Searcharxiv⌕ Search

arXiv subjects

Yi Yang

Publications and source records attributed to Yi Yang.

At least 199 records · Page 11Linked to original sources
arXiv2026

Towards Next-Generation Healthcare: A Survey of Medical Embodied AI for Perception, Decision-Making, and Action

Foundation models have demonstrated impressive performance in enhancing healthcare efficiency across a wide range of medical applications. Nevertheless, their limited ability to perceive, understand, and interact with the physical world significantly constrains their effectiveness in real-world clinical workflows, where safety-critical decision-making and physical execution are tightly coupled. Recently, embodied artificial intelligence (AI) has emerged as a promising physical-interactive paradigm for intelligent healthcare, enabling agents to operate in complex medical environments. As research in this area rapidly expands, understanding how intelligent agents function as integrated, end-to-end systems in clinical environments becomes increasingly critical. However, existing surveys on medical embodied AI largely emphasize individual aspects or functional components, lacking a unified system-level organization of the field. To support and consolidate recent advances, we systematically survey the core components of medical embodied AI, with a particular emphasis on the coordinated integration of perception, decision-making, and action. We further review representative medical applications and relevant datasets, and we analyze the major challenges encountered in real-world clinical practice. Finally, we discuss key directions for future research in this rapidly evolving field. The associated project can be found at https://github.com/VMVLab/Medical_Embodied_AI_Paper_List.

cs.AI↗
arXiv2026

Enhancement of the Rate of Tidal Disruption Events in Active Galactic Nuclei due to the Sweeping Secular Resonance Mechanism

Tidal disruption event (TDE) rates in active galactic nuclei (AGN) consistently exceed predictions from two-body relaxation, particularly in post-starburst and green valley galaxies. We explain this excess with a new mechanism: a sweeping secular resonance (SSR) driven by an intermediate-mass companion (IMC) and a depleting gaseous disk. As the disk mass declines, a resonance between stellar and IMC orbital precession sweeps through the nuclear cluster, exciting stellar eccentricities to near unity on orbital timescales far faster than gravitational relaxation. Our analytical framework, validated by N-body simulations (REBOUND), shows this mechanism requires IMC-to-SMBH mass ratios of $q \geq 10^{-3}$, disk mass ratio $p \geq 10^{-3}$, and few Myr-scale disk depletion. It is highly effective for co-orbiting IMCs but negligible for counter-orbiting ones. The TDE rate peaks at $10^{-3}-10^{-2}$ per galaxy per year for a depletion timescale $τ_{\rm dep} \sim 10$ Myr. Even lower-mass IMCs can produce significant enhancements with compact, long-lived disks. Our model naturally explains elevated AGN TDE rates and implies that a high TDE incidence is a potential tracer of hidden parsec-scale IMCs, offering testable predictions for future AGN monitoring.

astro-ph.GA↗
arXiv2026

Structural Diversity Drives Disruptive Scientific Innovation

Scientific innovation increasingly depends on collaboration, yet the organizational structure that fosters breakthrough ideas remains poorly understood. Existing metrics - such as team size or compositional diversity - capture readily observable characteristics but not the deeper architecture of collaboration. We introduce Structural Diversity (SD): the extent to which a team bridges multiple distinct knowledge communities within its prior collaboration network. Using a century-scale dataset of 260 million scientific publications (1900-2025) and combining causal inference with a quasi-natural experiment based on a U.S. National Science Foundation policy change in 2012, we show that SD is a powerful and robust predictor of disruptive innovation, outperforming traditional team novelty indicators such as team freshness and edge density. Moreover, SD positively interacts with team size and is able to mitigate the well-known "curse of scale" by transforming scale from a liability into a resource for creative synthesis. We find that one mechanism underlying this effect is Disciplinary Integration (DI): teams with higher SD can more effectively combine heterogeneous knowledge into novel configurations. Our findings position SD as both a new theoretical construct and an actionable design principle for organizing scientific collaboration. By linking the architecture of team assembly to the dynamics of creative discovery, our work offers a structural explanation for how collective intelligence can be systematically engineered to foster disruptive innovation.

cs.SI↗
arXiv2026

A Yang-Mills Type Gauge Theory of Gravity and the Dark Matter Problem

A Yang-Mills type gauge theory of gravity is shown to have a structure richer than that of Einstein's General Theory of Relativity. By elevating the full connections to independent dynamical gauge fields, the theory admits non-trivial vacuum configurations driven by gauge field self-interactions. We demonstrate that this non-linear geometric structure naturally yields an effective spacetime that explains the form of the galactic rotation curves and the anomalous amount of intergalactic gravitational lensing, completely circumventing the need for exotic dark matter particles.

physics.gen-ph↗
arXiv2026

Cosmological Evolution in the $GL(4,\mathbb{R})$ Yang-Mills Theory of Gravity: Resolving the JWST Early Galaxy Crisis and Late-Time Acceleration

We investigate the cosmological implications of the $GL(4,\mathbb{R})$ Yang-Mills gauge theory of gravity. A long-standing theoretical challenge in standard cosmology is the reliance on ad hoc rolling scalar fields (e.g., the inflaton or quintessence) to drive early-time inflation and late-time acceleration, despite their unknown particle physics origins. In this work, by treating the affine connection as a gauge field and the world metric as a non-dynamical background, we derive an exact expansion history that strictly eliminates the need for any rolling scalar fields or a cosmological constant. The dynamics are governed solely by the Yang-Mills field strength squared. We demonstrate that the early Universe exhibits a singularity-free coasting expansion $a(t) \propto t$, resolving the JWST high-redshift galaxy crisis by granting significantly more time for early structure formation. As radiation dilutes, the Universe naturally transitions into a Weitzenböck vacuum state, where a residual, topologically non-trivial constant torsion locks the spacetime kinematics to drive a late-time exponential acceleration $a(t) \propto \exp(ξt)$. This framework establishes a purely geometric and gauge-theoretic origin for the cosmological evolution.

physics.gen-ph↗
arXiv2026

Observation of Floquet erratic non-Hermitian skin effect in photonic mesh lattice

In ordered, translationally invariant non-Hermitian systems, the skin effect is understood as a boundary phenomenon: nonreciprocal hopping drives an extensive accumulation of eigenstates towards the edges, whereas the periodic-boundary spectrum remains Bloch extended. Here we experimentally reveal the opposite limit -- a disorder-enabled, boundary-independent, and intrinsically bulk form of skin localization -- the recently predicted erratic non-Hermitian skin effect (ENHSE), realized in a driven photonic platform. Using a time-multiplexed photonic mesh lattice with programmable gain, loss, and phase modulation, we engineer spatially fluctuating imaginary gauge fields and realize a Floquet non-Hermitian lattice whose global reciprocity can be tuned independently of strong local nonreciprocity. We observe a disorder-driven non-Hermitian topological transition between two oppositely directed disordered skin phases through a critical point of global reciprocity. At this transition, boundary skin accumulation disappears, yet the wave dynamics self-organizes into bulk-localized patterns without any interface, providing direct evidence of ENHSE. The measured localization profiles agree with simulations and exhibit the defining feature that distinct eigenstates share a common bulk-localized envelope determined by the disordered imaginary gauge fields. By further introducing controllable on-site disorder, we reveal the competition between ENHSE and Anderson localization, and show how increasing scattering progressively suppresses erratic skin dynamics. Our results help establish ENHSE as a unique disorder-induced non-Hermitian phenomenon and open a route to engineering localization, transport, and topology beyond conventional Bloch and boundary-based paradigms.

physics.optics↗
arXiv2026

LogiStory: A Logic-Aware Framework for Multi-Image Story Visualization

Generating coherent and communicative visual sequences, such as image sequences and videos, remains a significant challenge for current multimodal systems. Despite advances in visual quality and the integration of world knowledge, existing models still struggle to maintain logical flow, often resulting in disjointed actions, fragmented narratives, and unclear storylines. We attribute these issues to the lack of attention to visual logic, a critical yet underexplored dimension of visual sequence generation that we define as the perceptual and causal coherence among characters, actions, and scenes over time. To bridge this gap, we propose a logic-aware multi-image story visualization framework, LogiStory. The framework is built around the central innovation of explicitly modeling visual logic in story visualization. To realize this idea, we design a multi-agent system that grounds roles, extracts causal chains, and verifies story-level consistency, transforming narrative coherence from an implicit byproduct of image generation into an explicit modeling objective. This design effectively bridges structured story planning with visual generation, enhancing both narrative clarity and visual quality in story visualization. Furthermore, to evaluate the generation capacity, we construct LogicTale, a benchmark comprising richly annotated stories, emphasizing causal reasoning, and visual logic interpretability. We establish comprehensive automatic and human evaluation protocols designed to measure both visual logic and perceptual quality. Experiments demonstrate that our approach significantly improves the narrative logic of generated visual stories. This work provides a foundational step towards modeling and enforcing visual logic in general image sequence and video generation tasks.

cs.CV↗
arXiv2026

Echoes of ownership: Adversarial-guided dual injection for copyright protection in MLLMs

With the rapid deployment of multimodal large language models (MLLMs), disputes regarding model ownership have become increasingly frequent, raising significant concerns about intellectual property protection. In this paper, we propose a framework for generating copyright triggers for MLLMs, enabling model publishers to embed verifiable ownership information into the model. The goal is to construct trigger images that elicit ownership-related textual responses exclusively in fine-tuned derivatives, while remaining inert in other non-derivative models. Our method constructs a tracking trigger image by treating the image as a learnable tensor, performing adversarial optimization with dual-injection of ownership-relevant semantic information. The first injection is achieved by enforcing textual consistency between the output of an auxiliary MLLM and a predefined ownership-relevant target text; the consistency loss is backpropagated to inject this ownership-related information into the image. The second injection is performed at the semantic-level by minimizing the distance between the CLIP features of the image and those of the target text. Furthermore, we introduce an additional adversarial training stage involving the auxiliary model. It is specifically trained to resist generating ownership-relevant target text, thereby enhancing robustness in heavily fine-tuned derivative models. Extensive experiments demonstrate the effectiveness of our dual-injection approach in tracking model lineage under various fine-tuning and domain-shift scenarios. Code is at https://github.com/kunzhan/AGDI

cs.CV↗
arXiv2026

Robust Predictive Modeling Under Unseen Data Distribution Shifts: A Methodological Commentary

Most research designing novel predictive models, or employing existing ones, assumes that training and testing data are independent and identically distributed. In practice, the data encountered at serving time often deviate from the training distribution, leading to substantial performance degradation and potential design validity and/or biased measurement issues. This challenge is further complicated by the fact that the serving time data are frequently unavailable during model development. This method commentary raises awareness of this overlooked issue through a real-world customer churn example and reviews the growing literature on domain generalization, a subfield of transfer learning that explicitly addresses situations in which the target domain is unseen during training. We further argue for adopting an uncertainty-aware predictive modeling mindset and illustrate how this perspective can be operationalized through the distributionally robust optimization framework. Finally, we offer several practical recommendations to enhance the robustness of predictive modeling under unseen data distribution shifts.

cs.LG↗
arXiv2026

Universal Geometric Scaling in Cosmic Ray Spallation: Evidence of a Dynamical Causal Horizon from AMS-02

The interpretation of high-precision cosmic ray spectra is fundamentally bottlenecked by uncertainties in fragmentation cross-sections. Traditional kinematic models, driven by phase-space expansions, typically predict complex, energy-dependent evolutions. However, AMS-02 measurements reveal that at high rigidities ($R > 30$~GV), secondary-to-secondary flux ratios (Li/B, Be/B, and Li/Be) strictly converge to energy-independent plateaus. To understand this anomaly, we explore a macroscopic geometric framework. The ultra-relativistic spallation of a target nucleus snaps residual strong-interaction flux tubes, inducing an extreme deceleration on the remnant. Using a semi-microscopic estimation based on the Woods-Saxon potential and pion exchange, we suggest this dynamically generates a causal horizon with an effective Unruh temperature $T_U \approx 5.6-5.8$~MeV. Utilizing the Be/B ratio as an absolute calibration channel, we extract an asymptotic scale of $6.08$~MeV, remarkably consistent with our theoretical estimation and the established nuclear liquid-gas phase transition limit. Subsequent blind tests on Lithium ratios demonstrate a universal zero-slope convergence, providing compelling evidence that a constant geometric thermal bath effectively supersedes complex microscopic kinematics at high energies.

hep-ph↗
arXiv2026

FilterGS: Traversal-Free Parallel Filtering and Adaptive Shrinking for Large-Scale LoD 3D Gaussian Splatting

3D Gaussian Splatting has revolutionized neural rendering with real-time performance. However, scaling this approach to large scenes using Level-of-Detail methods faces critical challenges: inefficient serial traversal consuming over 60\% of rendering time, and redundant Gaussian-tile pairs that incur unnecessary processing overhead. To address these limitations, we introduce FilterGS, featuring a parallel filtering mechanism with two complementary filters that select Gaussian elements efficiently without tree traversal. Additionally, we propose a novel GTC metric that quantifies the redundancy of Gaussian-tile key-value pairs. Based on this metric, we introduce a scene-adaptive Gaussian shrinking strategy that effectively reduces redundant pairs. Extensive experiments demonstrate that FilterGS achieves state-of-the-art rendering speeds while maintaining competitive visual quality across multiple large-scale datasets. Project page: https://github.com/xenon-w/FilterGS

cs.CV↗
arXiv2026

Lumos-1: On Autoregressive Video Generation with Discrete Diffusion from a Unified Model Perspective

Autoregressive large language models (LLMs) have unified a vast range of language tasks, inspiring preliminary efforts in autoregressive (AR) video generation. Existing AR video generators either diverge from standard LLM architectures, depend on bulky external text encoders, or incur prohibitive latency due to next-token decoding. In this paper, we introduce Lumos-1, an LLM-based unified model for AR video generation with efficient discrete diffusion. Firstly, to fit videos with LLMs, we identify that 1D RoPE is ill-suited for visual spatiotemporal correlation modeling, and while demonstrated to be useful, naive 3D RoPE exhibits imbalanced frequency spectra. Therefore, we propose MM-RoPE, which preserves the original textual RoPE while seamlessly accommodating video data with comprehensive frequency spectra and scaled 3D positions. Secondly, to fit the video data's nature and overcome the inefficiency of next-token decoding, we adopt a parallel and mask-based discrete diffusion with the intra-frame bidirectional and inter-frame causal attention masks. Based on this attention mask, we uncover the frame-wise loss imbalance issue caused by spatial information redundancy and propose Autoregressive Discrete Diffusion Forcing, which introduces temporal tube masking during training with a compatible inference-time masking policy to avoid quality degradation. Despite using only 48 GPUs for pre-training and fine-tuning, limited data and a discrete tokenizer, Lumos-1 achieves results surpassing those of Show-o2 on GenEval, COSMOS-Video2World on VBench-I2V, and OpenSoraPlan on VBench-T2V. Code and models are available at https://github.com/alibaba-damo-academy/Lumos.

cs.CV↗
arXiv2026

Let's Reward Step-by-Step: Step-Aware Contrastive Alignment for Vision-Language Navigation in Continuous Environments

Vision-Language Navigation in Continuous Environments (VLN-CE) requires agents to learn complex reasoning from long-horizon human interactions. While Multi-modal Large Language Models (MLLMs) have driven recent progress, current training paradigms struggle to balance generalization capability, error recovery and training stability. Specifically, (i) policies derived from SFT suffer from compounding errors, struggling to recover from out-of-distribution states, and (ii) Reinforcement Fine-Tuning (RFT) methods e.g. GRPO are bottlenecked by sparse outcome rewards. Their binary feedback fails to assign credit to individual steps, leading to gradient signal collapse in failure dominant batches. To address these challenges, we introduce Step-Aware Contrastive Alignment (SACA), a framework designed to extract dense supervision from imperfect trajectories. At its core, the Perception-Grounded Step-Aware auditor evaluates progress step-by-step, disentangling failed trajectories into valid prefixes and exact divergence points. Leveraging these signals, Scenario-Conditioned Group Construction mechanism dynamically routes batches to specialized resampling and optimization strategies. Extensive experiments on VLN-CE benchmarks demonstrate that SACA achieves state-of-the-art performance.

cs.RO↗
arXiv2026

Ready2Unlearn: A Learning-Time Approach for Preparing Models with Future Unlearning Readiness

Machine unlearning is the process of removing the imprint left by specific data samples during the training of a machine learning model. AI developers, including those building personalized technologies, employ machine unlearning for various purposes such as privacy protection, security, and to address ethical concerns. This paper introduces Ready2Unlearn, a learning-time optimization approach designed to facilitate future unlearning processes. Unlike the majority of existing unlearning efforts that focus on designing unlearning algorithms, which are typically implemented reactively when an unlearning request is made during the model deployment phase, Ready2Unlearn shifts the focus to the training phase, adopting a "forward-looking" perspective. Building upon well-established meta-learning principles, Ready2Unlearn proactively trains machine learning models with unlearning readiness, such that they are well prepared and can handle future unlearning requests in a more efficient and principled manner. Ready2Unlearn is model-agnostic and compatible with any gradient ascent-based machine unlearning algorithms. We evaluate the method on both language and vision tasks under various unlearning settings, including class-wise unlearning and random data unlearning. Experimental results show that by incorporating such preparedness at training time, Ready2Unlearn produces an unlearning-ready model state, which offers several key advantages when future unlearning is requested. We hope this study inspires future research on proactive strategies for equipping machine learning models with built-in unlearning readiness, particularly in modern information systems that rely heavily on user data for recommendation, search, and personalized services, where privacy risks and data deletion demands are increasingly prevalent.

cs.LG↗
arXiv2026

Fairness May Backfire: When Leveling-Down Occurs in Fair Machine Learning

As machine learning (ML) systems increasingly shape access to credit, jobs, and other opportunities, the fairness of algorithmic decisions has become a central concern. Yet it remains unclear when enforcing fairness constraints in these systems genuinely improves outcomes for affected groups or instead leads to "leveling down," making one or both groups worse off. We address this question in a unified, population-level (Bayes) framework for binary classification under prevalent group fairness notions. Our Bayes approach is distribution-free and algorithm-agnostic, isolating the intrinsic effect of fairness requirements from finite-sample noise and from training and intervention specifics. We analyze two deployment regimes for ML classifiers under common legal and governance constraints: attribute-aware decision-making (sensitive attributes available at decision time) and attribute-blind decision-making (sensitive attributes excluded from prediction). We show that, in the attribute-aware regime, fair ML necessarily (weakly) improves outcomes for the disadvantaged group and (weakly) worsens outcomes for the advantaged group. In contrast, in the attribute-blind regime, the impact of fairness is distribution-dependent: fairness can benefit or harm either group and may shift both groups' outcomes in the same direction, leading to either leveling up or leveling down. We characterize the conditions under which these patterns arise and highlight the role of "masked" candidates in driving them. Overall, our results provide structural guidance on when pursuing algorithmic fairness is likely to improve group outcomes and when it risks systemic leveling down, informing fair ML design and deployment choices.

stat.ML↗
arXiv2026

MPCEval: A Benchmark for Multi-Party Conversation Generation

Multi-party conversation generation, such as smart reply and collaborative assistants, is an increasingly important capability of generative AI, yet its evaluation remains a critical bottleneck. Compared to two-party dialogue, multi-party settings introduce distinct challenges, including complex turn-taking, role-dependent speaker behavior, long-range conversational structure, and multiple equally valid continuations. Accordingly, we introduce MPCEval, a task-aware evaluation and benchmarking suite for multi-party conversation generation. MPCEval decomposes generation quality into speaker modeling, content quality, and speaker--content consistency, and explicitly distinguishes local next-turn prediction from global full-conversation generation. It provides novel, quantitative, reference-free, and reproducible metrics that scale across datasets and models. We apply MPCEval to diverse public and real-world datasets and evaluate modern generation methods alongside human-authored conversations. The results reveal systematic, dimension-specific model characteristics in participation balance, content progression and novelty, and speaker--content consistency, demonstrating that evaluation objectives critically shape model assessment and that single-score evaluation obscures fundamental differences in multi-party conversational behavior. The implementation of MPCEval and the associated evaluation code are publicly available at https://github.com/Owen-Yang-18/MPCEval.

cs.CL↗
arXiv2026

UniTalking: A Unified Audio-Video Framework for Talking Portrait Generation

While state-of-the-art audio-video generation models like Veo3 and Sora2 demonstrate remarkable capabilities, their closed-source nature makes their architectures and training paradigms inaccessible. To bridge this gap in accessibility and performance, we introduce UniTalking, a unified, end-to-end diffusion framework for generating high-fidelity speech and lip-synchronized video. At its core, our framework employs Multi-Modal Transformer Blocks to explicitly model the fine-grained temporal correspondence between audio and video latent tokens via a shared self-attention mechanism. By leveraging powerful priors from a pre-trained video generation model, our framework ensures state-of-the-art visual fidelity while enabling efficient training. Furthermore, UniTalking incorporates a personalized voice cloning capability, allowing the generation of speech in a target style from a brief audio reference. Qualitative and quantitative results demonstrate that our method produces highly realistic talking portraits, achieving superior performance over existing open-source approaches in lip-sync accuracy, audio naturalness, and overall perceptual quality.

cs.CV↗