arXiv subjects

Yiyang Zhang

Publications and source records attributed to Yiyang Zhang.

At least 19 recordsLinked to original sources

arXiv2026

SpCAST enables scalable and interpretable integration of single-cell RNA sequencing and single-cell-resolved spatial transcriptomics

Single-cell-resolution spatial transcriptomics (scST) preserves tissue architecture but often provides targeted or sparse transcriptomic measurements, whereas scRNA-seq offers broader coverage without spatial context. We present SpCAST, a scalable and interpretable framework that uses scRNA-seq references to transfer cell identity, reconstruct expression and expose gene-level decision evidence in scST. SpCAST jointly learns reference-cell classification, reference--query alignment and query reconstruction in mini-batches, avoiding the need for a global reference-by-query correspondence matrix. Spatially Aware Gene Attribution (SAGA) approximates the learned decision function with a sparse additive Kolmogorov--Arnold network. Across 53 sections comprising 413,404 spatial cells from five technologies, SpCAST achieved the highest aggregate annotation rank among seven methods and scaled to ten million simulated cells. Controlled masking recovered cell-type-associated expression signals and improved spatial marker concordance. SAGA further resolved expression-dependent gene evidence and distinguished evidence retained or attenuated across intra- and cross-species reference settings.

q-bio.CB↗

arXiv2026

Hidden in Pixels. I. Discovery of dual "little red dots" indicates excess clustering on kilo-parsec scales

``Little Red Dots'' (LRDs) are an abundant high-redshift population newly discovered by the James Webb Space Telescope (JWST) and considered to be an early growth phase of supermassive black holes (SMBHs). Using a method of pixel-by-pixel color selection and relaxing the compactness criteria, we identify four dual LRD candidates in the COSMOS-Web survey with projected separations of $0.\!\!^{\prime\prime}2$-$1.\!\!^{\prime\prime}2$. A comparison between existing LRD samples and mock data reveals that the projected separations of these dual LRD candidates are unlikely to result from chance projections of objects at different redshifts. Furthermore, two of the four systems are covered by COSMOS-3D slitless spectroscopy, and a single-line detection at the same observed wavelength for each LRD in a pair strongly supports that they are at identical redshifts. Assuming that the detected lines are H$α$ based on their high equivalent width and broad profile, the spectroscopic redshifts of $z=5.822$ and $5.464$ for the two pairs are consistent with their photometric redshifts, yielding projected separations of $1.64$ and $7.36\,{\rm kpc}$. These discoveries suggest that the angular auto-correlation function (ACF) of LRDs exhibits an excess ($\sim20$-$30$ times) on sub-arcsec (kilo-parsec) separations compared to an extrapolation of a power-law ACF of JWST-found AGNs measured over $10^{\prime\prime}$-$100^{\prime\prime}$. Our sample is likely to represent precursors of mergers between LRDs, and such mergers may be one of the mechanisms that can drive the rapid growth of SMBHs in their early evolutionary stages.

astro-ph.GA↗

arXiv2026

Extended Components of Little Red Dots in the Rest-Frame Optical

Recent JWST observations have revealed a population of red, compact, high-redshift objects called Little Red Dots (LRDs), whose host components have remained largely unconstrained, possibly due to their extreme compactness. Current morphological studies suggest the presence of extended emission in LRDs at rest-frame ultraviolet wavelengths. However, in the rest-frame optical regime, investigations have been limited by small sample sizes and insufficient imaging depth, hindering reliable separation between point-like and potential extended components. Here we perform the image stacking analysis of 217 LRDs in four NIRCam bands, a large and homogeneous sample observed with the COSMOS-Web survey. Our results reveal the detection of faint extended emission in the F444W band, with a typical size of ~200 parsecs and magnitude of ~27.7 AB at z~6.5. We perform four-band photometric spectral energy distribution fitting based on galaxy templates and derive an average stellar mass of log(M*/M_sun) = 9.02 +0.20/-0.18. Given this stellar mass, the host galaxy is compact, that is, ~2.5 times smaller than star-forming galaxies of similar mass at comparable redshifts. This work provides direct observational evidence for the existence of LRD host galaxies at rest-frame optical wavelengths and offers new insights into the stellar buildup of these systems within the first billion years after the Big Bang.

astro-ph.GA↗

arXiv2026

CellPath-Bench: A Multidimensional Benchmark for Whole-Slide Cellular Representations in Pathology Foundation Models

Pathology foundation models (PFMs) are increasingly used as general-purpose backbones, yet existing benchmarks cannot systematically diagnose their whole-slide cellular representation capabilities, including the decodability of cell-type information and the transferability of such information across tissue sections, datasets, and anatomical organs. We introduce CellPath-Bench, a cellular-resolution benchmark that evaluates frozen PFMs themselves. Following quality control of 52 candidate Xenium datasets, we construct a panel of 25 spatially aligned H\&E--Xenium tissue sections spanning 11 organs and 7,079,283 cells, harmonized into fine- and coarse-grained taxonomies. CellPath-Bench samples frozen WSI feature maps at registered nuclear coordinates and evaluates them using standardized multiclass linear probes. Cell Representation Advantage (CRA) measures the within-section advantage of nucleus-anchored representations over patch-level mean pooling, while Cell Representation Transferability (CRT) characterizes the generalization of cell-type decodability across tissue sections, datasets, and organs. We benchmark 30 pathology-specific and general-purpose foundation models through 304,920 runs across spatial readouts, magnifications, taxonomic granularities, and evaluation protocols. The results reveal substantial model-dependent differences in cell-type decodability and its cross-domain generalization, yielding distinct multidimensional capability profiles. CellPath-Bench provides a standardized framework for auditing cellular information in frozen PFM representations.

cs.AI↗

arXiv2026

Privacy-Preserving Localization via Transmit Antenna Selection and Permutation

Integrated sensing and communication (ISAC) has been identified as one primary usage scenario in the sixth-generation (6G) network. While techniques to preserve information privacy, such as cryptography, have been widely investigated, how to preserve sensing privacy is still an open problem in the literature. This paper makes an early attempt to tackle the above issue. Specifically, we consider a localization system consisting of a multi-antenna transmitter, termed Alice, a single-antenna legitimate receiver, termed Bob, and a single-antenna illegitimate receiver, termed Eve. To allow Bob to estimate Alice's angle-of-departure (AOD) but prevent Eve from performing this task based on Alice's signals, this paper proposes a novel antenna selection and permutation based transmission strategy for Alice. Under this scheme, Alice carefully selects a subset of antennas and permutes their indices to establish a specific pilot-antenna mapping for transmission. Similar to cryptography for information privacy, such a mapping will serve as the secret key to preserve localization privacy. In the special case without noise at Bob and Eve, we manage to find out all the antenna selection and permutation solutions such that with this key (knowledge about the exact pilot-antenna mapping), Bob can uniquely estimate Alice's AOD, while without this key, Eve can estimate multiple AODs of Alice that can lead to its received signals. In the noisy case, numerical results are provided to show that our scheme can confuse Eve to make inaccurate AOD estimation as well.

eess.SP↗

arXiv2026

Adjustable Text-Guided Backdoor Attacks with Natural-Word Triggers on Multimodal Pretrained Models

This paper presents Text-Guided Backdoor (TGB), an adjustable backdoor attack against multimodal pretrained models that uses natural-word triggers, namely words that can naturally occur in ordinary textual inputs. Most existing backdoor attacks require specific trigger conditions that are typically not satisfied by ordinary inference inputs, thereby limiting their activation in real-world deployments. TGB overcomes this limitation by exploiting naturally occurring words as triggers, enabling stealthy activation without requiring explicit trigger insertion at inference time. This property avoids conspicuous trigger patterns and improves the practicality of TGB. Furthermore, we introduce visual adversarial perturbations on poisoned samples to modulate the model's learning of natural-word triggers, thereby enabling flexible adjustment of TGB attack strength without modifying the poisoned data. Extensive experiments are conducted on downstream tasks built upon multimodal pretrained models, including Composed Image Retrieval (CIR) and Visual Question Answering (VQA). Results demonstrate the effectiveness of TGB across diverse poisoning settings and its ability to flexibly adjust attack success rates, which reveal critical security vulnerabilities in multimodal pretrained models.

cs.CR↗

arXiv2026

MOSS Transcribe Diarize Technical Report

Speaker-Attributed, Time-Stamped Transcription (SATS) aims to transcribe what is said and to precisely determine the timing of each speaker, which is particularly valuable for meeting transcription. Existing SATS systems rarely adopt an end-to-end formulation and are further constrained by limited context windows, weak long-range speaker memory, and the inability to output timestamps. To address these limitations, we present MOSS Transcribe Diarize, a unified multimodal large language model that jointly performs Speaker-Attributed, Time-Stamped Transcription in an end-to-end paradigm. Trained on extensive real wild data and equipped with a 128k context window for up to 90-minute inputs, MOSS Transcribe Diarize scales well and generalizes robustly. Across comprehensive evaluations, it outperforms state-of-the-art commercial systems on multiple public and in-house benchmarks.

cs.SD↗

arXiv2026

Formalization of Line Search Methods by Lean

This paper presents a formalization of line search methods in the Lean 4 theorem prover. Our goal is to advance machine verification of nonlinear optimization theory by translating standard textbook definitions and convergence arguments into rigorous Lean code. We formalize fundamental notions related to gradient descent and descent directions, adaptive step-size selection via backtracking line search, and several classical line search criteria, including the Armijo, Goldstein, and Wolfe conditions, as well as nonmonotone variants. We further formalize a key convergence result, namely the Zoutendijk theorem, which plays a central role in the global convergence analysis of gradient-based iterative methods. By providing machine-checkable definitions and proofs for line search theory, this work complements existing formalizations of first-order optimization methods and establishes a foundation for the verified development of more advanced algorithms in nonlinear programming.

math.OC↗

arXiv2026

Rotational Symmetry based Object Pose Estimation from Point Clouds in the Absence of Known 3D Models

Object pose estimation is crucial to many industrial applications, with one example being automated spray painting using a robot. However, confidentiality concerns often limit access to high-quality 3D models, posing a significant challenge for point-cloud-based pose estimation. In such scenarios, rotational symmetry, a readily accessible characteristic of many industrial objects, can provide valuable prior information to facilitate pose estimation.In this paper, we propose a method that leverages the rotational symmetry commonly found in industrial objects to address the challenge caused by the absence of 3D models. The object pose is jointly estimated with point cloud refinement through an iterative optimization process. This optimization relies on a rotational symmetry constraint loss. To construct this loss, each 3D point is rotated according to the currently estimated pose, and multiple correspondences are identified using nearest-neighbor search by exploiting the rotational symmetry property. These correspondences are then used to compute the rotational symmetry constraint loss, which iteratively refines both the pose and the point cloud.By explicitly incorporating rotational symmetry into the optimization process, the proposed method achieves robust pose estimation and generalizes well across diverse object types. The proposed method is evaluated on a dataset specifically created for point clouds without known 3D models, consisting of four categories of synthetic objects and one real wheel hub collected from a production line. Experimental results demonstrate that the proposed method achieves performance comparable to methods that rely on known 3D models.

cs.CV↗

arXiv2026

MOSS-Audio Technical Report

MOSS-Audio is a unified audio-language model for speech, environmental sound, and music understanding, supporting audio captioning, time-aware question answering, timestamped transcription, and audio-grounded reasoning. MOSS-Audio couples a dedicated audio encoder with a modality adapter and a large language model: the encoder produces 12.5 Hz temporal representations, the adapter projects them into the decoder space, and the decoder generates autoregressive text outputs. Two design choices are central to the system: DeepStack cross-layer feature injection, which exposes the decoder to acoustic information from multiple encoder depths, and time markers, which provide explicit temporal cues by inserting timestamp markers into the audio-token stream. At the data level, we design an event-preserving audio annotation pipeline that segments raw audio at coherent event boundaries, applies branch-specific annotation to speech, music, and general audio, and merges the results into unified captions for pretraining. The intermediate branch-specific captions are further retained to support the construction of task-oriented SFT data. The model is pretrained on large-scale audio-language data, with time-aware objectives incorporated to support temporal grounding, and then undergoes multi-stage post-training to enhance instruction following and audio-grounded reasoning. We release 4B and 8B variants in both Instruct and Thinking configurations. MOSS-Audio achieves strong performance across general audio understanding, speech captioning, ASR, and timestamped ASR, positioning it as a promising understanding foundation for future voice agents.

cs.SD↗

arXiv2026

DaX: Learning General Pathology Representations Across Scales

Computational pathology requires visual representations that transfer across diverse clinical endpoints and remain robust to variation in magnification, staining, scanner type, slide preparation, and input resolution. We present DaX, a pathology vision foundation model that adapts DINOv3-style self-supervised learning to whole-slide histopathology. DaX is initialized from natural-image DINOv3 weights and incorporates continuous magnification training, cross-scale tissue views, orientation-agnostic and acquisition-robust augmentation, multi-input-size training, and Gram-anchored dense consistency. These designs aim to connect local cellular morphology with global tissue architecture while stabilizing dense token-level representations across input scales. We further construct a WSI-level benchmark comprising 161 clinically meaningful tasks from 44 public datasets, covering 28,182 patients and 34,394 slides across four clinical domains and nine task categories. All models are evaluated under a fixed patient-level cross-validation protocol with fold-level statistical ranking, enabling reproducible comparisons that are less sensitive to split-dependent variation. Across this benchmark, DaX achieves the highest mean performance across tasks and consistently strong task-level ranking scores, with gains spanning diagnostic pathology, biomarker and molecular profiling, tissue/specimen context, and risk, response, and prognosis. These results support DaX as a transferable visual encoder for computational pathology and provide a standardized evaluation framework for future pathology foundation models. Project page: https://alibaba-damo-academy.github.io/DaX/benchboard/.

eess.IV↗

arXiv2026

Benchmarking Pathology Foundation Models for Spatial Domain Understanding

Pathology foundation models (PFMs) have emerged as a core approach for learning transferable representations from whole slide images (WSIs), and they are typically benchmarked through downstream clinical endpoints. While such task level evaluations are indispensable, they offer limited insight into what the representations themselves encode, particularly whether PFM embeddings can distinguish meaningful tissue regions and capture their spatial relationships. We present SpaPath-Bench, a representation level benchmark designed to diagnose spatial representation capability in PFMs. SpaPath-Bench formulates spatial domain identification (SDI) on paired whole slide image and spatial transcriptomics (ST) data as a diagnostic task. It curates 42 public paired WSI and ST slides, enables large scale evaluation across 19 encoders and seven SDI methods, and measures partition quality using three complementary criteria: unsupervised spatial coherence, transcriptomics referenced agreement, and expert referenced agreement. Across 83K runs, SpaPath-Bench reveals that different pretraining paradigms capture distinct aspects of tissue spatial architecture, and it provides practical guidance for building the next generation of spatially aware computational pathology models. Code and data pipelines are publicly available at https://bokai-zhao.github.io/SpaPath-benchboard/.

cs.CV↗

arXiv2026

Profiling the Voice: Speaker-Specific Phoneme Fingerprinting for Speech Deepfake Detection

The rapid advancement of generative AI has made audio deepfakes increasingly indistinguishable from authentic human vocals, posing significant threats to persons-of-interest (POI) such as public figures. Current detection systems primarily rely on generic, black-box models that fail to capture speaker-specific idiosyncratic traits and lack interpretability. In this paper, we propose Phoneme-based Voice Profiling (PVP), a novel personalized defense framework. By shifting the detection paradigm from macro-utterance analysis to micro-phonetic modeling, PVP captures the unique acoustic distributions underlying a POI's habitual articulatory patterns. Specifically, our framework models speaker-specific phonetic realizations using lightweight Gaussian Mixture Models (GMMs) estimated solely from bona fide reference speech. This design enables data-efficient profiling and robust generalization to previously unseen spoofing attacks without requiring heavy spoof-specific training. Furthermore, we introduce the first large-scale Chinese POI deepfake dataset to benchmark speaker-specific detection. Experimental results demonstrate that PVP significantly outperforms state-of-the-art generic detectors in POI spoofing scenarios, achieving substantial EER reductions while providing fine-grained, phoneme-level interpretability for forensic analysis. Code and data are available at: https://github.com/JunXue-tech/PVP

cs.SD↗

arXiv2026

Ultrasound Vision-Language Alignment via Contrastive Learning

Ultrasound foundation models have achieved strong performance on structured prediction tasks but remain exclusively vision-based, limiting zero-shot and few-shot transfer to novel tasks where task-specific annotation is scarce. We address this gap with EchoCare-CLIP, a CLIP-style dual-encoder contrastive framework that aligns ultrasound images with clinical text in a shared embedding space. We curate a multi-organ corpus of over 16K image-text pairs spanning breast, liver, lung, and thyroid, with over 78% of captions derived from expert-annotated reports, and complement the remainder with a three-tier template-based and LLM-based caption generation pipeline. We evaluate model configurations spanning two text encoder families (CLIP, BioClinicalBERT) and two caption strategies (template-based, LLM-generated) against OpenAI CLIP and BiomedCLIP baselines. Our trained models consistently improve cross-modal alignment over baselines, with the best configuration achieving a paired alignment score of 0.682. However, stronger alignment does not guarantee better downstream performance: CLIP-based variants with partial fine-tuning achieve the strongest zero-shot classification on external held-out datasets (0.709 on BUSI; 0.626 on AULI), while full end-to-end fine-tuning degrades transfer due to overfitting. On linear probing and few-shot adaptation, model rankings are dataset-dependent, reflecting a trade-off between domain adaptation and representational generalizability. We further show that template-based captions match or outperform LLM-generated captions, suggesting lexical diversity is not a proxy for caption quality. Taken together, our results demonstrate that ultrasound vision-language alignment is achievable from public data alone, but robust clinical transfer requires careful balancing of domain adaptation, encoder capacity, and caption supervision quality.

cs.CV↗

arXiv2026

HabitatAgent: An End-to-End Multi-Agent System for Housing Consultation

Housing selection is a high-stakes and largely irreversible decision problem. We study housing consultation as a decision-support interface for housing selection. Existing housing platforms and many LLM-based assistants often reduce this process to ranking or recommendation, resulting in opaque reasoning, brittle multi-constraint handling, and limited guarantees on factuality. We present HabitatAgent, the first LLM-powered multi-agent architecture for end-to-end housing consultation. HabitatAgent comprises four specialized agent roles: Memory, Retrieval, Generation, and Validation. The Memory Agent maintains multi-layer user memory through internal stages for constraint extraction, memory fusion, and verification-gated updates; the Retrieval Agent performs hybrid vector--graph retrieval (GraphRAG); the Generation Agent produces evidence-referenced recommendations and explanations; and the Validation Agent applies multi-tier verification and targeted remediation. Together, these agents provide an auditable and reliable workflow for end-to-end housing consultation. We evaluate HabitatAgent on 100 real user consultation scenarios (300 multi-turn question--answer pairs) under an end-to-end correctness protocol. A strong single-stage baseline (Dense+Rerank) achieves 75% accuracy, while HabitatAgent reaches 95%.

cs.LG↗

arXiv2026

MOSS-TTS Technical Report

This technical report presents MOSS-TTS, a speech generation foundation model built on a scalable recipe: discrete audio tokens, autoregressive modeling, and large-scale pretraining. Built on MOSS-Audio-Tokenizer, a causal Transformer tokenizer that compresses 24 kHz audio to 12.5 fps with variable-bitrate RVQ and unified semantic-acoustic representations, we release two complementary generators: MOSS-TTS, which emphasizes structural simplicity, scalability, and long-context/control-oriented deployment, and MOSS-TTS-Local-Transformer, which introduces a frame-local autoregressive module for higher modeling efficiency, stronger speaker preservation, and a shorter time to first audio. Across multilingual and open-domain settings, MOSS-TTS supports zero-shot voice cloning, token-level duration control, phoneme-/pinyin-level pronunciation control, smooth code-switching, and stable long-form generation. This report summarizes the design, training recipe, and empirical characteristics of the released models.

cs.SD↗

arXiv2026

MOSS-TTSD: Text to Spoken Dialogue Generation

Spoken dialogue generation is crucial for applications like podcasts, dynamic commentary, and entertainment content, but poses significant challenges compared to single-utterance text-to-speech (TTS). Key requirements include accurate turn-taking, cross-turn acoustic consistency, and long-form stability, which current models often fail to address due to a lack of dialogue context modeling. To bridge this gap, we present MOSS-TTSD, a spoken dialogue synthesis model designed for expressive, multi-party conversational speech across multiple languages. With enhanced long-context modeling, MOSS-TTSD generates long-form spoken conversations from dialogue scripts with explicit speaker tags, supporting up to 60 minutes of single-pass synthesis, multi-party dialogue with up to 5 speakers, and zero-shot voice cloning from a short reference audio clip. The model supports various mainstream languages, including English and Chinese, and is adapted to several long-form scenarios. Additionally, to address limitations of existing evaluation methods, we propose TTSD-eval, an objective evaluation framework based on forced alignment that measures speaker attribution accuracy and speaker similarity without relying on speaker diarization tools. Both objective and subjective evaluation results show that MOSS-TTSD surpasses strong open-source and proprietary baselines in dialogue synthesis.

cs.SD↗

arXiv2026

Stable Spike: Dual Consistency Optimization via Bitwise AND Operations for Spiking Neural Networks

Although the temporal spike dynamics of spiking neural networks (SNNs) enable low-power temporal pattern capture capabilities, they also incur inherent inconsistencies that severely compromise representation. In this paper, we perform dual consistency optimization via Stable Spike to mitigate this problem, thereby improving the recognition performance of SNNs. With the hardware-friendly ``AND" bit operation, we efficiently decouple the stable spike skeleton from the multi-timestep spike maps, thereby capturing critical semantics while reducing inconsistencies from variable noise spikes. Enforcing the unstable spike maps to converge to the stable spike skeleton significantly improves the inherent consistency across timesteps. Furthermore, we inject amplitude-aware spike noise into the stable spike skeleton to diversify the representations while preserving consistent semantics. The SNN is encouraged to produce perturbation-consistent predictions, thereby contributing to generalization. Extensive experiments across multiple architectures and datasets validate the effectiveness and versatility of our method. In particular, our method significantly advances neuromorphic object recognition under ultra-low latency, improving accuracy by up to 8.33\%. This will help unlock the full power consumption and speed potential of SNNs.

cs.NE↗