Searcharxiv⌕ Search

arXiv subjects

Tao Xia

Publications and source records attributed to Tao Xia.

10 recordsLinked to original sources
arXiv2026

Cura 1T: Specialized Model for Agentic Healthcare

Healthcare AI agents handle patient consultation, clinical reasoning over text and images, interactive diagnosis, and electronic health record (EHR) tool use, yet specialized agentic models that cover these use cases together remain limited. These capabilities fail in different ways, and a narrow update for one task can degrade another. We present Cura 1T, a healthcare-specialized LLM built on the open-weight Kimi-K2.6 and trained through a human-gated recursive self-improvement (RSI) loop. Specifically, in each round, the RSI harness plans a target capability, trains the model, evaluates benchmark trajectories, and refines the data mixture from observed failures with targeted synthetic and curated examples rather than a single generic medical-data update. Across the healthcare evaluation suite, Cura 1T ranks at or near the top among frontier baselines while remaining competitive on out-of-domain reasoning and agentic benchmarks.

cs.AI↗
arXiv2026

CHI-Bench: Can AI Agents Automate End-to-End, Long-Horizon, Policy-Rich Healthcare Workflows?

End-to-end automation of realistic healthcare operations stresses three capabilities underrepresented in current benchmarks: policy density, decisions must be grounded in a large library of medical, insurance, and operational rules; Multi-role composition: a single task requires the agent to play multiple roles with handoffs; and multilateral interaction: intermediate workflow steps are multi-turn dialogs, such as peer-to-peer review and patient outreach. We introduce $\chi$-Bench, a benchmark of long-horizon healthcare workflows across three domains: provider prior authorization, payer utilization management, and care management. Each task hands the agent a clinical case in a high-fidelity simulator of 20 healthcare apps exposed via 87 MCP tools, which it must drive to a terminal status through tool calls and writing the role's artifacts, guided by a 1,290+ document managed-care operations handbook skill. Across 30 agent harness/models configurations, the best agent resolves only 28.0% of tasks, no agent clears 20% on strict pass^3, and executing all tasks in a single session slumps the performance to 3.8%. These results raise the hypothesis that similar gaps are likely to surface in other policy-dense, role-composed, irreversible enterprise domains.

cs.CL↗
arXiv2026

Rethinking Structure Preservation in Text-Guided Image Editing with Visual Autoregressive Models

Visual autoregressive (VAR) models have recently emerged as a promising family of generative models, enabling a wide range of downstream vision tasks such as text-guided image editing. By shifting the editing paradigm from noise manipulation in diffusion-based methods to token-level operations, VAR-based approaches achieve better background preservation and significantly faster inference. However, existing VAR-based editing methods still face two key challenges: accurately localizing editable tokens and maintaining structural consistency in the edited results. In this work, we propose a novel text-guided image editing framework rooted in an analysis of intermediate feature distributions within VAR models. First, we introduce a coarse-to-fine token localization strategy that can refine editable regions, balancing editing fidelity and background preservation. Second, we analyze the intermediate representations of VAR models and identify structure-related features, by which we design a simple yet effective feature injection mechanism to enhance structural consistency between the edited and source images. Third, we develop a reinforcement learning-based adaptive feature injection scheme that automatically learns scale- and layer-specific injection ratios to jointly optimize editing fidelity and structure preservation. Extensive experiments demonstrate that our method achieves superior structural consistency and editing quality compared with state-of-the-art approaches, across both local and global editing scenarios.

cs.CV↗
arXiv2026

Giant Magnetocrystalline Anisotropy in Honeycomb Iridate NiIrO3 with Large Coercive Field Exceeding 17 T

The realization of unconventional quantum phases in frustrated and spin-orbit coupled materials remains at the forefront of quantum materials research. Here we report the synthesis and discovery of NiIrO3, the first honeycomb iridate with coupled 3d-5d magnetic sublattices, through a soft topotactic reaction. Structural analysis reveals an ilmenite-type stacking of edge-sharing NiO6 and IrO6 octahedral honeycomb sublattices in a Kitaev geometry. Comprehensive magnetic and electrical transport measurements unveil its long-range ferrimagnetic order below 213 K, which is in sharp contrast to the predominantly antiferromagnetic order in the known honeycomb iridates. Notably, the titled compound displays an exceptionally large magnetocrystalline anisotropy energy of 32.2 meV/f.u. and a giant coercivity with coercive field exceeding 17.3 T below 4.2 K, both ranking among the highest observed in iridates to date. Combined experimental and theoretical investigations indicate that the exceptional anisotropy and coercivity originate from the synergistic effect between strong lattice frustration in the coupled 3d-5d honeycomb lattice network and the robust spin-orbit coupling of the Ir4+ (Jeff = 1/2) state. This work positions NiIrO3 as a promising platform to investigate low-dimensional and frustrated quantum spin systems, and highlights its potential for spintronic applications through the targeted engineering of 3d-5d interactions.

cond-mat.str-el↗
arXiv2025

Consistent Image Layout Editing with Diffusion Models

Despite the great success of large-scale text-to-image diffusion models in image generation and image editing, existing methods still struggle to edit the layout of real images. Although a few works have been proposed to tackle this problem, they either fail to adjust the layout of images, or have difficulty in preserving visual appearance of objects after the layout adjustment. To bridge this gap, this paper proposes a novel image layout editing method that can not only re-arrange a real image to a specified layout, but also can ensure the visual appearance of the objects consistent with their appearance before editing. Concretely, the proposed method consists of two key components. Firstly, a multi-concept learning scheme is used to learn the concepts of different objects from a single image, which is crucial for keeping visual consistency in the layout editing. Secondly, it leverages the semantic consistency within intermediate features of diffusion models to project the appearance information of objects to the desired regions directly. Besides, a novel initialization noise design is adopted to facilitate the process of re-arranging the layout. Extensive experiments demonstrate that the proposed method outperforms previous works in both layout alignment and visual consistency for the task of image layout editing

cs.CV↗
arXiv2022

Mass spectra of neutral mesons $K_0,\ π_0,\ η,\ η'$ at finite magnetic field, temperature and baryon chemical potential

The mass spectra of neutral mesons $K_0, π_0, η, η'$ on temperature-quark chemical potential $(T-μ)$ plane in the presence of a constant magnetic field is investigated in the $SU(3)$ NJL model. As a Goldstone boson of chiral symmetry breaking, the mass of $K_0$ meson increases with temperature and/or quark chemical potential, and we observe two kinds of mass jumps of $K_0$ meson in media, which is induced by the mass jump of constituent quarks and the magnetic field, respectively. Due to the breaking of isospin symmetry between $u$ and $d$ quarks in magnetic fields, the mixing of $π_0-η- η'$ mesons occurs and this leads to rich structures of their mass spectra. For instance, $π_0$ mass is influenced by the strange quark. There appear the change of increase ratio of $π_0$ mass at high $μ$ and vanishing $T$ and the $π_0$ mass jump crossing over the threshold of two times of strange quark mass at finite $T$ and $μ$. The mass ordering of $π_0, \ η,\ η'$ mesons varies in media, due to their mass jumps, which are induced by the mass jump of constituent quarks or the magnetic field.

hep-ph↗
arXiv2015

Topological Susceptibility in Three-Flavor Quark Meson Model at Finite Temperature

We study $U_A(1)$ symmetry and its relation to chiral symmetry at finite temperature through the application of functional renormalization group to the $SU(3)$ quark meson model. Very different from the mass gap and mixing angel between $η$ and $η'$ mesons which are defined at mean field level and behavior like the chiral condensates, the topological susceptibility includes a fluctuations induced part which becomes dominant at high temperature. As a result, the $U_A(1)$ symmetry is still considerably broken in the chiral symmetry restoration phase.

hep-ph↗
arXiv2013

Three-flavor Nambu--Jona-Lasinio model at finite isospin chemical potential

QCD at finite isospin chemical potential $μ_{\text I}$ possesses a positively definite fermion determinant and the lattice simulation can be successfully performed. While the two-flavor effective models may be sufficient to describe the phenomenon of pion condensation, it is interesting to study the roles of the strangeness degree of freedom and the U$_{\rm A}(1)$ anomaly. In this paper, we present a systematic study of the three-flavor Nambu--Jona-Lasinio model with a Kobayashi-Maskawa-'t Hooft (KMT) term that mimics the U$_{\rm A}(1)$ anomaly at finite isospin chemical potential. In the mean-field approximation, the model predicts a phase transition from the vacuum to the pion superfluid phase, which takes place at $μ_{\rm I}$ equal to the pion mass $m_π$. Due to the U$_{\rm A}(1)$ anomaly, the strangeness degree of freedom couples to the light quark degrees of freedom and the strange quark effective mass depends on the pion condensate. However, the strange quark condensate and the strange quark effective mass change slightly in the pion superfluid phase, which verifies the validity of the two-flavor models. The effective four-fermion interaction of the Kobayashi-Maskawa-'t Hooft term in the presence of the pion condensation is constructed. Due to the U$_{\rm A}(1)$ anomaly, the pion condensation generally induces scalar-pseudoscalar interaction. The Bethe-Salpeter equation for the mesonic excitations is established and the meson mass spectra are obtained at finite isospin chemical potential and temperature. Finally, the general expression for the topological susceptibility $χ$ at finite isospin chemical potential $μ_{\rm I}$ is derived. In contrast to the finite temperature effect which suppresses $χ$, the isospin density effect leads to an enhancement of $χ$.

hep-ph↗
arXiv2011

Meson Screening Mass in a Strongly Coupled Pion Superfluid

We calculate the meson screening mass in a pion superfluid in the framework of Nambu--Jona-Lasinio model. The minimum of the attractive quark potential is always located at the phase boundary of pion superfluid. Different from the temperature and baryon density effect, the potential at finite isospin density can not be efficiently suppressed and the matter is always in a strongly coupled phase due to the Goldstone mode in the pion superfluid.

hep-ph↗