arXiv subjects

Siyuan Chen

Publications and source records attributed to Siyuan Chen.

At least 37 records · Page 2Linked to original sources

arXiv2026

HC-RAG: Evidence-Centric Retrieval-Augmented Generation over Heterogeneous Financial Filings

Financial question answering over annual reports requires more than retrieving semantically similar passages. It often involves identifying relevant companies and fiscal years, locating standardized filing sections, collecting textual and tabular evidence, and checking answers against the original documents. Existing RAG systems, however, usually flatten long filings into unordered chunks, pay limited attention to the typed structure of financial reports, and use fixed text-table fusion strategies without considering query intent. To address these limitations, we propose \textbf{HC-RAG}, a hierarchical cross-modal retrieval-augmented generation framework for evidence-centric financial QA. HC-RAG organizes filings into a typed financial evidence graph with documents, sections, text units, table units, and metadata nodes. It retrieves evidence through document-section-unit paths, aligns textual and tabular evidence in a shared retrieval space, and routes evidence according to four semantic intents: calculation, trend, fact, and comparison. We further introduce \textbf{Multi-Doc-2025}, a benchmark containing 2,327 expert-verified QA pairs from 179 SEC 10-K filings of 87 S\&P 500 companies across fiscal years 2022--2024, with labels for intent, difficulty, and structural evidence attributes. Experiments on public financial QA benchmarks and Multi-Doc-2025 show that HC-RAG improves both answer quality and evidence localization, especially in long-document, table-related, and cross-document settings. HC-RAG outperforms RAPTOR by 6.6 F1 points on DocFinQA and GraphRAG by 10.9 F1 points on Multi-Doc-2025. Evidence-level analysis and ablation studies show that the improvements mainly come from more accurate section localization, table grounding, cross-document evidence aggregation, and intent-aware text-table routing.

cs.CL↗

arXiv2026

SIRI: Self-Internalizing Reinforcement Learning with Intrinsic Skills for LLM Agent Training

Long-horizon LLM agents can benefit from reusable skills, yet existing skill-based methods often rely on external skill generators during training or persistent skill retrieval at inference, increasing engineering complexity, context length, and deployment latency. We propose Self-Internalizing Reinforcement learning with Intrinsic skills (SIRI), a three-phase framework that enables agents to discover, validate, and internalize skills without external skill generators or inference-time skill banks. SIRI first warms up the policy with GiGPO to acquire basic interaction ability and collect successful skill-free trajectories. It then performs self-skill mining, where the current policy summarizes compact skills from its own successful plain rollouts and validates them through paired skill-augmented and skill-free rollouts. Finally, SIRI distills only beneficial skill-guided action tokens into the plain policy using trajectory-level utility and action-level advantage. At inference, the agent runs with the original prompt only. On ALFWorld and WebShop with Qwen2.5-7B-Instruct, SIRI improves GiGPO from 0.908 to 0.930 on ALFWorld and from 0.728 to 0.813 on WebShop, outperforming prompt-based, RL-based, and memory-augmented baselines. Further analysis shows that our self-mining strategy can achieve performance comparable to distillation with closed-source large model. Our code is available at https://github.com/kirito618/SIRI.

cs.AI↗

arXiv2026

CAGE-SGG: Counterfactual Active Graph Evidence for Open-Vocabulary Scene Graph Generation

Open-vocabulary scene graph generation (SGG) aims to describe visual scenes with flexible and fine-grained relation phrases beyond a fixed predicate vocabulary. While recent vision-language models greatly expand the semantic coverage of SGG, they also introduce a critical reliability issue: predicted relations may be driven by language priors or object co-occurrence rather than grounded visual evidence. In this paper, we propose an evidence-rounded open-vocabulary SGG framework based on counterfactual relation verification. Instead of directly accepting plausible relation proposals, our method verifies whether each candidate relation is supported by relation-pecific visual, geometric, and contextual evidence. Specifically, we first generate open-vocabulary relation candidates with a vision-language proposer, then decompose predicate phrases into soft evidence bases such as support, contact, containment, depth and state. A relation-conditioned evidence encoder extracts predicate-relevant cues, while a counterfactual verifier tests whether the relation score decreases when necessary vidence is removed and remains stable under irrelevant perturbations. We further introduce contradiction-aware predicate learning and graph-level preference optimization to improve fine-grained discrimination and global graph consistency. Experiments on conventional, open-vocabulary, and panoptic SGG benchmarks show that our method consistently improves standard recall-based metrics, unseen predicate generalization, and counterfactual grounding quality. These results demonstrate that moving from relation generation to relation verification leads to more reliable, interpretable, and evidence-grounded scene graphs.

cs.CV↗

arXiv2026

DualMem: Bypassing the Objectness Bottleneck for Calibrated Unknown-Stream Filtering in Open-World Object Detection

Open-world object detection (OWOD) requires detectors to localize known classes while identifying unknown objects for future incremental learning. We find that the unknown prediction streams of strong OWOD detectors are heavily polluted: on M-OWODB, across PROB, OW-DETR, and HypOW, future-task positive unknowns make up less than 10% of unknown predictions, whereas background false positives account for 46-71%. We show that this is not a missing-information problem, but an information bottleneck at the objectness head. On PROB Task 1, a linear probe on the 256-D decoder query achieves an AUROC of 0.908 for positive-versus-negative unknown discrimination, but the final one-dimensional objectness scalar drops to 0.642. A frozen SigLIP feature, without access to the detector, independently recovers much of this proposal-level separability at the filtering stage (AUROC = 0.871). Motivated by this finding, we propose DualMem, a calibrated post-hoc filter that assumes a small image-disjoint annotated calibration split of held-out future-task objects and performs a non-parametric likelihood ratio test in frozen SigLIP feature space. DualMem uses a k-nearest-neighbor positive memory to protect future-task objects and a negative memory to suppress background-like proposals. Its decision threshold is chosen by Neyman-Pearson calibration, giving users an explicit trade-off between false-unknown suppression and novel recall. Across PROB, OW-DETR, and HypOW on M-OWODB Task 1, DualMem reduces background-type false unknown proposals per image by 44.9%-66.3%, with a mean reduction of 56.6%. On PROB Task 1, it more than doubles the reduction achieved by a natural K-means prototype baseline, while leaving known-class mAP unchanged because known detections bypass the filter.

cs.CV↗

arXiv2026

WorldParticle: Unified World Simulation of Lagrangian Particle Dynamics via Transformer

A unified simulator that can model diverse physical phenomena without solver-specific redesign is a long-standing goal across simulation science. We present a learning-based particle simulator built on a single transformer architecture to model cloth, elastic solds, Newtonian and non-Newtonian fluids, granular materials, and molecular dynamics. Our model follows a prediction-correction design on a shared Lagrangian particle representation. An explicit predictor first advances particles under the known external forces, producing an intermediate state that captures externally driven motion but not inter-particle interactions. A learned corrector then predicts the residual position and velocity updates through three stages: a particle tokenizer that encodes local particle-particle, particle-boundary, and topology-guided interactions; a super-token encoder that hierarchically merges particle tokens into a compact set of super tokens via alternating self-attention and token merging; and a super-token decoder that lifts these super tokens back to particle resolution through cross-attention to predict per-particle position and velocity corrections. Progressive token merging reduces the attention cost at successive encoder layers by halving the token count at each level, and the decoder communicates through the compact super-token set rather than full particle-to-particle attention. Across the six dynamics categories, the same architecture generalizes to unseen materials, boundary configurations, initial conditions, and external forces. We further demonstrate downstream interactive control, inverse design, and learning from real-world manipulation data, reducing the need for per-phenomenon solver engineering.

cs.GR↗

arXiv2026

Muon beams towards muonium physics: progress and prospects

Advances in accelerator technology have led to significant improvements in the quality of muon beams over the past decades. Investigations of the muon and muonium enable precise measurements of fundamental constants, as well as searches for new physics beyond the Standard Model. Furthermore, by utilizing muon beams with high intensity and polarization, studies of the dynamics of the muon and muonium within atomic level can offer valuable insights into materials science. This review presents recent progress and prospects at the frontiers of muon beams and high-precision muonium physics. It also provides an overview of novel methods and detection techniques to achieve high sensitivities in different areas, including particle physics, nuclear physics, materials science and beyond.

hep-ex↗

arXiv2026

Constraints on Ultralight Scalar and Dark Photon Dark Matter from PPTA-DR3 and EPTA-DR2

The cold dark matter model successfully describes the Universe on large scales, yet faces challenges at sub-galactic scales. Ultralight dark matter (ULDM), with particle masses around $10^{-22} \mathrm{eV}$, offers a promising solution to these small-scale issues. Pulsar Timing Arrays (PTAs), designed to detect nanohertz gravitational waves, can also provide a sensitive probe for ULDM signals. In this work, we perform a Bayesian search for ULDM using PTA data sets, focusing on two types of signals: the oscillatory gravitational potential from scalar ULDM and the fifth-force interaction mediated by dark photon dark matter (DPDM). We incorporate pulsar distances in the analysis to better model the ULDM density. No statistically significant evidence for ULDM has been found, therefore we place 95% confidence-level upper limits on the relevant parameters. For scalar ULDM, our analysis does not exclude the scenario in which ULDM constitutes all of dark matter. The constraints from PPTA-DR3 show significant improvements over the earlier PPTA-DR2 (2018 Preview) across most of the mass range, and are consistent with the recent uncorrelated limits from other PTAs. We also present for the first time the DPDM constraints using EPTA data. The obtained bounds on the DPDM from the EPTA-DR2 and PPTA-DR3 are comparable to existing constraints.

astro-ph.CO↗

arXiv2026

Positron Transport System for Muonium-to-Antimuonium Conversion Experiment

Muonium-to-Antimuonium Conversion Experiment (MACE) aims to find the charged lepton flavor violation (cLFV) process. A key component of MACE is the positron transport system (PTS) to collect and transport atomic positrons from antimuonium decays, which consists of an electrostatic accelerator and a solenoid beamline. Through field simulations in \textsc{COMSOL} and particle transport simulations based on \textsc{Geant4}, the PTS can achieve a geometric acceptance of the signal at 65.81(4)\% along with a position resolution of 88(1)~$μ$m~$\times$~102(1)~$μ$m. The system achieves 322.4(1)~ns transit time with a spread of 6.9(1)~ns, which allows for a TOF-based rejection of internal conversion backgrounds by a factor of $10^{-7}$. These promising results pave the way for new-physics signal identifications and background rejections in MACE and offer a novel paradigm for internal transport system in high-intensity frontiers.

hep-ex↗

arXiv2026

To understand the radiative processes of pulsars and fast radio bursts with the FAST

The radiative mechanism of coherent radio emission has remained an enigma since the discovery of pulsars, even the emergence of fast radio bursts (FRBs), which exhibit similarities to the single-pulse behavior of pulsars and have opened a new view for deciphering the long-standing mystery. Besides tremendous efforts in modelling, advanced facilities matter for solving the problem. The authors review the observational breakthroughs from the Five-hundred-meter Aperture Spherical radio Telescope (FAST), which are providing pivotal insights to unravel the underlying physics of pulsars and FRBs. This study offers a novel perspective in the era when pulsars meet FRBs, and further investigations are encouraged to utilize the highly sensitive telescope, the FAST.

astro-ph.HE↗

arXiv2026

Scalable continuous gravitational wave detection in PTA data with non-parametric red noise suppression and optimal pulsar selection

Bayesian methods for the detection of continuous gravitational waves (CGWs) in Pulsar Timing Array (PTA) data incur substantial computational costs that grow rapidly due to the number of noise and signal parameters characterizing the fitted model being proportional to the size of the PTA. This computational burden limits the scalability of these methods for large-scale PTAs comprising hundreds of pulsars anticipated from next-generation radio astronomy facilities. In this work, we introduce a computationally efficient frequentist method designed to circumvent this challenge. This is achieved by combining an adaptive spline fitting algorithm that non-parametrically suppresses red noise, thereby eliminating the need for complex noise modeling inherent to Bayesian methods, with a novel scheme for optimizing the subsets of pulsars included in the search. We quantify the performance of our method on a simulated dataset based on the NANOGrav 15-year data release and find that it achieves a performance comparable to that of Bayesian analysis: for a CGW signal with a signal-to-noise ratio of $\approx 10$, our method yields a relative characteristic strain error of 1.0\% and a frequency error of 0.072\% from the injected values by using the optimal pulsar selections, while the same errors are 1.7\% and 0.16\%, respectively, for the standard Bayesian analysis. At the same time, our analysis completes in less than 5 hours, in contrast to the 1-2 days required by Bayesian methods. This allows us to perform a rigorous study of our method using multiple data realizations and signal parameters, establishing it as an efficient and scalable tool for CGW searches with large-scale PTAs.

astro-ph.IM↗

arXiv2026

Perturb-and-Restore: Simulation-driven Structural Augmentation Framework for Imbalance Chromosomal Anomaly Detection

Detecting structural chromosomal abnormalities is crucial for accurate diagnosis and management of genetic disorders. However, collecting sufficient structural abnormality data is extremely challenging and costly in clinical practice, and not all abnormal types can be readily collected. As a result, deep learning approaches face significant performance degradation due to the severe imbalance and scarcity of abnormal chromosome data. To address this challenge, we propose a Perturb-and-Restore (P&R), a simulation-driven structural augmentation framework that effectively alleviates data imbalance in chromosome anomaly detection. The P&R framework comprises two key components: (1) Structure Perturbation and Restoration Simulation, which generates synthetic abnormal chromosomes by perturbing chromosomal banding patterns of normal chromosomes followed by a restoration diffusion network that reconstructs continuous chromosome content and edges, thus eliminating reliance on rare abnormal samples; and (2) Energy-guided Adaptive Sampling, an energy score-based online selection strategy that dynamically prioritizes high-quality synthetic samples by referencing the energy distribution of real samples. To evaluate our method, we construct a comprehensive structural anomaly dataset consisting of over 260,000 chromosome images, including 4,242 abnormal samples spanning 24 categories. Experimental results demonstrate that the P&R framework achieves state-of-the-art (SOTA) performance, surpassing existing methods with an average improvement of 8.92% in sensitivity, 8.89% in precision, and 13.79% in F1-score across all categories.

cs.CV↗

arXiv2026

Factorized Neural Implicit DMD for Parametric Dynamics

A data-driven, model-free approach to modeling the temporal evolution of physical systems mitigates the need for explicit knowledge of the governing equations. Even when physical priors such as partial differential equations are available, such systems often reside in high-dimensional state spaces and exhibit nonlinear dynamics, making traditional numerical solvers computationally expensive and ill-suited for real-time analysis and control. Consider the problem of learning a parametric flow of a dynamical system: with an initial field and a set of physical parameters, we aim to predict the system's evolution over time in a way that supports long-horizon rollouts, generalization to unseen parameters, and spectral analysis. We propose a physics-coded neural field parameterization of the Koopman operator's spectral decomposition. Unlike a physics-constrained neural field, which fits a single solution surface, and neural operators, which directly approximate the solution operator at fixed time horizons, our model learns a factorized flow operator that decouples spatial modes and temporal evolution. This structure exposes underlying eigenvalues, modes, and stability of the underlying physical process to enable stable long-term rollouts, interpolation across parameter spaces, and spectral analysis. We demonstrate the efficacy of our method on a range of dynamics problems, showcasing its ability to accurately predict complex spatiotemporal phenomena while providing insights into the system's dynamic behavior.

cs.LG↗

arXiv2026

Not All Candidates are Created Equal: A Heterogeneity-Aware Approach to Pre-ranking in Recommender Systems

Most large-scale recommender systems follow a multi-stage cascade of retrieval, pre-ranking, ranking, and re-ranking. A key challenge at the pre-ranking stage arises from the heterogeneity of training instances sampled from coarse-grained retrieval results, fine-grained ranking signals, and exposure feedback. Our analysis reveals that prevailing pre-ranking methods, which indiscriminately mix heterogeneous samples, suffer from gradient conflicts: hard samples dominate training while easy ones remain underutilized, leading to suboptimal performance. We further show that the common practice of uniformly scaling model complexity across all samples is inefficient, as it overspends computation on easy cases and slows training without proportional gains. To address these limitations, this paper presents Heterogeneity-Aware Adaptive Pre-ranking (HAP), a unified framework that mitigates gradient conflicts through conflict-sensitive sampling coupled with tailored loss design, while adaptively allocating computational budgets across candidates. Specifically, HAP disentangles easy and hard samples, directing each subset along dedicated optimization paths. Building on this separation, it first applies lightweight models to all candidates for efficient coverage, and further engages stronger models on the hard ones, maintaining accuracy while reducing cost. This approach not only improves pre-ranking effectiveness but also provides a practical perspective on scaling strategies in industrial recommender systems. HAP has been deployed in the Toutiao production system for 9 months, yielding up to 0.4% improvement in user app usage duration and 0.05% in active days, without additional computational cost. We also release a large-scale industrial hybrid-sample dataset to enable the systematic study of source-driven candidate heterogeneity in pre-ranking.

cs.IR↗

arXiv2026

Physically Valid Biomolecular Interaction Modeling with Gauss-Seidel Projection

Biomolecular interaction modeling has been substantially advanced by foundation models, yet they often produce all-atom structures that violate basic steric feasibility. We address this limitation by enforcing physical validity as a strict constraint during both training and inference with a uniffed module. At its core is a differentiable projection that maps the provisional atom coordinates from the diffusion model to the nearest physically valid conffguration. This projection is achieved using a Gauss-Seidel scheme, which exploits the locality and sparsity of the constraints to ensure stable and fast convergence at scale. By implicit differentiation to obtain gradients, our module integrates seamlessly into existing frameworks for end-to-end ffnetuning. With our Gauss-Seidel projection module in place, two denoising steps are sufffcient to produce biomolecular complexes that are both physically valid and structurally accurate. Across six benchmarks, our 2-step model achieves the same structural accuracy as state-of-the-art 200-step diffusion baselines, delivering approximately 10 times faster wall-clock speed while guaranteeing physical validity. The code is available at https://github.com/chensiyuan030105/ProteinGS.git.

q-bio.BM↗

arXiv2026

From Medical Records to Diagnostic Dialogues: A Clinical-Grounded Approach and Dataset for Psychiatric Comorbidity

Psychiatric comorbidity is clinically significant yet challenging due to the complexity of multiple co-occurring disorders. To address this, we develop a novel approach integrating synthetic patient electronic medical record (EMR) construction and multi-agent diagnostic dialogue generation. We create 502 synthetic EMRs for common comorbid conditions using a pipeline that ensures clinical relevance and diversity. Our multi-agent framework transfers the clinical interview protocol into a hierarchical state machine and context tree, supporting over 130 diagnostic states while maintaining clinical standards. Through this rigorous process, we construct PsyCoTalk, the first large-scale dialogue dataset supporting comorbidity, containing 3,000 multi-turn diagnostic dialogues validated by psychiatrists. This dataset enhances diagnostic accuracy and treatment planning, offering a valuable resource for psychiatric comorbidity research. Compared to real-world clinical transcripts, PsyCoTalk exhibits high structural and linguistic fidelity in terms of dialogue length, token distribution, and diagnostic reasoning strategies. Licensed psychiatrists confirm the realism and diagnostic validity of the dialogues. This dataset enables the development and evaluation of models capable of multi-disorder psychiatric screening in a single conversational pass.

cs.AI↗

arXiv2026

Pulsar Timing Array in the past decade

The past decade has been a transformative period for pulsar timing arrays (PTAs) and their search for nanohertz gravitational waves (GWs). This progress has been driven by collective advances in instrumentation for pulsar timing observations, increasingly sophisticated data-analysis techniques, and improved theoretical understanding of the origins of nanohertz GW signals. PTA sensitivity has steadily improved, leading first to progressively more stringent upper limits on the gravitational-wave background (GWB), and subsequently to the identification of a common red-noise process in pulsar timing data, the first hint of a GWB. In 2023, multiple PTA collaborations reported evidence for the Hellings-Downs correlation, widely regarded as the definitive signature of a GWB. These developments place PTAs on the threshold of a confident GW detection and the opening of a new low-frequency window on the GW Universe. In this article, we present an overview of PTA experiments, with particular emphasis on the rapid progress achieved during this pivotal period for PTA and nanohertz GW science.

astro-ph.HE↗

arXiv2026

Cosmological Budget of Entropy from Merging Black Holes

Black holes contain more entropy than any other component of the observable universe. Gravitational-wave observations from LIGO and Virgo have shown evidence of a previously unknown black hole mass range, which provides new information to update the entropy budget. Increases in entropy due to binary black hole mergers, as implied in the second law of thermodynamics, should also be added to the budget. In this study, we update the cosmological entropy budget for black holes in the stellar to lite-intermediate-mass range $(5-300~M_\odot)$, originating from either supernovae or binary mergers, by utilizing a suite of population synthesis models and phenomenological fits derived from numerical relativity. We report three new insights: Firstly, the cumulative entropy from merging black holes surpasses the total entropy from cosmic microwave background photons around the onset of the Over-massive Black Hole Galaxy phase at $z\sim 12$, suggesting that mergers played a more significant role in shaping the thermodynamic state of the early universe than relic radiation. Secondly, if primordial black holes constitute a nonzero fraction of dark matter, their early binary mergers establish an ``entropy floor" in the Dark Ages and can dominate the cumulative merger-generated entropy history even for small abundances. Thirdly, by computing the cosmological density parameters, we highlight the thermodynamic asymmetry in black hole mergers, where the production of gravitational-wave energy is inefficient compared to the immense generation of Bekenstein-Hawking entropy.

gr-qc↗

arXiv2026

FutureX-Pro: Extending Future Prediction to High-Value Vertical Domains

Building upon FutureX, which established a live benchmark for general-purpose future prediction, this report introduces FutureX-Pro, including FutureX-Finance, FutureX-Retail, FutureX-PublicHealth, FutureX-NaturalDisaster, and FutureX-Search. These together form a specialized framework extending agentic future prediction to high-value vertical domains. While generalist agents demonstrate proficiency in open-domain search, their reliability in capital-intensive and safety-critical sectors remains under-explored. FutureX-Pro targets four economically and socially pivotal verticals: Finance, Retail, Public Health, and Natural Disaster. We benchmark agentic Large Language Models (LLMs) on entry-level yet foundational prediction tasks -- ranging from forecasting market indicators and supply chain demands to tracking epidemic trends and natural disasters. By adapting the contamination-free, live-evaluation pipeline of FutureX, we assess whether current State-of-the-Art (SOTA) agentic LLMs possess the domain grounding necessary for industrial deployment. Our findings reveal the performance gap between generalist reasoning and the precision required for high-value vertical applications.

cs.AI↗