Search arXiv⌕ Search

arXiv subjects

Yang Chen

Publications and source records attributed to Yang Chen.

At least 91 records · Page 5Linked to original sources
arXiv2026

Scaling the Horizon, Not the Parameters: Reaching Trillion-Parameter Performance with a 35B Agent

We introduce Agents-A1, a 35B Mixture-of-Experts Agentic Model that reaches trillion-parameter-level performance by scaling the agent horizon. We investigate agent-horizon scaling from two perspectives: scaling long-horizon trajectories and scaling heterogeneous agent abilities. To support this goal, we build a long-horizon knowledge-action infrastructure that connects external knowledge, actions, observations, and verifier outcomes, producing agentic trajectories with an average length of 45K tokens. Based on this, we train Agents-A1 with a three-stage recipe. First, we perform full-domain supervised fine-tuning to align the base model with broad agentic behaviors. Second, we train domain-level teacher models to capture specialized expertise in each domain. Third, we propose a multi-teacher domain-routed on-policy distillation with salient vocabulary alignment to improve knowledge transfer efficiency across different domains, unifying six heterogeneous domains into one deployable student model. Agents-A1 achieves strong and broad performance for long-horizon agent benchmarks. Compared with 1T-parameter model such as Kimi-K2.6 and DeepSeek-V4-pro, Agents-A1 achieves leading results on SEAL-0 (56.4), IFBench (80.6), HiPhO (46.4), FrontierScience-Olympiad (79.0), and MolBench-Bind (56.8), and remains highly competitive on SciCode (44.3), HLE (47.6) and BrowseComp (75.5). We hope this work provides the community with a practical path for scaling the horizon using a 35B agent that can reach or match the performance of 1T models on long-horizon tasks.

cs.CL↗
arXiv2026

$\mathfrak{so}_n(\mathbb{C})$-modules which are free over an abelian nilradical

In this paper, we classify the category of $\mathfrak{so}_n(\mathbb{C})$-modules whose restrictions to the universal enveloping algebra of the abelian nilradical of a maximal parabolic subalgebra are free of rank $1$. We show that they generically are simple, and give an explicit description of submodules in the non-simple case. This category embodies a certain connection between weight modules and non-weight modules.

math.RT↗
arXiv2026

Chandra and XMM-Newton X-ray Study on the Core-collapse Supernova Remnant N63A in an H II Region

N63A is one of the brightest supernova remnants (SNRs) in the Large Magellanic Cloud and provides an excellent laboratory for studying SNR evolution in an H II region. We present a detailed X-ray analysis of N63A using Chandra and XMM-Newton observations, combining both imaging and high-resolution spectroscopy. Our global spectral fitting reveals three distinct thermal plasma components with temperatures $kT$$\sim$0.3, 0.7, and 1.5 keV. Spatially-resolved spectroscopy with Chandra shows substantial variations in physical parameters across the remnant, with the eastern lobes of the optical nebula exhibiting significantly higher ionization timescales than the western region. These multi-temperature plasma components indicate that N63A is evolving in a cloudy interstellar medium: the low-temperature component arises from evaporated dense cloudlets that are engulfed by the blast wave, the intermediate-temperature component represents shocked inter-cloud medium, and the highest-temperature component likely results from the shocks reflected by the clouds. We estimate a Sedov age of approximately 4.5 kyr and an explosion energy of about $4\times10^{51}$ erg. Comparison of the observed abundance ratios and masses of metal elements with the nucleosynthesis models constrains the progenitor mass to approximately $20 M_{\odot}$, supporting a single-star core-collapse origin for N63A.

astro-ph.HE↗
arXiv2026

Implicit discretization schemes for full-kinetic ion and drift-kinetic electron simulations

We present a new electromagnetic plasma simulation model with full-kinetic ions and drift-kinetic electrons. This model (termed as FIDES) solves the electric field using the implicit perpendicular Ohm's law and a novel implicit parallel Ampere's law, where the latter requires an implicit scheme for the parallel electric field in advancing the electron weights. To suppress unphysical high-frequency instabilities, ion weights are advanced using an implicit scheme for perpendicular electric fields. Simulations of perpendicular and parallel waves validate the model's capability in handling high-frequency physics. Low-frequency wave simulations demonstrate that the implicit parallel Ampere's law can mitigate the cancellation problem more effectively than the conventional schemes using the parallel Ohm's law. To reduce the numerical damping from implicit time-stepping, we develop a second-order scheme for particle pushing. Meanwhile, an integrated strategy combining the first- and second-order schemes is employed to suppress odd-even decoupling while maintaining the accuracy of the second-order formulation.

physics.plasm-ph↗
arXiv2026

OmniMapBench: Benchmarking Visual-Centric Reasoning on Diverse Map Documents

Recent advancements in LVLMs necessitate robust benchmarks for complex, visually grounded reasoning. A critical limitation is identified in many document understanding benchmarks: visual content is often reducible to text, enabling high performance without genuine visual grounding. To address this limitation, OmniMapBench is introduced to foster visual-centric reasoning for map documents. The benchmark comprises 2,096 manually annotated question-answer pairs across 1,603 map documents from nine categories. It is designed to probe a hierarchy of skills, ranging from perception to multi-step visual reasoning. To quantify benchmark properties, a simple yet effective benchmark-level metric is proposed: the Visual Dependency Index (VDI), defined as the accuracy drop when images are replaced with question-agnostic descriptions. OmniMapBench exhibits higher VDI than established benchmarks, which quantitatively validates its focus on irreducible visual reasoning. Comprehensive evaluations of 25 leading LVLMs are conducted on OmniMapBench. A significant performance gap is observed, with the top-performing model achieving only 75.03\% accuracy. This result underscores the challenges posed by OmniMapBench to current LVLMs. This work aims to catalyze progress in visual-centric reasoning for document understanding of LVLMs. The dataset and code are publicly available at https://github.com/SIGMME/OmniMapBench.

cs.CV↗
arXiv2026

MIMFlow: Integrating Masked Image Modeling with Normalizing Flows for End-to-End Image Generation

Normalizing Flows (NFs) are powerful generative models capable of exact density estimation and sampling. However, their strict invertibility often forces the model to exhaust its capacity on low-level pixel details, hindering the capture of high-level semantic structures. While Masked Image Modeling (MIM) has excelled in representation learning, its integration into generative pipelines has remained largely modular and disjointed. In this paper, we propose MIMFlow, a unified end-to-end framework that jointly optimizes latent semantics, pixel reconstruction, and generative flow. By employing a VAE encoder to infer semantic latent from masked images, MIMFlow achieves a principled decoupling of the generative task: the Normalizing Flow focuses on modeling a simplified, low-frequency semantic manifold, while a specialized decoder handles high-frequency synthesis. This design effectively resolves the inherent capacity bottleneck of NFs, allowing the model to prioritize global structural coherence over redundant noise. Empirical results on ImageNet 256$\times$256 show that MIMFlow-L reaches 71.3\% linear probing accuracy and an FID of 2.50. Despite using only 128 tokens (50\% fewer than standard models), it yields a 32.8\% performance gain over similar-scale NF baselines. Our code is available at https://github.com/MCG-NJU/MIMFlow.

cs.CV↗
arXiv2026

From Data Completeness to Data Sufficiency: A Task-Driven Imaging Framework for Intraoperative CBCT under Quality-Time-Dose Trade-offs

Mobile C-arm cone-beam computed tomography (CBCT) has been widely used for real-time intraoperative 3D imaging. However, current practice often mechanically applies the fan-beam CT criterion of "180° plus fan angle" in pursuit of "data completeness" in reconstruction. This review argues that, under the single circular trajectory of three-dimensional cone-beam geometry, complete data are mathematically unattainable; moreover, blindly increasing sampling may exacerbate the trade-off among intraoperative image quality (Q), imaging time (T), and radiation dose (D). Against this background, this review reframes the evaluation of intraoperative CBCT around "data sufficiency" rather than "data completeness." This perspective moves beyond the excessive pursuit of absolute mathematical and analytic accuracy, and instead emphasizes task-specific minimum image-quality thresholds required for clinical decision-making. By synthesizing evidence from multiple clinical scenarios, this review suggests that approximation errors can be acceptable when clinical decision-making requirements are satisfied, thereby achieving a Q-T-D balance.

eess.IV↗
arXiv2026

Unified Audio Intelligence Without Regressing on Text Intelligence

Audio intelligence involves understanding, reasoning about, and generating both audio and speech. In this work, we introduce Nemotron-Labs-Audex-30B-A3B (Audex), a unified audio-text LLM built on Nemotron-Cascade-2-30B-A3B, a strong text-only MoE LLM. Audex adopts a simple unified design with a single Transformer decoder: audio inputs are encoded and projected into the text embedding space, while text tokens and quantized audio output tokens are treated uniformly during generation. This architecture enables strong audio-text fusion, seamless multimodal generation, and compatibility with standard LLM training and inference infrastructure. For training, we meticulously curate audio-text datasets comprising 157.4B audio tokens and 320.5B text tokens. We apply multi-stage supervised training on these datasets, followed by text-only Cascade RL and multi-domain on-policy distillation. Audex delivers state-of-the-art audio understanding, speech recognition and translation, text-to-speech, audio generation, and speech-to-speech generation, while preserving very compelling reasoning, alignment, knowledge, long-context, and agentic capabilities of its text-only LLM backbone with marginal or no regression. We release the model checkpoints to facilitate open research.

cs.CL↗
arXiv2026

Broadband microwave time-frequency analysis via stabilized period-one oscillation and recirculating frequency shifting with shared fiber loop

To address the need for time-frequency analysis (TFA) of broadband microwave signals and to overcome the reliance of existing schemes on large-bandwidth swept microwave sources, we propose a broadband microwave signal TFA approach based on stabilized period-one (P1) oscillation and recirculating frequency shifting (RFS). By employing a feedback loop, a stable swept optical signal is generated from the stabilized P1 oscillation of a semiconductor laser, and its sweep bandwidth is further extended by an RFS loop to achieve multi-fold bandwidth expansion. For system compactness, the feedback loop and RFS loop share a common long fiber. The combined operation produces a broadband swept optical signal, which, through stimulated Brillouin scattering-based frequency-to-time mapping, enables TFA and frequency measurement of broadband microwave signals. Experimental results demonstrate an instantaneous analysis bandwidth of up to 57 GHz, a frequency resolution of 60 MHz, and a maximum mean absolute frequency measurement error of 38.16 MHz.

physics.optics↗
arXiv2026

On the electromagnetic effects of collisionless trapped-electron modes

We present a linear gyrokinetic theory for the electromagnetic collisionless trapped-electron mode (CTEM). It is found that the weak electromagnetic effects of CTEMs originate from the particle dynamics. Theoretical analysis reveals that the kinetic and fluid-like components of the trapped-electron parallel current cancel at leading order. The ion parallel current is also negligible due to the weak ion transit resonance. Consequently, the perturbed parallel current in the electromagnetic CTEM is dominated by passing electrons. We demonstrate that these characteristics of particle dynamics decouple the CTEM from the shear Alfvén wave branch, rendering the electromagnetic effects subdominant. Both eigenmode analyses and gyrokinetic simulations validate these findings.

physics.plasm-ph↗
arXiv2026

Cross-Domain Feature Expansion for Tabular Medical Data via Knowledge Graphs Injection

Acquiring comprehensive cross-domain biomedical profiles is often costly and time-consuming, resulting in severe data scarcity in medical research. To address this challenge, we propose MedKGTab, a knowledge-injected framework specifically engineered for cross-domain feature expansion in tabular medical data. MedKGTab seeks to infer uncollected biomedical features from available ones by exploiting their inherent statistical dependencies and established medical correlations. By employing a row-column dual-attention mechanism, MedKGTab operates directly on raw structured tabular data, inherently capturing exact numerical distributions without the structural loss caused by tokenization. Crucially, MedKGTab integrates data-driven statistical priors with the SPOKE biomedical knowledge graph, achieving an optimal synergy between the data and knowledge channels. Within this synergy, the representations derived from the data channel are modulated by the injected biomedical knowledge, ensuring the final generated data are grounded in empirical medical research. Experimental results demonstrate that MedKGTab achieves high data fidelity and realistic data representation in cross-domain feature expansion. It outperforms both SOTA medical large models (e.g., Baichuan M3-plus) and specialized tabular models designed for medical data generation. Furthermore, MedKGTab consistently delivers superior performance across various data generation scenarios, whether inferring missing features within the same dataset or generalizing across different medical cohorts.

cs.AI↗
arXiv2026

Bolometric correction for cosmologically redshifted stars with dust: an update to the YBC database

Observations from HST & JWST continue to reveal gravitationally magnified high-redshift star candidates, resulting in increasing demand for accurate stellar bolometric corrections to compare stellar models with observational data. We update YBC stellar bolometric correction database by incorporating bolometric corrections for cosmologically redshifted stars, called zYBC. The bolometric corrections are derived by redshifting stellar spectra from libraries, attenuated by extinction curves for both the dust in the host galaxy and the Milky Way, and followed by convolution with the transmission curves of photometric filters. Our methodology incorporates the effects due to the cosmological K-correction and the dust. Besides the spectral libraries in earlier YBC, we add NLTE-based spectral libraries for O, B stars, which are better suited for hot massive stars, particularly wind-included PoWR and CMFGEN models. The database supports key photometric systems for high-redshift studies, such as HST/WFC3, JWST/NIRCam, and CSST's MSC and MCI, and maintains the flexibility to incorporate additional photometric systems upon request. As examples, we present colors as functions of Teff at various redshifts for several photometric systems, which exhibit non-monotonic behaviors and demonstrate the necessity for a dedicated modelling. In particular, we find that the relations show larger dispersions at high redshift than the zero redshift case. This indicates that the stellar parameters of high redshift stars can be better determined than those of their local counterparts, given their redshifts reliably determined through other methods and their photometric data are of high enough quality for physical parameter determination through spectral-fitting. We also show the difference in the effect brought by the different amount of extinctions. zYBC represents a valuable resource for high-redshift star research.

astro-ph.SR↗
arXiv2026

Exponential-Family Tensor Completion via Nonconvex Dual Total-Variation Regularization

With the emergence of various tensor data, tensor completion from partial measurements has attracted widespread attention in data science and signal processing. Total Variation (TV) has been widely used as an effective regularization technique for tensor completion; however, theoretical studies on TV regularization in this context remain limited. In this work, we present a rigorous theoretical analysis of TV regularization for tensor completion. Specifically, we consider tensor completion under exponential-family noise, which generalizes the standard settings such as Gaussian and Poisson tensor completion. To handle exponential-family tensor completion, we propose a family of dual-TV (DTV) regularizers based on the transformed L1 function, which simultaneously capture sparsity and low-rank structures in the gradient tensor. Moreover, we establish the theoretical upper bounds on the recovery error of the proposed estimator. In certain cases, these upper bounds can attain the convergence order of $\mathcal{O}\big( n_3 r_t\big(\max_{k} s_k^2\big) \log\big((n_1+n_2)n_3\big) /n \big)$, and the minimax lower bound analysis is further presented to show that the upper-bounds can approach the lower bound with the gap of order $\mathcal{O}(\max_k s_k^2/max(n_1, n_2))$ up to a logarithmic factor. Finally, multiple groups of experiments on synthetic, image and video tensor data sets are conducted to support our theoretical results and demonstrate the effectiveness of our method.

stat.ME↗
arXiv2026

A pulsar escaping an ancient open cluster via tidal stripping

Open clusters are the primary birthplaces of stars in the Milky Way disk, yet their neutron star progeny are rarely found within them, presumably due to supernova-induced kicks that eject them at birth. Here we report the arcsec-level localization of the pulsar PSR J1921+3745 to the tidal tail of NGC 6791, one of the oldest and most massive open clusters. Our N-body simulation shows that more than 95% of neutron stars formed in such clusters have been ejected. This pulsar's location in the tidal tail indicates it was retained for billions of years before being stripped by Galactic tides. This long-term retention requires low natal kicks, consistent with formation via electron-capture supernova. Our findings capture a rare snapshot of a neutron star transitioning into the Galactic field, identifying tidal stripping of ancient clusters as a verified source of the Galactic neutron star population.

astro-ph.HE↗
arXiv2026

An ACA map of a molecular cloud interacting with supernova remnant W28

Supernova remnants (SNRs) strongly influence the physical and chemical properties of the molecular clouds (MCs) with which they interact. We carried out a high-resolution observation toward W28F, a chemically rich MC interacting with SNR W28, with the Atacama Compact Array (ACA) in Band 7. Significant emission (> 10 sigma) of CO, CH3OH, p-H2CO, SiO and SO is detected. We reveal the clumpy structures of the shocked MC, with different spatial distributions between CH3OH and SiO. We select six molecular clumps to conduct spectral decomposition and non-local-thermodynamic-equilibrium analysis with the CH3OH and p-H2CO lines. The best-fit results show a H2 density of nH2 ~ (1-3) * 10^5 cm^-3 and a gas temperature of Tgas ~ 50-170 K in most of the fitted components. The H2 density and gas temperature show a clear anti-correlation across different regions, with the thermal pressure consistent with that of the adjacent X-ray-emitting hot plasma. This is consistent with the picture that the SNR shocks propagate into multi-phase gas, with a pressure balance existing between different phases. We propose that the high abundance ratio between E-CH3OHand A-CH3OH (> 0.9) suggests extra gas-phase processes to enhance this ratio, such as proton exchange with H3+ and HCO+. The chemical segregation between CH3OH and SiO, in both the spatial and spectral regime, can be explained by the fact that CH3OH traces slow shocks while SiO traces fast shocks.

astro-ph.GA↗
arXiv2026

Unlocking Model Potentials Through Adaptive Multi-Agent Scaffolding for Efficient Issue Resolution

Resolving issues with ambiguous and incomplete descriptions, particularly concerning complex bugs, requires a sophisticated, long-horizon workflow. Agents must navigate codebases to locate the root cause, reproduce the failure, implement a fix, and validate the resulting patch. Inefficient context management, thereby, can lead to rapid context degradation and context poisoning, preventing successful resolution. We propose icat-agent, a decentralized, multi-agent scaffolding that replaces shared context with synchronous, event-based message passing. Utilizing a rubric-based issue quality check, icat-agent strategically pivots its workflow: it initiates parallel patching and validation for well-defined issues, while deploying preliminary exploration for low-quality ones. A comprehensive evaluation of icat-agent on SWE-bench Verified and SWE-bench Pro demonstrates that it consistently outperforms prominent baselines across all difficulty levels, including SWE-agent, mini-SWE-agent, and Claude Code, while using the same underlying models, improving by 3.6-8.4% on SWE-bench Verified and 6.3-18.5% on SWE-bench Pro. icat-agent is also computationally efficient, reducing the average cost by $1.18 per instance compared with the multi-agent Claude Code baseline. Our findings reveal that a robust scaffold such as icat-agent unlocks substantial latent capability within a fixed model, with the same backbone resolving markedly more issues under icat-agent than under existing scaffolds. icat-agent +GPT-5.4-xhigh resolves 67.4% of SWE-bench Pro problems, outperforming the current best result on SWE-bench Pro (59.10%, mini-SWE-agent+GPT-5.4-xhigh) by 8.3 percentage points.

cs.SE↗
arXiv2026

A coherent structure transport model for scrape-off layer turbulence

Understanding the locality of high-temperature plasma energy deposition on material surfaces in fusion reactors is critical for design. Here, we utilize the Gyrokinetic ElectroMagnetic turbulence including X-points (GEMX) simulation, together with SOLPS-ITER solutions for the background equilibrium electric field including drifts, to model the heat flux at the divertor plate and characterize the heat load width using realistic X-point geometry. We use a theory-based blobby transport model called the "Coherent Structure Transport" (CST) model to include the effect of plasma transport in the edge scrape-off layer. The CST model is extremely fast and can be used to quickly analyze any SOLPS-ITER solution. SOLPS-ITER provides the steady state, or equilibrium on which we superimpose blobby turbulence characterized by blob size, amplitude and frequency. We obtain the $1/B_p$ scaling of the heat load exponential decay width $λ_q$, in agreement with the Eich empirical scaling and with the Goldston heuristic theory. When including blobby turbulence in combination with the SOLPS-ITER electric field, we find a secondary peak in the heat flux radial profile, outwardly displaced from the strike point radius, with a relative amplitude that increases with the initial blob density. We describe the CST model in detail and provide initial investigations of the scaling of $λ_q$ and the secondary heat flux peak with blob size and amplitude.

physics.plasm-ph↗
arXiv2026

C^2GR: Coupled Comprehensive Generative Replay for a Continually Learnable Universal Segmentation Model

Universal segmentation models exhibit significant potential for diverse tasks involving different imaging modalities and segmentation objectives. Task-Incremental Learning provides a privacy-preserving approach to continually evolve a universal model on tasks from sequentially-arriving medical departments. However, training the model solely on the incoming task induces forgetting on past tasks, since consecutive tasks exhibit concurrent shifts in image appearance and segmentation objective. To address this problem, we propose a novel Coupled Comprehensive Generative Replay (C^2GR) framework that simultaneously synthesizes image-mask pairs of previous tasks to mitigate forgetting under concurrent appearance and objective shifts. This requires preserving image-mask correspondence for structure-realistic generation and bridging asynchronous optimization of the generator and segmentor for segmentation-oriented generation. Specifically, we propose a Bayesian Joint Diffusion (BJD) method that formulates the correspondence as conditional distributions optimized via conditional denoising. Furthermore, we develop a Relation-aware Unified Prompt Synchronization (RUPS) scheme to simultaneously modulate the generator and segmentor via a shared task-relation-aware prompt for synchronizing their optimization. Experiments on 20 tasks spanning diverse modalities and objectives demonstrate that C^2GR exhibits only a 2.44% drop in overall performance compared to joint training with all task data, effectively alleviating forgetting from the concurrent shifts. Our code will be made publicly available at https://github.com/mar-cry/C2GR.

cs.CV↗