage, demonstrating practicality for high-volume, time-critical validation. △ Less

Submitted 17 August, 2026; originally announced August 2026.

Journal ref: Proceedings of The 10th Workshop on Financial Technology and Natural Language Processing (FinNLP 2025), Association for Computational Linguistics, pp. 75-92, 2025

Direct Optimization of Stellarator Omnigenity from the Second Adiabatic Invariant

Authors: Hanlin Chen, Zhiyuan Lu, Guosheng Xu, Shuai Cao, Yang Han, Dehong Chen, Baonian Wan

Abstract: Stellarators offer a steady-state, disruption-free path to fusion energy but suffer from enhanced particle losses due to their three-dimensional geometry. Existing optimization methods rely on geometric proxies rather than the actual trapped-particle orbit condition. We present a differentiable framework that directly optimizes the fundamental orbit action governing particle confinement. The appro… ▽ More Stellarators offer a steady-state, disruption-free path to fusion energy but suffer from enhanced particle losses due to their three-dimensional geometry. Existing optimization methods rely on geometric proxies rather than the actual trapped-particle orbit condition. We present a differentiable framework that directly optimizes the fundamental orbit action governing particle confinement. The approach yields compact stellarator designs with excellent fast-ion confinement, finite-pressure stability, and coil compatibility, demonstrating that first-principles orbit optimization can be integrated with engineering constraints in a single computational workflow for fusion reactor design. △ Less

Submitted 3 August, 2026; v1 submitted 3 August, 2026; originally announced August 2026.

Comments: 25 pages, 13 figures. Corresponding authors: zhiyuan.lu@ipp.ac.cn, gsxu@ipp.ac.cn

FRAMES: Guarded and Dual-Objective Skill Evolution for Agents in Policy-Governed Enterprise Workflows

Authors: Xuhui Wang, Ruoqi Shu, Chen Dan, Tianhua Xu, Mengxi Luo, Yanming Mai, Bo Wan

Abstract: LLM agents increasingly run policy-bound enterprise workflows such as document auditing, where they must apply rules consistently, ground every value, and stay auditable. Improving these agents is hard: operational feedback is sparse and unlabeled, edits to one rule can regress unrelated cases, and accuracy must improve without inflating inference cost or losing auditability. We present FRAMES, a… ▽ More LLM agents increasingly run policy-bound enterprise workflows such as document auditing, where they must apply rules consistently, ground every value, and stay auditable. Improving these agents is hard: operational feedback is sparse and unlabeled, edits to one rule can regress unrelated cases, and accuracy must improve without inflating inference cost or losing auditability. We present FRAMES, a closed-loop framework that cold-starts deployable skills from existing assets and then evolves them through consensus-based mutation, Pareto selection over accuracy and cost, and an anti-regression guarantee, all while preserving auditability. Deployed on our internal production system, FRAMES attains the best accuracy-cost trade-off among baselines, with the same gains reproduced on tau-bench. △ Less

Submitted 3 August, 2026; originally announced August 2026.

LayoutLite: Token-Level Implicit Layout Analysis for Efficient Document OCR

Authors: Xudong Liu, Bicheng Wan, Yulin Jin

Abstract: End-to-end OCR systems based on vision-language models have achieved strong performance in complex document OCR, but their efficiency is limited by the large number of visual tokens produced from document images. Many of these tokens correspond to blank margins or visually redundant regions, yet directly applying generic visual token compression methods may remove OCR-critical fine-grained details… ▽ More End-to-end OCR systems based on vision-language models have achieved strong performance in complex document OCR, but their efficiency is limited by the large number of visual tokens produced from document images. Many of these tokens correspond to blank margins or visually redundant regions, yet directly applying generic visual token compression methods may remove OCR-critical fine-grained details. In this paper, we propose LayoutLite, a lightweight plug-and-play module for efficient document OCR. Instead of relying on explicit document layout detection, LayoutLite performs implicit layout analysis at the token level between the vision encoder and the language decoder. It aggregates multi-layer visual representations from the vision encoder, and predicts an importance score for each visual token with a lightweight scoring network. Low-information tokens are then removed before entering the language decoder while preserving the original spatial positional information of retained tokens. To train LayoutLite without human annotations, we cast token selection as a reinforcement learning problem and optimize it with a group-relative policy optimization objective driven by OCR output consistency, together with an auxiliary layout supervision signal to stabilize training. Experiments on OmniDocBench demonstrate that LayoutLite can substantially reduce visual token length and inference cost with negligible degradation in recognition quality. We further evaluate LayoutLite on two OCR-specialized VLMs, FireRed-OCR and Logics-Parsing-V2. Under up to 50% token compression, LayoutLite preserves almost the same score on both models while reducing prefill latency, FLOPs, and KV cache memory by over 40%, with only a small additional inference overhead. These results show that token-level implicit layout analysis is an effective and practical approach for accelerating VLM-based OCR systems. △ Less

Submitted 24 July, 2026; originally announced July 2026.

Comments: 11 pages, 7 figures

Rethinking MCP Security: A Large-Scale Study of Runtime MCP Servers and Security Scanner Reliability

Authors: Pei Chen, Baichao An, Mengying Wu, Binwang Wan, Geng Hong, Jinsong Chen, Xudong Pan, Jiarun Dai, Min Yang

Abstract: The Model Context Protocol (MCP) has rapidly established itself as a standard interface for enabling LLM-based agents to interact with external tools and services. As MCP servers are increasingly entrusted with security-sensitive operations, understanding their real-world risks has become critical. In practice, due to the absence of large-scale runtime MCP servers, such understanding largely relie… ▽ More The Model Context Protocol (MCP) has rapidly established itself as a standard interface for enabling LLM-based agents to interact with external tools and services. As MCP servers are increasingly entrusted with security-sensitive operations, understanding their real-world risks has become critical. In practice, due to the absence of large-scale runtime MCP servers, such understanding largely relies on security scanners applied to a small number of cases, yet the reliability of these assessments remains unclear. In this study, we revisit how MCP security is measured. We present MCPZoo, the largest collection of MCP servers for dynamic analysis to date. MCPZoo is constructed through a multi-agent framework for transforming in-the-wild static repositories into dynamic services. The framework emulates how human experts build, diagnose, and iteratively repair deployment and runtime defects by combining environment inference with feedback-driven refinement. To ensure practical interactivity at runtime, the servers are validated via real protocol interactions. As a result, MCPZoo contains 64,611 unique MCP servers (113,927 in total), with more than 37,288 supporting dynamic analysis. Leveraging MCPZoo, we conduct the first ecosystem-scale measurement of MCP servers and the scanners that analyze them. While existing scanners report that 96.89% of servers are risky, we find that these signals are unreliable. In particular, manual validation shows that less than 50% of sampled alerts are true positives, and scanner outputs exhibit clear inconsistency across scanners. Overall, MCPZoo enables large-scale, reproducible measurement of MCP server security and exposes limitations of current scanning practices. We further release a public query interface to support practical risk assessment of MCP servers. △ Less

Submitted 13 July, 2026; originally announced July 2026.

Comments: 18 pages, 11 figures, and 10 tables. This article substantially extends the preliminary 3-page MCPZoo dataset release arXiv:2512.15144. Includes appendices

Parametric Skills

Authors: Xuan Zhao, Haonan He, Qingyu Yang, Minglei Li, Jingqi Ye, Zelin Tan, Bo Wan, Peng Ye

Abstract: Since intelligence fundamentally relies on efficient skill acquisition (Chollet, 2019), the ability to leverage skills is critical. For LLMs, skills, manually authored or extracted from task trajectories, are textual recipes encoding mature problem-solving experience and are critical to agentic capabilities. Despite widespread deployment, their utility is limited by the model's ability to comprehe… ▽ More Since intelligence fundamentally relies on efficient skill acquisition (Chollet, 2019), the ability to leverage skills is critical. For LLMs, skills, manually authored or extracted from task trajectories, are textual recipes encoding mature problem-solving experience and are critical to agentic capabilities. Despite widespread deployment, their utility is limited by the model's ability to comprehend and follow skill instructions, especially under complex and long-context scenarios, where key instructions are difficult to locate and adhere to. To address this limitation, we propose ParametricSkills, a framework that can convert free-form textual skills into parameters at test time, enabling context-free skill exploitation. Specifically, we first construct a large-scale, high-quality skill library, and synthesize single-turn and multi-turn skill exploitation trajectories built around these skills with OpenCode. Using these data, we then train a hypernetwork that parameterizes both the skill content and the test-time exploitation methodology by receiving textual skills and converting them into LoRA adapters. Experimental results on six complex software engineering (SWE) subtasks demonstrate that, the proposed ParametricSkills averagely outperforms in-context learning by 6.44 points as judged by DeepSeek-V4-Flash, while also achieving significantly higher BERT Score and F1 score, confirming its effectiveness. Beyond performance, we further find that parametric skills, being inherently accumulative, offer a preliminary yet promising avenue toward test-time continual learning. △ Less

Submitted 29 June, 2026; originally announced June 2026.

Comments: Preprint, Under Review

SU(3)-flavor breaking as a structural probe of hidden-charm-strange $0^{--}$ tetraquarks in a color-octet basis

Authors: Bing-Dong Wan, Jun-Hao Zhang, Yan Zhang, Ming-Yang Yuan

Abstract: We study hidden-charm-strange tetraquark candidates with the exotic quantum number $J^{PC}=0^{--}$ to test whether SU(3)-flavor breaking acts as a universal mass shift or as a structural probe of a fixed color-octet current basis. Using $[\bar c c]_{8_c}\otimes[\bar s s]_{8_c}$-type and $[\bar c s]_{8_c}\otimes[\bar s c]_{8_c}$-type color-octet currents within QCD sum rules, we keep the strange-qu… ▽ More We study hidden-charm-strange tetraquark candidates with the exotic quantum number $J^{PC}=0^{--}$ to test whether SU(3)-flavor breaking acts as a universal mass shift or as a structural probe of a fixed color-octet current basis. Using $[\bar c c]_{8_c}\otimes[\bar s s]_{8_c}$-type and $[\bar c s]_{8_c}\otimes[\bar s c]_{8_c}$-type color-octet currents within QCD sum rules, we keep the strange-quark mass and strange condensates explicitly in the operator product expansion through dimension eight so that the strange-sector response can be traced at fixed color and Dirac structure. The hidden-charm-strange system is treated as the primary phenomenological target, while the hidden-bottom-strange sector serves as a stability benchmark. The strange-sector spectrum remains ordered, but the induced charm-sector shifts are grouped rather than uniform, with relatively small shifts for the $[\bar c c]_{8_c}\otimes[\bar s s]_{8_c}$ configurations and substantially larger shifts for the $[\bar c s]_{8_c}\otimes[\bar s c]_{8_c}$ ones. The $[\bar c s]_{8_c}\otimes[\bar s c]_{8_c}$ solutions are shifted toward the $D_s^*\bar D_{s1}$ threshold region, with one overlapping this region within uncertainties and another showing the largest positive SU(3)-breaking shift. Taken together, these features indicate that hidden strangeness can serve as a useful discriminator of internal current structure in the exotic $0^{--}$ sector. △ Less

Submitted 24 June, 2026; originally announced June 2026.

Comments: 21 pages, 9 figures, and 1 table

A Solver-Free Training Method for Predict-then-Optimize

Authors: Beichen Wan, Mo Liu

Abstract: We propose a scalable method for training prediction (machine learning) models in the predict-then-optimize paradigm, where model outputs serve as coefficients for a subsequent linear optimization task. Directly minimizing the empirical decision regret is intractable for linear programming and combinatorial optimization since the decision mapping is piecewise constant, and the gradients are zero a… ▽ More We propose a scalable method for training prediction (machine learning) models in the predict-then-optimize paradigm, where model outputs serve as coefficients for a subsequent linear optimization task. Directly minimizing the empirical decision regret is intractable for linear programming and combinatorial optimization since the decision mapping is piecewise constant, and the gradients are zero almost everywhere. While existing methods address this by smoothing the differentiation process, they suffer from scalability issues, since a computationally expensive solver call is required for every gradient evaluation. To address this, we propose a decision-focused learning pipeline based on a measure transformation principle, which yields a new surrogate loss that is completely optimization-solver-free during training. We establish theoretical guarantees, including Fisher consistency and excess risk bounds. Empirically, our method achieves decision quality competitive with state-of-the-art methods while reducing training time by orders of magnitude. △ Less

Submitted 17 June, 2026; originally announced June 2026.

Comments: Accepted by ICML 2026

Ensuring Trustworthy Online A/B Testing: Addressing Five Key Questions on CUPED

Authors: Yu Zhang, Bokui Wan, Yongli Qin, Jinyong Ma, Yifan Guo

Abstract: A/B testing has become the gold standard for data-driven decision-making in large-scale online experimentation, providing critical guidance for feature launch, pricing optimization, and user experience enhancement. To maximize statistical sensitivity, many technology companies routinely employ Controlled-experiment Using Pre-Experiment Data (CUPED), a technique that achieves substantial variance r… ▽ More A/B testing has become the gold standard for data-driven decision-making in large-scale online experimentation, providing critical guidance for feature launch, pricing optimization, and user experience enhancement. To maximize statistical sensitivity, many technology companies routinely employ Controlled-experiment Using Pre-Experiment Data (CUPED), a technique that achieves substantial variance reduction while preserving the unbiasedness of estimating the average treatment effect. Despite its widespread adoption, several critical methodological and practical nuances of CUPED remain underexplored. This paper systematically addresses five frequently encountered yet overlooked questions regarding the application of CUPED. First, we provide a comparative analysis of various post-CUPED estimators to identify the optimal adjustment specification. Second, we evaluate the validity of regression-based adjustments and delineate robust variance estimation methods tailored for such frameworks. Finally, we extend our investigation to complex but common scenarios, including multi-arm experiments and two-stage sampling designs. Our findings reveal that in these settings, naive reliance on standard variance estimators can lead to severely misleading inferences. By offering rigorous theoretical insights and extensive experimental validation, this work deepens the conceptual understanding of CUPED. Notably, the recommended methodologies have been successfully deployed and integrated into ByteDance's experimentation platform. △ Less

Submitted 17 June, 2026; originally announced June 2026.

Comments: 15 pages, 3 figures

SAW: Stage-Aware Dynamic Weighting for Multi-Objective Reinforcement Learning in Large Language Models

Authors: Yuchen He, Baolong Bi, Shenghua Liu, Huaming Liao, Yuyao Ge, Bolin Wan, Siqian Tong, Juan Chen, Jiafeng Guo, Xueqi Cheng

Abstract: Although multi-objective reinforcement learning (MORL) is central to aligning large language models with complex human preferences, the prevailing practice of static weighted summation overlooks a more fundamental phenomenon: reward learning is markedly asynchronous across objectives. Well-learned dimensions quickly produce homogeneous, low-variance signals whose residual noise contaminates the ag… ▽ More Although multi-objective reinforcement learning (MORL) is central to aligning large language models with complex human preferences, the prevailing practice of static weighted summation overlooks a more fundamental phenomenon: reward learning is markedly asynchronous across objectives. Well-learned dimensions quickly produce homogeneous, low-variance signals whose residual noise contaminates the aggregated reward (in GRPO) or occupies a fixed share of the advantage budget (in GDPO), interfering with the scarce yet high-value signals carried by under-learned dimensions. To address this asynchrony, we propose Stage-Aware Dynamic Weighting (SAW), a lightweight, algorithm-agnostic dynamic weighting mechanism. SAW utilizes the coefficient of variation (CV) as a scale-invariant proxy for real-time informativeness, reweighting each dimension's reward or advantage contribution by its relative informativeness within the batch. Unlike gradient-based methods that require multiple forward and backward passes, SAW relies solely on batch-level statistics, introducing nearly negligible computational overhead. Experiments on tool-calling and text summarization tasks demonstrate that SAW consistently improves both training efficiency and final performance under both GRPO and GDPO frameworks, confirming it as a general-purpose plug-in for multi-reward LLM alignment. Our code is available at https://github.com/Zhaolutuan/SAW △ Less

Submitted 5 June, 2026; originally announced June 2026.

Comments: 17 pages, 7 figures, 5 tables

Spectroscopy of hidden-heavy tetraquark states with $J^{PC}=0^{--}$ in a color-octet configuration

Authors: Bing-Dong Wan, Jun-Hao Zhang, Yan Zhang, Ming-Yang Yuan

Abstract: Within the framework of QCD sum rules, we investigate hidden-heavy tetraquark states with the exotic quantum number $J^{PC}=0^{--}$ in color-octet configurations, namely $[Q\bar q]_{8_c}\otimes[q\bar Q]_{8_c}$ and $[Q\bar Q]_{8_c}\otimes[\bar q q]_{8_c}$ with $Q=c,b$. Since the $0^{--}$ quantum number cannot be realized by conventional $q\bar q$ mesons, the observation of such a state would provid… ▽ More Within the framework of QCD sum rules, we investigate hidden-heavy tetraquark states with the exotic quantum number $J^{PC}=0^{--}$ in color-octet configurations, namely $[Q\bar q]_{8_c}\otimes[q\bar Q]_{8_c}$ and $[Q\bar Q]_{8_c}\otimes[\bar q q]_{8_c}$ with $Q=c,b$. Since the $0^{--}$ quantum number cannot be realized by conventional $q\bar q$ mesons, the observation of such a state would provide a particularly clean signal for exotic hadronic structures. We construct four color-octet interpolating currents for the hidden-heavy systems and carry out the operator product expansion up to dimension-eight condensates. Our numerical analysis indicates that the hidden-bottom sector exhibits the clearest sum-rule stability, with flatter Borel platforms than the corresponding hidden-charm sector. We obtain four $0^{--}$ hidden-bottom tetraquark candidates in the mass range $10.8$--$11.1~\mathrm{GeV}$, while their hidden-charm partners are predicted around $4.3$--$4.6~\mathrm{GeV}$. The extracted masses suggest a compact spectral pattern with a mild dependence on the underlying color-octet clustering structure. We also discuss possible decay patterns and emphasize that the absence of the lowest pseudoscalar--pseudoscalar heavy-meson channels is a distinctive consequence of the exotic $0^{--}$ assignment. These results provide useful theoretical guidance for future searches for hidden-heavy exotic states at Belle II and LHCb, with complementary probes of the hidden-charm partners at BESIII. △ Less

Submitted 20 May, 2026; originally announced May 2026.

FastOCR: Dynamic Visual Fixation via KV Cache Pruning for Efficient Document Parsing

Authors: Zihan Tang, Leqi Shen, Hui Chen, Ao Wang, Ben Wan, Yan Feng, Ke Zhang, Sicheng Zhao, Tongxuan Liu, Guiguang Ding

Abstract: Vision-Language Models (VLMs) have shown strong promise on Optical Character Recognition (OCR), yet the sheer number of visual tokens required to encode dense documents incurs prohibitive inference cost. Existing pruning methods rely on physical eviction, e.g., permanently discarding visual tokens during the prefill stage. While effective for natural images, this strategy fundamentally breaks down… ▽ More Vision-Language Models (VLMs) have shown strong promise on Optical Character Recognition (OCR), yet the sheer number of visual tokens required to encode dense documents incurs prohibitive inference cost. Existing pruning methods rely on physical eviction, e.g., permanently discarding visual tokens during the prefill stage. While effective for natural images, this strategy fundamentally breaks down on OCR, where virtually every visual token may correspond to a character or structural element, and any irreversible loss leads to catastrophic accuracy degradation. We observe that, although document images appear globally dense and seemingly unprunable, the model's attention to them is in fact temporally sparse: at each decoding step it concentrates on a small region that shifts gradually across steps, much as a human reader fixates on successive words rather than perceiving an entire page at once. Motivated by this Dynamic Visual Fixation phenomenon, we recast the intractable global pruning problem as a tractable local, dynamic one and propose FastOCR, a training-free framework with two complementary modules. Specifically, Focal-Guided Pruning identifies a small set of focal layers and selects the most task-relevant visual tokens from them at each step, while Cross-Step Fixation Reuse exploits the gradual shift of fixation to warm-start each step from the previous one. By dynamically adjusting which tokens are attended rather than evicting any from the cache, FastOCR avoids permanent information loss. Extensive experiments show that FastOCR serves as a plug-and-play acceleration module, generalizing consistently across five VLMs of varying sizes and architectures. On Qwen2.5-VL, FastOCR retains 98% of the unpruned model's accuracy while attending to only 5% of the visual tokens per decoding step, reducing attention latency by 3.0$\times$. △ Less

Submitted 17 May, 2026; originally announced May 2026.

Nodal mechanism for the suppressed $D\bar D$ decay of $ψ(4040)$ in the Bethe--Salpeter framework

Authors: Bing-Dong Wan, Sheng-Qi Zhang

Abstract: The strong decay $ψ(4040)\to D\bar D$ is anomalously suppressed despite ample phase space, whereas the $D\bar D^*$ and $D_s\bar D_s$ channels remain sizable. In this work, we study this suppression and the associated open-charm hierarchy in the framework of the instantaneous Bethe--Salpeter equation combined with the relativistic $^3P_0$ model, with the pair-creation strength fixed independently f… ▽ More The strong decay $ψ(4040)\to D\bar D$ is anomalously suppressed despite ample phase space, whereas the $D\bar D^*$ and $D_s\bar D_s$ channels remain sizable. In this work, we study this suppression and the associated open-charm hierarchy in the framework of the instantaneous Bethe--Salpeter equation combined with the relativistic $^3P_0$ model, with the pair-creation strength fixed independently from $ψ(3770)\to D\bar D$. Within this framework, we show that the suppressed $D\bar D$ mode can be understood as a consequence of node-induced cancellations in the relativistic decay amplitude. The $D\bar D$ amplitude is strongly reduced because the corresponding overlap integral receives comparable positive and negative contributions from different momentum regions, whereas the $D\bar D^*$ and $D_s\bar D_s$ channels do not undergo the same strong cancellation. This interpretation is further supported by the pronounced sensitivity of the $D\bar D$ width to the initial mass, the charged-neutral $D$-meson mass splitting, and the dip structure in the mass dependence of the partial width. Our results provide a dynamical explanation of the suppressed $D\bar D$ mode and the core open-charm hierarchy of $ψ(4040)$ within a conventional $3\,{}^3S_1$ charmonium picture, while the precise value of the near-vanishing $D\bar D$ width remains model dependent. △ Less

Submitted 11 May, 2026; originally announced May 2026.

Comments: 28 pages, 3figures, and 6 tables

GameGen-Verifier: Parallel Keypoint-Based Verification for LLM-Generated Games via Runtime State Injection

Authors: Chaobo Jia, Ruipeng Wan, Ting Sun, Weihao Tan, Borui Wan, Yuxuan Tong, Guangming Sheng, Hong Xu

Abstract: LLM-based game generation promises to turn natural-language specifications into executable games, but progress is limited by the lack of reliable automated verification. Unlike conventional code generation, game correctness is defined over long-horizon interaction: a game may appear correct while violating core mechanics such as state updates, interaction rules, and phase transitions. Existing Age… ▽ More LLM-based game generation promises to turn natural-language specifications into executable games, but progress is limited by the lack of reliable automated verification. Unlike conventional code generation, game correctness is defined over long-horizon interaction: a game may appear correct while violating core mechanics such as state updates, interaction rules, and phase transitions. Existing Agent-as-a-Verifier approaches collapse verification into open-ended gameplay, making verdicts reachability-bound, time-consuming, coverage-limited, and sensitive to the agent's gameplay ability. We present GameGen-Verifier, an automated verification paradigm for LLM-generated games that decomposes a specification into verifiable keypoints and grounds them into independent verification units. Each unit patches the game runtime into a concrete target state, executes a bounded interaction, and judges the outcome against the keypoint assertion. We implement GGV-Harness, a scalable agentic harness providing concurrency management, runtime isolation, and fault recovery. On VeriGame, our dataset of 100 games across seven genres, GameGen-Verifier achieves up to 92.2% accuracy against human judgments versus 58.8% for the coverage-enforced Agent-as-a-Verifier baseline, while reducing wall-clock time by up to 16.6x. △ Less

Submitted 8 May, 2026; originally announced May 2026.

RTPrune: Reading-Twice Inspired Token Pruning for Efficient DeepSeek-OCR Inference

Authors: Ben Wan, Yan Feng, Zihan Tang, Weizhe Huang, Yuting Zeng, Jia Wang, Tongxuan Liu

Abstract: DeepSeek-OCR leverages visual-text compression to reduce long-text processing costs and accelerate inference, yet visual tokens remain prone to redundant textual and structural information. Moreover, current token pruning methods for conventional vision-language models (VLMs) fail to preserve textual fidelity due to improper compression mechanisms. By analyzing the decoding process of DeepSeek-OCR… ▽ More DeepSeek-OCR leverages visual-text compression to reduce long-text processing costs and accelerate inference, yet visual tokens remain prone to redundant textual and structural information. Moreover, current token pruning methods for conventional vision-language models (VLMs) fail to preserve textual fidelity due to improper compression mechanisms. By analyzing the decoding process of DeepSeek-OCR, we find that a distinct two-stage reading trajectory: the model initially prioritizes the majority of high-norm tokens, then subsequently redistributes its attention to the remaining ones. Motivated by this insight, we propose RTPrune, a two-stage token pruning method tailored for DeepSeek-OCR. In the first stage, we prioritize high-norm visual tokens that capture salient textual and structural information. In the second stage, the remaining tokens are paired and merged based on optimal transport theory to achieve efficient feature aggregation. We further introduce a dynamic pruning ratio that adapts to token similarity and textual density for OCR tasks, enabling a better efficiency-accuracy trade-off. Extensive experiments demonstrate state-of-the-art performance, as evidenced by 99.47% accuracy and 1.23$\times$ faster prefill on OmniDocBench, achieved with 84.25% token retention when applied to DeepSeek-OCR-Large. △ Less

Submitted 21 May, 2026; v1 submitted 1 May, 2026; originally announced May 2026.

Comments: 21 pages, accepted by ICML2026

QCD sum rule analysis of local meson-meson currents for the $K(1690)$ state

Authors: Yi-Qi Mu, Peng-Wen Xu, Si-Tong Chen, Yi-Tong Wei, Ge-Jia Zhang, Bing-Dong Wan

Abstract: The nature of the recently observed $K(1690)$ state, reported by the COMPASS Collaboration as a candidate for a strange crypto-exotic meson with $J^P=0^-$, remains unclear. In this work, we investigate whether it can be described by local meson-meson currents within the framework of QCD sum rules. We construct a set of local meson-meson-type interpolating currents with $J^P=0^-$, covering the repr… ▽ More The nature of the recently observed $K(1690)$ state, reported by the COMPASS Collaboration as a candidate for a strange crypto-exotic meson with $J^P=0^-$, remains unclear. In this work, we investigate whether it can be described by local meson-meson currents within the framework of QCD sum rules. We construct a set of local meson-meson-type interpolating currents with $J^P=0^-$, covering the representative Dirac structures $0^- \otimes 0^+$, $0^+ \otimes 0^-$, $1^- \otimes 1^+$, $1^+ \otimes 1^-$, as well as tensor configurations. For all these currents, we perform a systematic operator product expansion up to dimension-eight condensates and carry out a detailed analysis of Borel stability, continuum threshold dependence, and pole contributions. We find that the extracted masses are consistently located around $2~\mathrm{GeV}$ or higher, significantly above the experimental mass of the $K(1690)$. This behavior is highly stable against variations of QCD parameters and the choice of interpolating currents, and is observed universally across all the considered configurations. The absence of any low-lying pole compatible with the COMPASS signal therefore disfavors interpreting the $K(1690)$ as a state predominantly coupled to these local meson-meson currents within the QCD sum rule framework. Our results thus make a compact multiquark configuration a more plausible explanation for this state. △ Less

Submitted 22 April, 2026; originally announced April 2026.

Comments: 17 pages, 4 figures, 1table

MOON3.0: Reasoning-aware Multimodal Representation Learning for E-commerce Product Understanding

Authors: Junxian Wu, Chenghan Fu, Zhanheng Nie, Daoze Zhang, Bowen Wan, Wanxian Guan, Chuan Yu, Jian Xu, Bo Zheng

Abstract: With the rapid growth of e-commerce, exploring general representations rather than task-specific ones has attracted increasing attention. Although recent multimodal large language models (MLLMs) have driven significant progress in product understanding, they are typically employed as feature extractors that implicitly encode product information into global embeddings, thereby limiting their abilit… ▽ More With the rapid growth of e-commerce, exploring general representations rather than task-specific ones has attracted increasing attention. Although recent multimodal large language models (MLLMs) have driven significant progress in product understanding, they are typically employed as feature extractors that implicitly encode product information into global embeddings, thereby limiting their ability to capture fine-grained attributes. Therefore, we argue that leveraging the reasoning capabilities of MLLMs to explicitly model fine-grained product attributes holds significant potential. Nevertheless, achieving this goal remains non-trivial due to several key challenges: (i) long-context reasoning tends to dilute the model's attention to salient information in the raw input; (ii) supervised fine-tuning (SFT) primarily encourages rigid imitation, limiting the exploration of effective reasoning strategies; and (iii) fine-grained details are progressively attenuated during forward propagation. To address these issues, we propose MOON3.0, the first reasoning-aware MLLM-based model for product representation learning. Our method (1) employs a multi-head modality fusion module to adaptively integrate raw signals; (2) incorporates a joint contrastive and reinforcement learning framework to autonomously explore more effective reasoning strategies; and (3) introduces a fine-grained residual enhancement module to progressively preserve local details throughout the network. Additionally, we release a large-scale multimodal e-commerce benchmark MBE3.0. Experimentally, our model demonstrates state-of-the-art zero-shot performance across various downstream tasks on both our benchmark and public datasets. △ Less

Submitted 5 August, 2026; v1 submitted 1 April, 2026; originally announced April 2026.

Comments: Accepted by the 34th ACM International Conference on Multimedia (ACM MM), 2026. 10 pages, 6 figures

RSONet: Region-guided Selective Optimization Network for RGB-T Salient Object Detection

Authors: Bin Wan, Runmin Cong, Xiaofei Zhou, Hao Fang, Chengtao Lv, Sam Kwong

Abstract: This paper focuses on the inconsistency in salient regions between RGB and thermal images. To address this issue, we propose the Region-guided Selective Optimization Network for RGB-T Salient Object Detection, which consists of the region guidance stage and saliency generation stage. In the region guidance stage, three parallel branches with same encoder-decoder structure equipped with the context… ▽ More This paper focuses on the inconsistency in salient regions between RGB and thermal images. To address this issue, we propose the Region-guided Selective Optimization Network for RGB-T Salient Object Detection, which consists of the region guidance stage and saliency generation stage. In the region guidance stage, three parallel branches with same encoder-decoder structure equipped with the context interaction (CI) module and spatial-aware fusion (SF) module are designed to generate the guidance maps which are leveraged to calculate similarity scores. Then, in the saliency generation stage, the selective optimization (SO) module fuses RGB and thermal features based on the previously obtained similarity values to mitigate the impact of inconsistent distribution of salient targets between the two modalities. After that, to generate high-quality detection result, the dense detail enhancement (DDE) module which adopts the multiple dense connections and visual state space blocks is applied to low-level features for optimizing the detail information. In addition, the mutual interaction semantic (MIS) module is placed in the high-level features to dig the location cues by the mutual fusion strategy. We conduct extensive experiments on the RGB-T dataset, and the results demonstrate that the proposed RSONet achieves competitive performance against 27 state-of-the-art SOD methods. △ Less

Submitted 13 March, 2026; originally announced March 2026.

G2HFNet: GeoGran-Aware Hierarchical Feature Fusion Network for Salient Object Detection in Optical Remote Sensing Images

Authors: Bin Wan, Runmin Cong, Xiaofei Zhou, Hao Fang, Chengtao Lv, Sam Kwong

Abstract: Remote sensing images captured from aerial perspectives often exhibit significant scale variations and complex backgrounds, posing challenges for salient object detection (SOD). Existing methods typically extract multi-level features at a single scale using uniform attention mechanisms, leading to suboptimal representations and incomplete detection results. To address these issues, we propose a Ge… ▽ More Remote sensing images captured from aerial perspectives often exhibit significant scale variations and complex backgrounds, posing challenges for salient object detection (SOD). Existing methods typically extract multi-level features at a single scale using uniform attention mechanisms, leading to suboptimal representations and incomplete detection results. To address these issues, we propose a GeoGran-Aware Hierarchical Feature Fusion Network (G2HFNet) that fully exploits geometric and granular cues in optical remote sensing images. Specifically, G2HFNet adopts Swin Transformer as the backbone to extract multi-level features and integrates three key modules: the multi-scale detail enhancement (MDE) module to handle object scale variations and enrich fine details, the dual-branch geo-gran complementary (DGC) module to jointly capture fine-grained details and positional information in mid-level features, and the deep semantic perception (DSP) module to refine high-level positional cues via self-attention. Additionally, a local-global guidance fusion (LGF) module is introduced to replace traditional convolutions for effective multi-level feature integration. Extensive experiments demonstrate that G2HFNet achieves high-quality saliency maps and significantly improves detection performance in challenging remote sensing scenarios. △ Less

Submitted 19 March, 2026; v1 submitted 13 March, 2026; originally announced March 2026.

RDNet: Region Proportion-Aware Dynamic Adaptive Salient Object Detection Network in Optical Remote Sensing Images

Authors: Bin Wan, Runmin Cong, Xiaofei Zhou, Hao Fang, Yaoqi Sun, Sam Kwong

Abstract: Salient object detection (SOD) in remote sensing images faces significant challenges due to large variations in object sizes, the computational cost of self-attention mechanisms, and the limitations of CNN-based extractors in capturing global context and long-range dependencies. Existing methods that rely on fixed convolution kernels often struggle to adapt to diverse object scales, leading to det… ▽ More Salient object detection (SOD) in remote sensing images faces significant challenges due to large variations in object sizes, the computational cost of self-attention mechanisms, and the limitations of CNN-based extractors in capturing global context and long-range dependencies. Existing methods that rely on fixed convolution kernels often struggle to adapt to diverse object scales, leading to detail loss or irrelevant feature aggregation. To address these issues, this work aims to enhance robustness to scale variations and achieve precise object localization. We propose the Region Proportion-Aware Dynamic Adaptive Salient Object Detection Network (RDNet), which replaces the CNN backbone with the SwinTransformer for global context modeling and introduces three key modules: (1) the Dynamic Adaptive Detail-aware (DAD) module, which applies varied convolution kernels guided by object region proportions; (2) the Frequency-matching Context Enhancement (FCE) module, which enriches contextual information through wavelet interactions and attention; and (3) the Region Proportion-aware Localization (RPL) module, which employs cross-attention to highlight semantic details and integrates a Proportion Guidance (PG) block to assist the DAD module. By combining these modules, RDNet achieves robustness against scale variations and accurate localization, delivering superior detection performance compared with state-of-the-art methods. △ Less

Submitted 12 March, 2026; originally announced March 2026.

Learning Positive-Incentive Point Sampling in Neural Implicit Fields for Object Pose Estimation

Authors: Yifei Shi, Boyan Wan, Xin Xu, Kai Xu

Abstract: Learning neural implicit fields of 3D shapes is a rapidly emerging field that enables shape representation at arbitrary resolutions. Due to the flexibility, neural implicit fields have succeeded in many research areas, including shape reconstruction, novel view image synthesis, and more recently, object pose estimation. Neural implicit fields enable learning dense correspondences between the camer… ▽ More Learning neural implicit fields of 3D shapes is a rapidly emerging field that enables shape representation at arbitrary resolutions. Due to the flexibility, neural implicit fields have succeeded in many research areas, including shape reconstruction, novel view image synthesis, and more recently, object pose estimation. Neural implicit fields enable learning dense correspondences between the camera space and the object's canonical space-including unobserved regions in camera space-significantly boosting object pose estimation performance in challenging scenarios like highly occluded objects and novel shapes. Despite progress, predicting canonical coordinates for unobserved camera-space regions remains challenging due to the lack of direct observational signals. This necessitates heavy reliance on the model's generalization ability, resulting in high uncertainty. Consequently, densely sampling points across the entire camera space may yield inaccurate estimations that hinder the learning process and compromise performance. To alleviate this problem, we propose a method combining an SO(3)-equivariant convolutional implicit network and a positive-incentive point sampling (PIPS) strategy. The SO(3)-equivariant convolutional implicit network estimates point-level attributes with SO(3)-equivariance at arbitrary query locations, demonstrating superior performance compared to most existing baselines. The PIPS strategy dynamically determines sampling locations based on the input, thereby boosting the network's accuracy and training efficiency. Our method outperforms the state-of-the-art on three pose estimation datasets. Notably, it demonstrates significant improvements in challenging scenarios, such as objects captured with unseen pose, high occlusion, novel geometry, and severe noise. △ Less

Submitted 23 February, 2026; originally announced February 2026.

The S-wave topped meson

Authors: Jun-Hao Zhang, Shuo Yang, Bing-Dong Wan

Abstract: Motivated by the recent near-threshold enhancement in top-quark pair production reported by CMS and ATLAS, we study the S-wave spectral structure of heavy-light systems containing a single top quark, namely $t\bar{q}$, $t\bar{c}$, and $t\bar{b}$, within the instantaneous Bethe-Salpeter formalism. Because the top quark decays on a timescale much shorter than the typical hadronization time, the disc… ▽ More Motivated by the recent near-threshold enhancement in top-quark pair production reported by CMS and ATLAS, we study the S-wave spectral structure of heavy-light systems containing a single top quark, namely $t\bar{q}$, $t\bar{c}$, and $t\bar{b}$, within the instantaneous Bethe-Salpeter formalism. Because the top quark decays on a timescale much shorter than the typical hadronization time, the discrete eigenvalues we obtain should be interpreted as model-dependent reference positions of possible quasi-bound heavy-light configurations, rather than as predictions for fully formed conventional hadrons. The numerical results indicate that the masses of these configurations lie close to the top-quark mass. For the $t\bar{b}$ system, the masses of the first four S-wave $0^{-}$ radial states are about $5.1$, $5.4$, $5.6$, and $5.7$~GeV above the top-quark mass, respectively. For the $t\bar{c}$ system, the corresponding values are about $1.9$, $2.2$, $2.5$, and $2.6$~GeV. We also briefly discuss possible production and decay patterns at a qualitative level, which may serve as a reference for future dedicated phenomenological studies or for experimental constraints. △ Less

Submitted 8 June, 2026; v1 submitted 10 February, 2026; originally announced February 2026.

Comments: 18 pages, 5 figures, and 1 table. Accepted by CPC

Decision-Focused Sequential Experimental Design: A Directional Uncertainty-Guided Approach

Authors: Beichen Wan, Mo Liu, Paul Grigas, Zuo-Jun Max Shen

Abstract: We consider the sequential experimental design problem in the predict-then-optimize paradigm. In this paradigm, the outputs of the prediction model are used as coefficient vectors in a downstream linear optimization problem. Traditional sequential experimental design aims to control the input variables (features) so that the improvement in prediction accuracy from each experimental outcome (label)… ▽ More We consider the sequential experimental design problem in the predict-then-optimize paradigm. In this paradigm, the outputs of the prediction model are used as coefficient vectors in a downstream linear optimization problem. Traditional sequential experimental design aims to control the input variables (features) so that the improvement in prediction accuracy from each experimental outcome (label) is maximized. However, in the predict-then-optimize setting, performance is ultimately evaluated based on the decision loss induced by the downstream optimization, rather than by prediction error. This mismatch between prediction accuracy and decision loss renders traditional decision-blind designs inefficient. To address this issue, we propose a directional-based metric to quantify predictive uncertainty. This metric does not require solving an optimization oracle and is therefore computationally tractable. We show that the resulting sequential design criterion enjoys strong consistency and convergence guarantees. Under a broad class of distributions, we demonstrate that our directional uncertainty-based design attains an earlier stopping time than decision-blind designs. This advantage is further supported by real-world experiments on an LLM job allocation problem. △ Less

Submitted 5 February, 2026; originally announced February 2026.

RigMo: Unifying Rig and Motion Learning for Generative Animation

Authors: Hao Zhang, Jiahao Luo, Bohui Wan, Yizhou Zhao, Zongrui Li, Michael Vasilkovsky, Chaoyang Wang, Jian Wang, Narendra Ahuja, Bing Zhou

Abstract: Despite significant progress in 4D generation, rig and motion, the core structural and dynamic components of animation are typically modeled as separate problems. Existing pipelines rely on ground-truth skeletons and skinning weights for motion generation and treat auto-rigging as an independent process, undermining scalability and interpretability. We present RigMo, a unified generative framework… ▽ More Despite significant progress in 4D generation, rig and motion, the core structural and dynamic components of animation are typically modeled as separate problems. Existing pipelines rely on ground-truth skeletons and skinning weights for motion generation and treat auto-rigging as an independent process, undermining scalability and interpretability. We present RigMo, a unified generative framework that jointly learns rig and motion directly from raw mesh sequences, without any human-provided rig annotations. RigMo encodes per-vertex deformations into two compact latent spaces: a rig latent that decodes into explicit Gaussian bones and skinning weights, and a motion latent that produces time-varying SE(3) transformations. Together, these outputs define an animatable mesh with explicit structure and coherent motion, enabling feed-forward rig and motion inference for deformable objects. Beyond unified rig-motion discovery, we introduce a Motion-DiT model operating in RigMo's latent space and demonstrate that these structure-aware latents can naturally support downstream motion generation tasks. Experiments on DeformingThings4D, Objaverse-XL, and TrueBones demonstrate that RigMo learns smooth, interpretable, and physically plausible rigs, while achieving superior reconstruction and category-level generalization compared to existing auto-rigging and deformation baselines. RigMo establishes a new paradigm for unified, structure-aware, and scalable dynamic 3D modeling. △ Less

Submitted 9 January, 2026; originally announced January 2026.

Comments: Project Page: https://RigMo-Page.github.io

MCPZoo: A Large-Scale Dataset of Runnable Model Context Protocol Servers for AI Agent

Authors: Mengying Wu, Pei Chen, Geng Hong, Baichao An, Jinsong Chen, Binwang Wan, Xudong Pan, Jiarun Dai, Min Yang

Abstract: Model Context Protocol (MCP) enables agents to interact with external tools, yet empirical research on MCP is hindered by the lack of large-scale, accessible datasets. We present MCPZoo, the largest and most comprehensive dataset of MCP servers collected from multiple public sources, comprising 129,059 servers (56,053 distinct). MCPZoo includes 16,356 server instances that have been deployed and v… ▽ More Model Context Protocol (MCP) enables agents to interact with external tools, yet empirical research on MCP is hindered by the lack of large-scale, accessible datasets. We present MCPZoo, the largest and most comprehensive dataset of MCP servers collected from multiple public sources, comprising 129,059 servers (56,053 distinct). MCPZoo includes 16,356 server instances that have been deployed and verified as runnable and interactable, supporting realistic experimentation beyond static analysis. The dataset provides unified metadata and access interfaces, enabling systematic exploration and interaction without manual deployment effort. MCPZoo is released as an open and accessible resource to support research on MCP-based systems and security analysis. △ Less

Submitted 26 December, 2025; v1 submitted 17 December, 2025; originally announced December 2025.

Spectrum of $J^{PC} = 0^{\pm\pm}$ Gluonic Hidden-Charm Tetraquark States

Authors: Bing-Dong Wan, Ming-Yang Yuan, Jun-Hao Zhang, Yan Zhang

Abstract: We investigate gluonic hidden-charm tetraquark states composed of two valence quarks, two valence antiquarks and an explicit valence gluon. In the color configuration $[\bar{3}_c]_{c q}\otimes[8_c]_{G}\otimes[3_c]_{\bar{c}\bar{q}}$, a complete set of eight interpolating currents is constructed for states with quantum numbers $^{PC}=0^{++}$, $0^{-+},$ $0^{--}$, and $0^{+-}$. The corresponding mass… ▽ More We investigate gluonic hidden-charm tetraquark states composed of two valence quarks, two valence antiquarks and an explicit valence gluon. In the color configuration $[\bar{3}_c]_{c q}\otimes[8_c]_{G}\otimes[3_c]_{\bar{c}\bar{q}}$, a complete set of eight interpolating currents is constructed for states with quantum numbers $^{PC}=0^{++}$, $0^{-+},$ $0^{--}$, and $0^{+-}$. The corresponding mass spectra are systematically analysed within the QCD sum rule framework, including nonperturbative condensate contributions up to dimension eight. Our numerical analysis indicates the possible existence of six gluonic hidden-charm tetraquark states exhibiting stable behaviour in the adopted Borel windows. By replacing the charm quark with the bottom quark, masses for the corresponding hidden-bottom partners are also estimated. Possible production mechanisms and dominant decay channels are discussed, providing phenomenological guidance for experimental searches. These predicted states may be accessible at current and forthcoming facilities, including Belle II, PANDA, SuperB and LHCb, and thus offer an opportunity to probe explicit gluonic degrees of freedom in multiquark systems and deepen our understanding of nonperturbative QCD. △ Less

Submitted 30 April, 2026; v1 submitted 13 December, 2025; originally announced December 2025.

Comments: 29 pages, 13 figures, 3 tables. Accepted by EPJC

Hidden-charm and -bottom tetraquark states with $J^{PC}=1^{-+}$ via QCD sum rules

Authors: Bing-Dong Wan, Yan Zhang, Jun-Hao Zhang, Ming-Yang Yuan

Abstract: We investigate the $1^{-+}$ hidden-charm and hidden-bottom tetraquark states within the framework of QCD sum rules. The mass spectra are computed by including condensates up to dimension eight in the operator product expansion. Our results indicate the possible existence of four $1^{-+}$ hidden-charm tetraquark states, with predicted masses of $(4.83 \pm 0.15)$ GeV, $(4.88 \pm 0.18)$ GeV,… ▽ More We investigate the $1^{-+}$ hidden-charm and hidden-bottom tetraquark states within the framework of QCD sum rules. The mass spectra are computed by including condensates up to dimension eight in the operator product expansion. Our results indicate the possible existence of four $1^{-+}$ hidden-charm tetraquark states, with predicted masses of $(4.83 \pm 0.15)$ GeV, $(4.88 \pm 0.18)$ GeV, $(4.72 \pm 0.16)$ GeV, and $(4.79 \pm 0.12)$ GeV, while their hidden-bottom counterparts are estimated to have masses of $(11.08 \pm 0.16)$ GeV, $(11.16 \pm 0.14)$ GeV, $(10.99 \pm 0.16)$ GeV, and $(11.03 \pm 0.15)$ GeV, respectively. We also analyze the possible decay modes of these tetraquark states, which may be accessible in future experiments at BESIII, Belle~II, LHCb, and future STCF. These findings provide valuable guidance for the experimental search for exotic $1^{-+}$ tetraquark states in both the charm and bottom sectors. △ Less

Submitted 30 January, 2026; v1 submitted 3 December, 2025; originally announced December 2025.

Divide-and-Conquer Decoupled Network for Cross-Domain Few-Shot Segmentation

Authors: Runmin Cong, Anpeng Wang, Bin Wan, Cong Zhang, Xiaofei Zhou, Wei Zhang

Abstract: Cross-domain few-shot segmentation (CD-FSS) aims to tackle the dual challenge of recognizing novel classes and adapting to unseen domains with limited annotations. However, encoder features often entangle domain-relevant and category-relevant information, limiting both generalization and rapid adaptation to new domains. To address this issue, we propose a Divide-and-Conquer Decoupled Network (DCDN… ▽ More Cross-domain few-shot segmentation (CD-FSS) aims to tackle the dual challenge of recognizing novel classes and adapting to unseen domains with limited annotations. However, encoder features often entangle domain-relevant and category-relevant information, limiting both generalization and rapid adaptation to new domains. To address this issue, we propose a Divide-and-Conquer Decoupled Network (DCDNet). In the training stage, to tackle feature entanglement that impedes cross-domain generalization and rapid adaptation, we propose the Adversarial-Contrastive Feature Decomposition (ACFD) module. It decouples backbone features into category-relevant private and domain-relevant shared representations via contrastive learning and adversarial learning. Then, to mitigate the potential degradation caused by the disentanglement, the Matrix-Guided Dynamic Fusion (MGDF) module adaptively integrates base, shared, and private features under spatial guidance, maintaining structural coherence. In addition, in the fine-tuning stage, to enhanced model generalization, the Cross-Adaptive Modulation (CAM) module is placed before the MGDF, where shared features guide private features via modulation ensuring effective integration of domain-relevant information. Extensive experiments on four challenging datasets show that DCDNet outperforms existing CD-FSS methods, setting a new state-of-the-art for cross-domain generalization and few-shot adaptation. △ Less

Submitted 10 November, 2025; originally announced November 2025.

Journal ref: AAAI 2026

Maestro: Orchestrating Robotics Modules with Vision-Language Models for Zero-Shot Generalist Robots

Authors: Junyao Shi, Rujia Yang, Kaitian Chao, Selina Bingqing Wan, Yifei Shao, Jiahui Lei, Jianing Qian, Long Le, Pratik Chaudhari, Kostas Daniilidis, Chuan Wen, Dinesh Jayaraman

Abstract: Today's best-explored routes towards generalist robots center on collecting ever larger "observations-in actions-out" robotics datasets to train large end-to-end models, copying a recipe that has worked for vision-language models (VLMs). We pursue a road less traveled: building generalist policies directly around VLMs by augmenting their general capabilities with specific robot capabilities encaps… ▽ More Today's best-explored routes towards generalist robots center on collecting ever larger "observations-in actions-out" robotics datasets to train large end-to-end models, copying a recipe that has worked for vision-language models (VLMs). We pursue a road less traveled: building generalist policies directly around VLMs by augmenting their general capabilities with specific robot capabilities encapsulated in a carefully curated set of perception, planning, and control modules. In Maestro, a VLM coding agent dynamically composes these modules into a programmatic policy for the current task and scenario. Maestro's architecture benefits from a streamlined closed-loop interface without many manually imposed structural constraints, and a comprehensive and diverse tool repertoire. As a result, it largely surpasses today's VLA models for zero-shot performance on challenging manipulation skills. Further, Maestro is easily extensible to incorporate new modules, easily editable to suit new embodiments such as a quadruped-mounted arm, and even easily adapts from minimal real-world experiences through local code edits. △ Less

Submitted 18 November, 2025; v1 submitted 2 November, 2025; originally announced November 2025.

Comments: Plan to resubmit after significant revisions

Ultrafast Relaxation Dynamics of Inner-Shell Vacancies in Hydrated Pyrrole

Authors: Kedong Wang, Bohui Wan, Cody L. Covington, Kalman Varga

Abstract: We employ real-space, real-time time-dependent density functional theory (TDDFT) combined with Ehrenfest dynamics to investigate ultrafast intermolecular relaxation following inner-valence ionization in hydrated pyrrole. This time-dependent approach treats electronic and nuclear motions simultaneously, allowing the description of electronic excitation, charge transfer, ionization, and nuclear moti… ▽ More We employ real-space, real-time time-dependent density functional theory (TDDFT) combined with Ehrenfest dynamics to investigate ultrafast intermolecular relaxation following inner-valence ionization in hydrated pyrrole. This time-dependent approach treats electronic and nuclear motions simultaneously, allowing the description of electronic excitation, charge transfer, ionization, and nuclear motion.When the initial vacancy in the O 2s 1 state is created on the water molecule, the system predominantly undergoes intermolecular Coulombic decay (ICD) and electron-transfer mediated decay (ETMD), accompanied by pronounced charge transfer between pyrrole and water. In contrast, ionization of the pyrrole site for N 2s electron leads to both ICD and Auger decay channels. These results demonstrate that the decay dynamics are strongly governed by the initial vacancy location, offering microscopic insight into intermolecular energy-transfer mechanisms in hydrated molecular systems. △ Less

Submitted 29 October, 2025; originally announced October 2025.

Laminar: A Scalable Asynchronous RL Post-Training Framework

Authors: Guangming Sheng, Yuxuan Tong, Borui Wan, Wang Zhang, Chaobo Jia, Xibin Wu, Yuqi Wu, Xiang Li, Chi Zhang, Yanghua Peng, Haibin Lin, Xin Liu, Chuan Wu

Abstract: Reinforcement learning (RL) post-training for Large Language Models (LLMs) is now scaling to large clusters and running for extended durations to enhance model reasoning performance. However, the scalability of existing RL frameworks is limited, as extreme long-tail skewness in RL trajectory generation causes severe GPU underutilization. Current asynchronous RL systems attempt to mitigate this, bu… ▽ More Reinforcement learning (RL) post-training for Large Language Models (LLMs) is now scaling to large clusters and running for extended durations to enhance model reasoning performance. However, the scalability of existing RL frameworks is limited, as extreme long-tail skewness in RL trajectory generation causes severe GPU underutilization. Current asynchronous RL systems attempt to mitigate this, but they rely on global weight synchronization between the actor and all rollouts, which creates a rigid model update schedule. This global synchronization is ill-suited for the highly skewed and evolving distribution of trajectory generation latency in RL training, crippling training efficiency. Our key insight is that efficient scaling requires breaking this lockstep through trajectory-level asynchrony, which generates and consumes each trajectory independently. We propose Laminar, a scalable and robust RL post-training system built on a fully decoupled architecture. First, we replace global updates with a tier of relay workers acting as a distributed parameter service. This enables asynchronous and fine-grained weight synchronization, allowing rollouts to pull the latest weight anytime without stalling the actor's training loop. Second, a dynamic repack mechanism consolidates long-tail trajectories onto a few dedicated rollouts, maximizing generation throughput. The fully decoupled design also isolates failures, ensuring robustness for long-running jobs. Our evaluation on a 1024-GPU cluster shows that Laminar achieves up to 5.48$\times$ training throughput speedup over state-of-the-art systems, while reducing model convergence time. △ Less

Submitted 14 October, 2025; originally announced October 2025.

PEO: Training-Free Aesthetic Quality Enhancement in Pre-Trained Text-to-Image Diffusion Models with Prompt Embedding Optimization

Authors: Hovhannes Margaryan, Bo Wan, Tinne Tuytelaars

Abstract: This paper introduces a novel approach to aesthetic quality improvement in pre-trained text-to-image diffusion models when given a simple prompt. Our method, dubbed Prompt Embedding Optimization (PEO), leverages a pre-trained text-to-image diffusion model as a backbone and optimizes the text embedding of a given simple and uncurated prompt to enhance the visual quality of the generated image. We a… ▽ More This paper introduces a novel approach to aesthetic quality improvement in pre-trained text-to-image diffusion models when given a simple prompt. Our method, dubbed Prompt Embedding Optimization (PEO), leverages a pre-trained text-to-image diffusion model as a backbone and optimizes the text embedding of a given simple and uncurated prompt to enhance the visual quality of the generated image. We achieve this by a tripartite objective function that improves the aesthetic fidelity of the generated image, ensures adherence to the optimized text embedding, and minimal divergence from the initial prompt. The latter is accomplished through a prompt preservation term. Additionally, PEO is training-free and backbone-independent. Quantitative and qualitative evaluations confirm the effectiveness of the proposed method, exceeding or equating the performance of state-of-the-art text-to-image and prompt adaptation methods. △ Less

Submitted 2 October, 2025; originally announced October 2025.

WorldSplat: Gaussian-Centric Feed-Forward 4D Scene Generation for Autonomous Driving

Authors: Ziyue Zhu, Zhanqian Wu, Zhenxin Zhu, Lijun Zhou, Haiyang Sun, Bing Wan, Kun Ma, Guang Chen, Hangjun Ye, Jin Xie, jian Yang

Abstract: Recent advances in driving-scene generation and reconstruction have demonstrated significant potential for enhancing autonomous driving systems by producing scalable and controllable training data. Existing generation methods primarily focus on synthesizing diverse and high-fidelity driving videos; however, due to limited 3D consistency and sparse viewpoint coverage, they struggle to support conve… ▽ More Recent advances in driving-scene generation and reconstruction have demonstrated significant potential for enhancing autonomous driving systems by producing scalable and controllable training data. Existing generation methods primarily focus on synthesizing diverse and high-fidelity driving videos; however, due to limited 3D consistency and sparse viewpoint coverage, they struggle to support convenient and high-quality novel-view synthesis (NVS). Conversely, recent 3D/4D reconstruction approaches have significantly improved NVS for real-world driving scenes, yet inherently lack generative capabilities. To overcome this dilemma between scene generation and reconstruction, we propose WorldSplat, a novel feed-forward framework for 4D driving-scene generation. Our approach effectively generates consistent multi-track videos through two key steps: (i) We introduce a 4D-aware latent diffusion model integrating multi-modal information to produce pixel-aligned 4D Gaussians in a feed-forward manner. (ii) Subsequently, we refine the novel view videos rendered from these Gaussians using a enhanced video diffusion model. Extensive experiments conducted on benchmark datasets demonstrate that WorldSplat effectively generates high-fidelity, temporally and spatially consistent multi-track novel view driving videos. Project: https://wm-research.github.io/worldsplat/ △ Less

Submitted 16 October, 2025; v1 submitted 27 September, 2025; originally announced September 2025.

Robust LLM Training Infrastructure at ByteDance

Authors: Borui Wan, Gaohong Liu, Zuquan Song, Jun Wang, Yun Zhang, Guangming Sheng, Shuguang Wang, Houmin Wei, Chenyuan Wang, Weiqiang Lou, Xi Yang, Mofan Zhang, Kaihua Jiang, Cheng Ren, Xiaoyun Zhi, Menghan Yu, Zhe Nan, Zhuolin Zheng, Baoquan Zhong, Qinlong Wang, Huan Yu, Jinxin Chi, Wang Zhang, Yuhan Li, Zixian Du , et al. (10 additional authors not shown)

Abstract: The training scale of large language models (LLMs) has reached tens of thousands of GPUs and is still continuously expanding, enabling faster learning of larger models. Accompanying the expansion of the resource scale is the prevalence of failures (CUDA error, NaN values, job hang, etc.), which poses significant challenges to training stability. Any large-scale LLM training infrastructure should s… ▽ More The training scale of large language models (LLMs) has reached tens of thousands of GPUs and is still continuously expanding, enabling faster learning of larger models. Accompanying the expansion of the resource scale is the prevalence of failures (CUDA error, NaN values, job hang, etc.), which poses significant challenges to training stability. Any large-scale LLM training infrastructure should strive for minimal training interruption, efficient fault diagnosis, and effective failure tolerance to enable highly efficient continuous training. This paper presents ByteRobust, a large-scale GPU infrastructure management system tailored for robust and stable training of LLMs. It exploits the uniqueness of LLM training process and gives top priorities to detecting and recovering failures in a routine manner. Leveraging parallelisms and characteristics of LLM training, ByteRobust enables high-capacity fault tolerance, prompt fault demarcation, and localization with an effective data-driven approach, comprehensively ensuring continuous and efficient training of LLM tasks. ByteRobust is deployed on a production GPU platform and achieves 97% ETTR for a three-month training job on 9,600 GPUs. △ Less

Submitted 20 October, 2025; v1 submitted 19 September, 2025; originally announced September 2025.

Bridging Control Variates and Regression Adjustment in A/B Testing: From Design-Based to Model-Based Frameworks

Authors: Yu Zhang, Bokui Wan, Yongli Qin

Abstract: A B testing serves as the gold standard for large scale, data driven decision making in online businesses. To mitigate metric variability and enhance testing sensitivity, control variates and regression adjustment have emerged as prominent variance reduction techniques, leveraging pre experiment data to improve estimator performance. Over the past decade, these methods have spawned numerous deriva… ▽ More A B testing serves as the gold standard for large scale, data driven decision making in online businesses. To mitigate metric variability and enhance testing sensitivity, control variates and regression adjustment have emerged as prominent variance reduction techniques, leveraging pre experiment data to improve estimator performance. Over the past decade, these methods have spawned numerous derivatives, yet their theoretical connections and comparative properties remain underexplored. In this paper, we conduct a comprehensive analysis of their statistical properties, establish a formal bridge between the two frameworks in practical implementations, and extend the investigation from design based to model-based frameworks. Through simulation studies and real world experiments at ByteDance, we validate our theoretical insights across both frameworks. Our work aims to provide rigorous guidance for practitioners in online controlled experiments, addressing critical considerations of internal and external validity. The recommended method control variates with group specific coefficient estimates has been fully implemented and deployed on ByteDance's experimental platform. △ Less

Submitted 10 October, 2025; v1 submitted 17 September, 2025; originally announced September 2025.

Comments: 20 pages, 44 figures

RoboMatch: A Unified Mobile-Manipulation Teleoperation Platform with Auto-Matching Network Architecture for Long-Horizon Tasks

Authors: Hanyu Liu, Yunsheng Ma, Jiaxin Huang, Keqiang Ren, Jiayi Wen, Yilin Zheng, Haoru Luan, Baishu Wan, Pan Li, Jiejun Hou, Zhihua Wang, Zhigong Song

Abstract: This paper presents RoboMatch, a novel unified teleoperation platform for mobile manipulation with an auto-matching network architecture, designed to tackle long-horizon tasks in dynamic environments. Our system enhances teleoperation performance, data collection efficiency, task accuracy, and operational stability. The core of RoboMatch is a cockpit-style control interface that enables synchronou… ▽ More This paper presents RoboMatch, a novel unified teleoperation platform for mobile manipulation with an auto-matching network architecture, designed to tackle long-horizon tasks in dynamic environments. Our system enhances teleoperation performance, data collection efficiency, task accuracy, and operational stability. The core of RoboMatch is a cockpit-style control interface that enables synchronous operation of the mobile base and dual arms, significantly improving control precision and data collection. Moreover, we introduce the Proprioceptive-Visual Enhanced Diffusion Policy (PVE-DP), which leverages Discrete Wavelet Transform (DWT) for multi-scale visual feature extraction and integrates high-precision IMUs at the end-effector to enrich proprioceptive feedback, substantially boosting fine manipulation performance. Furthermore, we propose an Auto-Matching Network (AMN) architecture that decomposes long-horizon tasks into logical sequences and dynamically assigns lightweight pre-trained models for distributed inference. Experimental results demonstrate that our approach improves data collection efficiency by over 20%, increases task success rates by 20-30% with PVE-DP, and enhances long-horizon inference performance by approximately 40% with AMN, offering a robust solution for complex manipulation tasks. Project website: https://robomatch.github.io △ Less

Submitted 26 March, 2026; v1 submitted 10 September, 2025; originally announced September 2025.

Comments: Accepted to the 2026 IEEE International Conference on Robotics and Automation (ICRA)

Is-NeRF: In-scattering Neural Radiance Field for Blurred Images

Authors: Nan Luo, Chenglin Ye, Jiaxu Li, Gang Liu, Bo Wan, Di Wang, Lupeng Liu, Jun Xiao

Abstract: Neural Radiance Fields (NeRF) has gained significant attention for its prominent implicit 3D representation and realistic novel view synthesis capabilities. Available works unexceptionally employ straight-line volume rendering, which struggles to handle sophisticated lightpath scenarios and introduces geometric ambiguities during training, particularly evident when processing motion-blurred images… ▽ More Neural Radiance Fields (NeRF) has gained significant attention for its prominent implicit 3D representation and realistic novel view synthesis capabilities. Available works unexceptionally employ straight-line volume rendering, which struggles to handle sophisticated lightpath scenarios and introduces geometric ambiguities during training, particularly evident when processing motion-blurred images. To address these challenges, this work proposes a novel deblur neural radiance field, Is-NeRF, featuring explicit lightpath modeling in real-world environments. By unifying six common light propagation phenomena through an in-scattering representation, we establish a new scattering-aware volume rendering pipeline adaptable to complex lightpaths. Additionally, we introduce an adaptive learning strategy that enables autonomous determining of scattering directions and sampling intervals to capture finer object details. The proposed network jointly optimizes NeRF parameters, scattering parameters, and camera motions to recover fine-grained scene representations from blurry images. Comprehensive evaluations demonstrate that it effectively handles complex real-world scenarios, outperforming state-of-the-art approaches in generating high-fidelity images with accurate geometric details. △ Less

Submitted 19 August, 2025; originally announced August 2025.

Creative4U: MLLMs-based Advertising Creative Image Selector with Comparative Reasoning

Authors: Yukang Lin, Xiang Zhang, Shichang Jia, Bowen Wan, Chenghan Fu, Xudong Ren, Yueran Liu, Wanxian Guan, Pengji Wang, Jian Xu, Bo Zheng, Baolin Liu

Abstract: Creative image in advertising is the heart and soul of e-commerce platform. An eye-catching creative image can enhance the shopping experience for users, boosting income for advertisers and advertising revenue for platforms. With the advent of AIGC technology, advertisers can produce large quantities of creative images at minimal cost. However, they struggle to assess the creative quality to selec… ▽ More Creative image in advertising is the heart and soul of e-commerce platform. An eye-catching creative image can enhance the shopping experience for users, boosting income for advertisers and advertising revenue for platforms. With the advent of AIGC technology, advertisers can produce large quantities of creative images at minimal cost. However, they struggle to assess the creative quality to select. Existing methods primarily focus on creative ranking, which fails to address the need for explainable creative selection. In this work, we propose the first paradigm for explainable creative assessment and selection. Powered by multimodal large language models (MLLMs), our approach integrates the assessment and selection of creative images into a natural language generation task. To facilitate this research, we construct CreativePair, the first comparative reasoning-induced creative dataset featuring 8k annotated image pairs, with each sample including a label indicating which image is superior. Additionally, we introduce Creative4U (pronounced Creative for You), a MLLMs-based creative selector that takes into account users' interests. Through Reason-to-Select RFT, which includes supervised fine-tuning with Chain-of-Thought (CoT-SFT) and Group Relative Policy Optimization (GRPO) based reinforcement learning, Creative4U is able to evaluate and select creative images accurately. Both offline and online experiments demonstrate the effectiveness of our approach. Our code and dataset will be made public to advance research and industrial applications. △ Less

Submitted 25 May, 2026; v1 submitted 18 August, 2025; originally announced August 2025.

Mass spectrum of the $Ω\barΩ$ states

Authors: Bing-Dong Wan, Jun-Hao Zhang, Yan Zhang

Abstract: In this study, we investigate the mass spectrum of the $Ω\barΩ$ states with quantum numbers $J^{PC}=0^{-+}$, $1^{--}$, $0^{++}$, and $1^{++}$ within the framework of QCD sum rules. Employing suitably constructed interpolating currents, the analyses are carried out with the operator product expansion (OPE) including condensate contributions up to dimension $12$. Our results indicate the existence o… ▽ More In this study, we investigate the mass spectrum of the $Ω\barΩ$ states with quantum numbers $J^{PC}=0^{-+}$, $1^{--}$, $0^{++}$, and $1^{++}$ within the framework of QCD sum rules. Employing suitably constructed interpolating currents, the analyses are carried out with the operator product expansion (OPE) including condensate contributions up to dimension $12$. Our results indicate the existence of four possible baryonium states with masses $m_{0^{-+}}=(3.22\pm0.07)$ GeV, $m_{1^{--}}=(3.28\pm0.08)$ GeV, $m_{0^{++}}=(3.46\pm0.09)$ GeV, and $m_{1^{++}}=(3.54\pm0.11)$ GeV. For the $0^{-+}$ and $1^{--}$ states, the predicted masses lie below the corresponding dibaryon thresholds, suggesting possible bound-state configurations. In contrast, the $0^{++}$ and $1^{++}$ states are found above the respective thresholds, implying resonance-like behavior. Potential decay channels for these baryonium candidates are discussed, with emphasis on those accessible to current experimental facilities such as BESIII, Belle II, and LHCb. △ Less

Submitted 10 December, 2025; v1 submitted 14 August, 2025; originally announced August 2025.

Comments: accepted by EPJC

Light baryonium states with exotic quantum numbers

Authors: Bing-Dong Wan, Jun-Hao Zhang, Yan Zhang, Ming-Yang Yuan

Abstract: The existence of baryonium-bound or resonant states composed of a baryon and an antibaryon has long been postulated as a natural extension of conventional hadron spectroscopy. In the present work, we conduct a systematic investigation of the mass spectrum and internal configurations of light baryonium candidates exhibiting exotic quantum numbers that are inaccessible within the framework of the tr… ▽ More The existence of baryonium-bound or resonant states composed of a baryon and an antibaryon has long been postulated as a natural extension of conventional hadron spectroscopy. In the present work, we conduct a systematic investigation of the mass spectrum and internal configurations of light baryonium candidates exhibiting exotic quantum numbers that are inaccessible within the framework of the traditional quark model. Employing the method of QCD sum rules, we analyze nucleon-antinucleon and light hyperon-anti-hyperon systems with quantum numbers $J^{PC}=0^{--}$ and $0^{+-}$, which are quantum number combinations prohibited for conventional mesonic states. Our analysis reveals the potential existence of two $0^{--}$ $Λ$-$\barΛ$ baryonium states with masses $(2.90\pm0.09)$ GeV and $(3.36\pm0.09)$ GeV, respectively, as well as two $0^{+-}$ $Λ$-$\barΛ$ states with masses $(2.91\pm0.07)$ GeV and $(3.29\pm0.07)$ GeV, respectively. In addition, corresponding nucleon-antinucleon partner states are identified at $(2.69\pm0.07)$ GeV, $(3.07\pm0.08)$ GeV, $(2.86\pm0.07)$ GeV, and $(3.22\pm0.07)$ GeV, respectively. Furthermore, analogous $Ξ$-$\barΞ$ configurations are predicted with masses of $(3.10\pm0.09)$ GeV, $(3.54\pm0.07)$ GeV, $(3.08\pm0.08)$ GeV, and $(3.45\pm0.08)$ GeV, respectively. The possible decay modes of the light exotic baryonium states are analyzed, which are hopefully measurable in BESIII, BELLEII, and LHCb experiments. △ Less

Submitted 2 May, 2026; v1 submitted 11 August, 2025; originally announced August 2025.

Comments: 20 pages, 12 figures, and 2 tables. Accepted by EPJC

Fully strange tetraquark states via QCD sum rules

Authors: Bing-Dong Wan, Ji-Chong Yang

Abstract: In this paper, we have systematically explored the mass spectrum of fully strange tetraquark candidates within the framework of QCD sum rules, focusing on states with quantum numbers $J^{PC}=0^{++}$, $0^{-+}$, $0^{--}$, $1^{--}$, $1^{+-}$, and $1^{++}$. The analysis reveals the existence of fully strange tetraquark states with masses ranging from approximately $2.07$ to $3.12$ GeV. These predictio… ▽ More In this paper, we have systematically explored the mass spectrum of fully strange tetraquark candidates within the framework of QCD sum rules, focusing on states with quantum numbers $J^{PC}=0^{++}$, $0^{-+}$, $0^{--}$, $1^{--}$, $1^{+-}$, and $1^{++}$. The analysis reveals the existence of fully strange tetraquark states with masses ranging from approximately $2.07$ to $3.12$ GeV. These predictions are confronted with existing experimental observations of potential fully strange tetraquark resonances, notably the $X(2300)$ recently reported by the BESIII Collaboration, which may be interpreted as a fully strange tetraquark state. Furthermore, the possible decay modes of these fully strange tetraquark states are analyzed, providing guidance for their identification in current and future high energy experiments such as BESIII, Belle II, and LHCb. △ Less

Submitted 21 December, 2025; v1 submitted 15 July, 2025; originally announced July 2025.

Comments: 22 pages, 15 figures, accepted by CPC

CheXPO: Preference Optimization for Chest X-ray VLMs with Counterfactual Rationale

Authors: Xiao Liang, Jiawei Hu, Di Wang, Zhi Ma, Lin Zhao, Ronghan Li, Bo Wan, Quan Wang

Abstract: Vision-language models (VLMs) are prone to hallucinations that critically compromise reliability in medical applications. While preference optimization can mitigate these hallucinations through clinical feedback, its implementation faces challenges such as clinically irrelevant training samples, imbalanced data distributions, and prohibitive expert annotation costs. To address these challenges, we… ▽ More Vision-language models (VLMs) are prone to hallucinations that critically compromise reliability in medical applications. While preference optimization can mitigate these hallucinations through clinical feedback, its implementation faces challenges such as clinically irrelevant training samples, imbalanced data distributions, and prohibitive expert annotation costs. To address these challenges, we introduce CheXPO, a Chest X-ray Preference Optimization strategy that combines confidence-similarity joint mining with counterfactual rationale. Our approach begins by synthesizing a unified, fine-grained multi-task chest X-ray visual instruction dataset across different question types for supervised fine-tuning (SFT). We then identify hard examples through token-level confidence analysis of SFT failures and use similarity-based retrieval to expand hard examples for balancing preference sample distributions, while synthetic counterfactual rationales provide fine-grained clinical preferences, eliminating the need for additional expert input. Experiments show that CheXPO achieves 8.93% relative performance gain using only 5% of SFT samples, reaching state-of-the-art performance across diverse clinical tasks and providing a scalable, interpretable solution for real-world radiology applications. △ Less

Submitted 9 July, 2025; originally announced July 2025.

Seamless Interaction: Dyadic Audiovisual Motion Modeling and Large-Scale Dataset

Authors: Vasu Agrawal, Akinniyi Akinyemi, Kathryn Alvero, Morteza Behrooz, Julia Buffalini, Fabio Maria Carlucci, Joy Chen, Junming Chen, Zhang Chen, Shiyang Cheng, Praveen Chowdary, Joe Chuang, Antony D'Avirro, Jon Daly, Ning Dong, Mark Duppenthaler, Cynthia Gao, Jeff Girard, Martin Gleize, Sahir Gomez, Hongyu Gong, Srivathsan Govindarajan, Brandon Han, Sen He, Denise Hernandez , et al. (59 additional authors not shown)

Abstract: Human communication involves a complex interplay of verbal and nonverbal signals, essential for conveying meaning and achieving interpersonal goals. To develop socially intelligent AI technologies, it is crucial to develop models that can both comprehend and generate dyadic behavioral dynamics. To this end, we introduce the Seamless Interaction Dataset, a large-scale collection of over 4,000 hours… ▽ More Human communication involves a complex interplay of verbal and nonverbal signals, essential for conveying meaning and achieving interpersonal goals. To develop socially intelligent AI technologies, it is crucial to develop models that can both comprehend and generate dyadic behavioral dynamics. To this end, we introduce the Seamless Interaction Dataset, a large-scale collection of over 4,000 hours of face-to-face interaction footage from over 4,000 participants in diverse contexts. This dataset enables the development of AI technologies that understand dyadic embodied dynamics, unlocking breakthroughs in virtual agents, telepresence experiences, and multimodal content analysis tools. We also develop a suite of models that utilize the dataset to generate dyadic motion gestures and facial expressions aligned with human speech. These models can take as input both the speech and visual behavior of their interlocutors. We present a variant with speech from an LLM model and integrations with 2D and 3D rendering methods, bringing us closer to interactive virtual agents. Additionally, we describe controllable variants of our motion models that can adapt emotional responses and expressivity levels, as well as generating more semantically-relevant gestures. Finally, we discuss methods for assessing the quality of these dyadic motion models, which are demonstrating the potential for more intuitive and responsive human-AI interactions. △ Less

Submitted 30 June, 2025; v1 submitted 27 June, 2025; originally announced June 2025.

Strategic A/B testing via Maximum Probability-driven Two-armed Bandit

Authors: Yu Zhang, Shanshan Zhao, Bokui Wan, Jinjuan Wang, Xiaodong Yan

Abstract: Detecting a minor average treatment effect is a major challenge in large-scale applications, where even minimal improvements can have a significant economic impact. Traditional methods, reliant on normal distribution-based or expanded statistics, often fail to identify such minor effects because of their inability to handle small discrepancies with sufficient sensitivity. This work leverages a cou… ▽ More Detecting a minor average treatment effect is a major challenge in large-scale applications, where even minimal improvements can have a significant economic impact. Traditional methods, reliant on normal distribution-based or expanded statistics, often fail to identify such minor effects because of their inability to handle small discrepancies with sufficient sensitivity. This work leverages a counterfactual outcome framework and proposes a maximum probability-driven two-armed bandit (TAB) process by weighting the mean volatility statistic, which controls Type I error. The implementation of permutation methods further enhances the robustness and efficacy. The established strategic central limit theorem (SCLT) demonstrates that our approach yields a more concentrated distribution under the null hypothesis and a less concentrated one under the alternative hypothesis, greatly improving statistical power. The experimental results indicate a significant improvement in the A/B testing, highlighting the potential to reduce experimental costs while maintaining high statistical power. △ Less

Submitted 27 June, 2025; originally announced June 2025.

Comments: 25 pages, 14 figures

Seed1.5-Thinking: Advancing Superb Reasoning Models with Reinforcement Learning

Authors: ByteDance Seed, :, Jiaze Chen, Tiantian Fan, Xin Liu, Lingjun Liu, Zhiqi Lin, Mingxuan Wang, Chengyi Wang, Xiangpeng Wei, Wenyuan Xu, Yufeng Yuan, Yu Yue, Lin Yan, Qiying Yu, Xiaochen Zuo, Chi Zhang, Ruofei Zhu, Zhecheng An, Zhihao Bai, Yu Bao, Xingyan Bin, Jiangjie Chen, Feng Chen, Hongmin Chen , et al. (249 additional authors not shown)

Abstract: We introduce Seed1.5-Thinking, capable of reasoning through thinking before responding, resulting in improved performance on a wide range of benchmarks. Seed1.5-Thinking achieves 86.7 on AIME 2024, 55.0 on Codeforces and 77.3 on GPQA, demonstrating excellent reasoning abilities in STEM and coding. Beyond reasoning tasks, the method demonstrates notable generalization across diverse domains. For in… ▽ More We introduce Seed1.5-Thinking, capable of reasoning through thinking before responding, resulting in improved performance on a wide range of benchmarks. Seed1.5-Thinking achieves 86.7 on AIME 2024, 55.0 on Codeforces and 77.3 on GPQA, demonstrating excellent reasoning abilities in STEM and coding. Beyond reasoning tasks, the method demonstrates notable generalization across diverse domains. For instance, it surpasses DeepSeek R1 by 8% in win rate on non-reasoning tasks, indicating its broader applicability. Compared to other state-of-the-art reasoning models, Seed1.5-Thinking is a Mixture-of-Experts (MoE) model with a relatively small size, featuring 20B activated and 200B total parameters. As part of our effort to assess generalized reasoning, we develop two internal benchmarks, BeyondAIME and Codeforces, both of which will be publicly released to support future research. Model trial link: https://www.volcengine.com/experience/ark. △ Less

Submitted 29 April, 2025; v1 submitted 10 April, 2025; originally announced April 2025.

MegaScale-Data: Scaling Dataloader for Multisource Large Foundation Model Training

Authors: Juntao Zhao, Qi Lu, Wei Jia, Borui Wan, Lei Zuo, Junda Feng, Jianyu Jiang, Yangrui Chen, Shuaishuai Cao, Jialing He, Kaihua Jiang, Yuanzhe Hu, Shibiao Nong, Yanghua Peng, Haibin Lin, Chuan Wu

Abstract: Modern frameworks for training large foundation models (LFMs) employ dataloaders in a data-parallel manner, with each loader processing a disjoint subset of training data. When preparing data for LFM training that originates from multiple, distinct sources, two fundamental challenges arise. First, due to the quadratic computational complexity of the attention operator, the non-uniform sample distr… ▽ More Modern frameworks for training large foundation models (LFMs) employ dataloaders in a data-parallel manner, with each loader processing a disjoint subset of training data. When preparing data for LFM training that originates from multiple, distinct sources, two fundamental challenges arise. First, due to the quadratic computational complexity of the attention operator, the non-uniform sample distribution over data-parallel ranks leads to significant workload imbalance among dataloaders, degrading the training efficiency. Second, supporting diverse data sources requires per-dataset file access states that are redundantly replicated across parallel loaders, consuming excessive memory. This also hinders dynamic data mixing (e.g., curriculum learning) and causes redundant access/memory overhead in hybrid parallelism. We present MegaScale-Data, an industrial-grade distributed data loading architecture for multisource LFMs training, with three key innovations: (1) Disaggregated data preprocessing via role-specific actors (Source Loaders/Data Constructors) to eliminate source and parallelism redundant data access and ensure multisource scalability. (2) Centralized and declarative data plane for load-time multisource orchestration, such as long-short context, multimodality, and curriculum learning. (3) Multi-level auto-partitioning and scaling mechanism for source loaders under heterogeneous preprocessing costs. We also contribute our designs and operational experience in deployment and fault tolerance. MegaScale-Data achieves up to: (1) 4.5x end-to-end training throughput improvement, and (2) 13.5x reduction in CPU memory usage. △ Less

Submitted 27 April, 2026; v1 submitted 13 April, 2025; originally announced April 2025.

Journal ref: European Conference on Computer Systems (EUROSYS '26), April 27--30, 2026, Edinburgh, Scotland, UK

A Confounding Factors-Inhibition Adversarial Learning Framework for Multi-site fMRI Mental Disorder Identification

Authors: Xin Wen, Shijie Guo, Wenbo Ning, Rui Cao, Yan Niu, Bin Wan, Peng Wei, Xiaobo Liu, Jie Xiang

Abstract: In open data sets of functional magnetic resonance imaging (fMRI), the heterogeneity of the data is typically attributed to a combination of factors, including differences in scanning procedures, the presence of confounding effects, and population diversities between multiple sites. These factors contribute to the diminished effectiveness of representation learning, which in turn affects the overa… ▽ More In open data sets of functional magnetic resonance imaging (fMRI), the heterogeneity of the data is typically attributed to a combination of factors, including differences in scanning procedures, the presence of confounding effects, and population diversities between multiple sites. These factors contribute to the diminished effectiveness of representation learning, which in turn affects the overall efficacy of subsequent classification procedures. To address these limitations, we propose a novel multi-site adversarial learning network (MSalNET) for fMRI-based mental disorder detection. Firstly, a representation learning module is introduced with a node information assembly (NIA) mechanism to better extract features from functional connectivity (FC). This mechanism aggregates edge information from both horizontal and vertical directions, effectively assembling node information. Secondly, to generalize the feature across sites, we proposed a site-level feature extraction module that can learn from individual FC data, which circumvents additional prior information. Lastly, an adversarial learning network is proposed as a means of balancing the trade-off between individual classification and site regression tasks, with the introduction of a novel loss function. The proposed method was evaluated on two multi-site fMRI datasets, i.e., Autism Brain Imaging Data Exchange (ABIDE) and ADHD-200. The results indicate that the proposed method achieves a better performance than other related algorithms with the accuracy of 75.56 and 68.92 in ABIDE and ADHD-200 datasets, respectively. Furthermore, the result of the site regression indicates that the proposed method reduces site variability from a data-driven perspective. The most discriminative brain regions revealed by NIA are consistent with statistical findings, uncovering the "black box" of deep learning to a certain extent. △ Less

Submitted 12 April, 2025; originally announced April 2025.

Report number: 47

Journal ref: Proceedings of the Annual Meeting of the Cognitive Science Society 2025

BioMamba: Leveraging Spectro-Temporal Embedding in Bidirectional Mamba for Enhanced Biosignal Classification

Authors: Jian Qian, Teck Lun Goh, Bingyu Xie, Chengyao Zhu, Biao Wan, Yawen Guan, Rachel Ding Chen, Patrick Yin Chiang

Abstract: Biological signals, such as electroencephalograms (EEGs) and electrocardiograms (ECGs), play a pivotal role in numerous clinical practices, such as diagnosing brain and cardiac arrhythmic diseases. Existing methods for biosignal classification rely on Attention-based frameworks with dense Feed Forward layers, which lead to inefficient learning, high computational overhead, and suboptimal performan… ▽ More Biological signals, such as electroencephalograms (EEGs) and electrocardiograms (ECGs), play a pivotal role in numerous clinical practices, such as diagnosing brain and cardiac arrhythmic diseases. Existing methods for biosignal classification rely on Attention-based frameworks with dense Feed Forward layers, which lead to inefficient learning, high computational overhead, and suboptimal performance. In this work, we introduce BioMamba, a Spectro-Temporal Embedding strategy applied to the Bidirectional Mamba framework with Sparse Feed Forward layers to enable effective learning of biosignal sequences. By integrating these three key components, BioMamba effectively addresses the limitations of existing methods. Extensive experiments demonstrate that BioMamba significantly outperforms state-of-the-art methods with marked improvement in classification performance. The advantages of the proposed BioMamba include (1) Reliability: BioMamba consistently delivers robust results, confirmed across six evaluation metrics. (2) Efficiency: We assess both model and training efficiency, the BioMamba demonstrates computational effectiveness by reducing model size and resource consumption compared to existing approaches. (3) Generality: With the capacity to effectively classify a diverse set of tasks, BioMamba demonstrates adaptability and effectiveness across various domains and applications. △ Less

Submitted 25 March, 2025; v1 submitted 14 March, 2025; originally announced March 2025.

Comments: Biological signals