Searcharxiv⌕ Search

arXiv subjects

Chengyang Zhang

Publications and source records attributed to Chengyang Zhang.

At least 19 recordsLinked to original sources
arXiv2026

PathoJev: Efficient Pathology Decisions from Shared Visual Context

Pathology workflows require multiple visual judgments about the same slide, from identifying tumor type to assessing grade and invasion. Generating and parsing a separate textual response for each structured question adds latency between visual evidence and usable decisions. Building on the System One paradigm, we introduce PathoJev, a pathology model that directly predicts answer probabilities for whole-slide and region-level assessment. PathoJev encodes each slide once and evaluates independent question suffixes in batches over the shared visual context. Reusing the hybrid backbone's recurrent states further limits the computation that grows with slide-context length for each additional question. Across three whole-slide benchmarks, the 9B and 27B models achieve mean accuracies of 77.2% and 78.1%, exceeding SlideChat by 5.4 and 6.3 percentage points. Both scales also maintain competitive accuracy on five ROI benchmarks. On WSI-Bench, the 9B model runs 9.1x faster than SlideChat. Shared context accelerates eight-question workloads by 6.9x and 5.9x over separate prefix encoding, rising to 11.2x and 8.9x for 64 questions. These results provide a reusable probabilistic interface for combining multiple visual judgments in whole-slide and local tissue assessment. Code: https://github.com/ChyaZhang/PathoJev.

cs.CV↗
arXiv2026

Variational Cognitive Memory Abstraction for Long-Horizon Vision-Language-Action Models

Vision-Language-Action (VLA) models have shown remarkable success in robotic manipulation, yet their ability to execute long-horizon tasks remains limited by insufficient long- term memory modeling. Existing methods either rely on implicit temporal representations within policy networks, where historical information can be gradually diluted, or maintain explicit memory buffers that suffer from redundancy, noise accumulation, and inefficient retrieval. In this paper, we propose CogMemory, a novel variational cognitive memory framework that enables VLA systems to selectively preserve and reuse task-relevant historical information. Our approach encodes multimodal trajectories into compact latent memory representations through a selective state- space memory encoder, multi-slot temporal abstraction, and variational information compression. During action generation, dynamic cross-attention retrieval with gated fusion adaptively incorporates relevant memories into policy prediction. With merely 3.45M additional parameters, CogMemory stays lightweight and seamlessly fits both early- and intermediate-fusion VLA backbones. Extensive experiments on long-horizon robotic manipulation benchmarks demonstrate consistent improvements across diverse VLA backbones.

cs.AI↗
arXiv2026

FloodVLM-Pix: Language-Guided Pixel-Level Flood Understanding

As climate change intensifies, floods are becoming more frequent and destructive, making accurate flood understanding an urgent priority. However, existing vision-language models perform poorly on flood-related tasks, suffering from attentional bias and inaccurate descriptions of flood magnitude. To bridge this gap, we construct the first large-scale remote sensing flood multi-modal benchmark that supports language-level flood understanding and pixel-level flood segmentation. The benchmark contains 131,200 flood image patches and corresponding 443,100 textual descriptions for flood severity and evolution. Based on this benchmark, we propose FloodVLM-Pix, a language-guided pixel-level flood understanding model that includes a flood prior module and a multi-temporal flood pixel decoder to achieve accurate flood understanding. The flood prior module automatically distills sub-region flood spatial priors and inputs priors into FloodVLM-Pix, solving the attentional bias problem in flood language understanding. The flood pixel decoder introduces a novel general-specific feature fusion mechanism to address performance degradation caused by interference (e.g., clouds or mountain shadows) during flood segmentation. Experiments on FloodVL-Pix demonstrate that FloodVLM-Pix improves both flood description quality and pixel-level flood segmentation performance compared with state-of-the-art VLMs and flood segmentation models. Our code and data will be released at https://github.com/Haomiaoyanmeng/FloodPix.

cs.CV↗
arXiv2026

ProtoPur: Prototype-Purity Pseudo-Labeling for Weakly Supervised Instance Learning in Pathology

Weak bag-level labels are widely available in computational pathology, whereas reliable instance-level annotations for whole-slide images remain expensive and ambiguous. Weakly supervised multiple instance learning (MIL) achieves strong bag-level classification, but instance-level supervision from attention scores, model predictions, negative bags, or spatial refinement may fail to identify class-specific local evidence. We propose ProtoPur, a prototype-purity pseudo-labeling method for weakly supervised instance-level learning in pathology whole-slide images. ProtoPur estimates class-balanced local purity over prototype regions constructed from frozen foundation-model features, and assigns pseudo-labels to high-purity regions strongly associated with a target class. This purity-first design separates class-specific evidence from negative or shared morphology, with coverage used only to ensure sufficient pseudo-label assignment. We provide a PAC-style analysis showing that the risk of an instance classifier trained with ProtoPur pseudo-labels can be decomposed into a standard uniform-convergence term and a ProtoPur-specific pseudo-label noise term, comprising selected-region mismatch and a coverage residual. Experiments on three public whole-slide image datasets with two pathology foundation encoders show that ProtoPur consistently improves instance-level performance across multiple MIL backbones while maintaining competitive bag-level performance. Pseudo-label quality comparisons on two public datasets further demonstrate that prototype-purity selection provides stronger instance supervision. These results suggest that the foundation-model features contain exploitable instance-level supervision signals, and ProtoPur is a way to reveal and use these signals from weak bag labels without requiring dense instance annotations.

cs.CV↗
arXiv2026

See, Measure, and Reason: Learning Visually Grounded Reasoning in Pathology

Pathological assessment relies on recognizing fine-grained visual details in histological images. Vision-language models (VLMs) increasingly support pathology interpretation, yet their ability to perceive these details remains inadequate. This weakness leads to inaccurate cellular observations that can persist even when final answers are correct. In this paper, we propose ASPECT to improve visually grounded reasoning through explicit supervision of cellular appearance and abundance. ASPECT trains intermediate visual tokens through pathology feature reconstruction, cell feature alignment, and count supervision. Three-stage supervised fine-tuning teaches the model to perceive, generate visual tokens, and reason, followed by reinforcement learning that rewards answer correctness and consistency with reported measurements. We also introduce PathoVernier, a benchmark of 759 expert-reviewed questions from five pathology datasets covering four cellular composition tasks. It evaluates both final answers and intermediate measurements to expose errors hidden by answer accuracy. On PathoVernier, ASPECT achieves relative accuracy gains of approximately 19.2% over the strongest baseline, Gemini-3.1-Pro, and 99.3% over its Qwen3-VL-8B backbone, while reducing RAWR, which measures counting errors within correct responses, by 28.1% and 42.7%, respectively. ASPECT also improves over its backbone on three external pathology benchmarks covering classification and question answering beyond cellular composition tasks.

cs.CV↗
arXiv2026

CellScientist: From Execution Feedback to Auditable Model-Revision Trajectories for Cellular Perturbation Prediction

Cellular perturbation-response modeling requires coordinated choices of representations, fusion mechanisms, objectives, and training procedures. Large language models (LLMs) can propose executable candidates, but unconstrained revision can produce invalid implementations, change task semantics, or discard useful components. We present CellScientist, a protocol-constrained workflow that converts execution and validation feedback into auditable model-revision trajectories. It records design states and outcomes, routes discrepancies to specific components, and applies local revisions under a fixed task contract. A matched-budget study fixes the candidate language, predictor, fitting, and evaluator: structured revision finds better held-out predictors at small budgets under two LLM backbones. Operational audits link history to fewer repeated proposals, contract checks to contained violations, and discrepancy routing to targeted repairs. Refits of two frozen designs on an independently acquired cohort evaluate external predictive utility. Open-workflow trajectories retain improvements, regressions, and failures, while transcriptomic and single-cell searches extend application to additional response spaces. CellScientist produces both a selected predictor and an inspectable record of its development. Project page: https://limengran98.github.io/CellScientist/.

cs.LG↗
arXiv2026

ProcVLM: Learning Procedure-Grounded Progress Rewards for Robotic Manipulation

Long-horizon robotic manipulation requires dense feedback that reflects how a task advances through its procedural stages, not merely whether the final outcome is successful. Existing reward models often rely on trajectory-level success labels or time-based interpolation, which can conflate elapsed time with true task progress and therefore fail to capture unfinished steps, stagnation, and failure states. We present ProcVLM, a progress-aware vision-language model that learns procedure-grounded progress as a dense reward signal for manipulation. Rather than deriving progress from terminal outcomes or temporal proxies, ProcVLM grounds progress estimation in procedural structure and intra-stage visual change, and further adopts a reasoning-before-estimation paradigm that infers the remaining atomic actions before estimating task progress. Specifically, we construct this supervision by synthesizing frame-level subtask-semantic annotations, assigning progress budgets according to subtask structure, and distributing each budget based on intra-subtask visual change. To train ProcVLM at scale, we build a standardized procedural supervision synthesis pipeline and construct ProcCorpus-60M from 30 embodied datasets with 60M annotated frames, from which we derive ProcVQA for procedure-aware pretraining, with progress estimation as the central task alongside action segmentation and future planning. Experiments on ProcVQA and reward-model benchmarks show that ProcVLM improves embodied procedural reasoning and yields more discriminative trajectory-internal progress estimates than representative baselines, supporting its use as a dense reward model for downstream reward-guided policy optimization. Project page: https://procvlm.github.io/

cs.RO↗
arXiv2026

Discover, Falsify, Revise: Auditing Input-Use Claims from Source Code to Predictive Contribution in Agent-Discovered Cell Models

AI virtual cells aim to predict cellular responses to specified interventions, yet held-out predictive performance alone does not establish use of the supplied perturbation information. This prediction-claim gap matters in agentic model discovery, where language-model agents generate and revise predictors using score-based feedback. We introduce CELLAUDIT, which audits input-use claims by asking whether an input can enter the cited computation, whether fitted predictions depend on it, and whether that dependence improves prediction of observed response. On a paired morphology-transcriptomics perturbation benchmark (BBBC047), an agent-selected predictor attains a mean held-out Global Pearson correlation coefficient (PCC) of 0.3153 but remains invariant to compound replacement; a control-profile-only predictor reaches 0.3142. Source inspection identifies a compound-query pathway blocked by singleton key-value attention, and the invariance persists after refitting with disjoint control wells. In a stratified audit of 48 candidates across two linked tasks, 47 change predictions under compound replacement on both held-out folds, but only 20 show target-loss gains with intervals above zero on both folds. On BBBC047, falsification-guided revisions recover positive mean compound contributions while retaining gains over the control-profile-only baseline. In matched sci-Plex searches, audit-enriched feedback yields higher held-out performance and larger mean compound and dose contributions across five trajectories, although paired intervals span zero. Refitting fixed designs on an independently acquired cohort shows predictive generalization need not imply generalization of input-use claims: dose contribution persists, whereas support for compound identity does not. CELLAUDIT adds a falsification layer to agentic model discovery, moving from generate-score-revise toward discover-falsify-revise.

cs.LG↗
arXiv2026

Experiments and Modeling of Defect Dynamics and BTI Behavior in Doped InO TFTs during $400^\circ$C Post-Processing Forming Gas Annealing

We investigate the impact of a monolithic three-dimensional (M3D) integration process-critical $400^\circ$C post-processing forming gas anneal (FGA) on the electrical performance, reliability, and defect evolution of oxide-channel thin-film transistors (TFTs), combining systematic experiments with density-functional-theory (DFT)-based liquid-quench molecular-dynamics (MD) simulations. Indium tungsten oxide (IWO) TFTs are employed as a model system and encapsulated with a thin 3 nm Al$_2$O$_3$ / 3 nm HfO$_2$ hybrid layer that effectively suppresses external hydrogen ingress. We reveal a non-monotonic evolution of device behavior during FGA, governed by initial densification followed by partial crystallization. Short-duration FGA (10 min) induces channel densification and the formation of shallow, delocalized defect states, leading to pronounced positive bias temperature instability (PBTI) degradation and the emergence of a characteristic transfer-curve "kink." With prolonged annealing (>40 min), partial crystallization of the oxide channel occurs, stabilizing hydrogen in deep, localized defect states, suppressing hydrogen mobility, and restoring device reliability. As a result, the PBTI shift is reduced to 10.4 mV after 2000 seconds of stress, accompanied by complete elimination of the transfer-curve kink. These findings provide a mechanistic understanding of hydrogen-defect interactions during high-temperature post-processing FGA and demonstrate that appropriate hydrogen-blocking encapsulation enables oxide-channel TFT integration without compromising electrical performance or reliability.

cond-mat.mtrl-sci↗
arXiv2026

Do Pathology Vision-Language Models Truly See Pathology?

Pathology vision-language models (VLMs) have recently progressed rapidly and are commonly evaluated by answer accuracy on pathology VQA benchmarks. However, we dig into current evaluations and identify three overlooked issues: 1) Visual evidence is not always necessary. For instance, Gemini-3-Pro achieves 53.5% average accuracy across 5 VQA benchmarks without any visual input. 2) Domain training can improve accuracy without proportional gains in visual binding. Compared with Qwen2.5-VL-7B, Patho-R1-7B exhibits a 5.8-point lower multimodal gain and a 3.7-point lower attention IoU. 3) Entity-level attention is diffuse and weakly query-specific. On PathVG, attention maps remain highly correlated across different entity queries. These issues can lead to substantial misjudgments of pathology VLMs' actual multimodal capabilities. To this end, we present PathBind, a benchmark comprising 2,600 samples: PathBind-VQA with 1,500 questions across six dimensions, PathBind-PTA with 600 questions from a private pathology teaching atlas, and PathBind-Grounding with 500 expert-curated region-level samples. Each component undergoes task-specific automated filtering and expert review to reduce textual shortcuts and improve entity-region correspondence. We evaluate 18 representative VLMs on VQA samples of PathBind and five existing pathology VQA benchmarks, and further evaluate 10 VLMs on PathBind-Grounding and PathVG. Results show that current pathology VLMs still exhibit a substantial gap between answer-side performance and visual-semantic binding.

cs.CV↗
arXiv2026

HieDG: A Hierarchical Discrete Geometry-Guided Framework for Multi-Animal Tracking

Multi-animal tracking (MAT) is critical for wildlife monitoring and behavioral analysis, yet remains challenging due to uniform appearance, high density, and irregular motion. Existing methods typically follow heuristic- or query-based paradigms: the former relies on handcrafted geometric associations without end-to-end optimization, whereas the latter enables joint optimization but relies heavily on appearance embeddings. In such conditions, continuous geometric embeddings can be unstable, as small coordinate perturbations may disproportionately alter cross-frame attention weights, degrading identity association performance. To address this limitation, we propose HieDG, a Hierarchical Discrete Geometry-guided tracking framework that reformulates geometric dynamics as structured discrete representations within a query-based tracker. Instead of directly using raw geometric signals, HieDG employs a two-stage residual codebook to discretize position, scale, and velocity cues, transforming unstable continuous geometry into structured, stable discrete tokens. These tokens are aligned with visual embeddings and integrated into the tracking queries to enhance identity consistency. Extensive experiments on animal-specific benchmarks (AnimalTrack, BFT, and BuckTales) demonstrate state-of-the-art association performance with significant improvements in HOTA, AssA, and IDF1. Additional evaluations on generic multi-object tracking benchmarks, including DanceTrack and SportsMOT, show competitive performance, indicating the broader applicability of discretized geometric modeling beyond animal-specific scenarios.

cs.CV↗
arXiv2026

Thermal Processing Limits in Oxide-Channel Ferroelectric Field Effect Transistors

In this work, we report a systematic study of the impact of high-temperature post-capping thermal annealing on the memory characteristics of Oxide-semiconductor channel ferroelectric field-effect transistors (OS-FeFETs). Using an identical engineered ferroelectric gate stack 8nm Hf0.5Zr0.5O2 (HZO) / 3 nm Al2O3 / 8 nm HZO (8/3/8) and a hybrid capping layer (3 nm HfO2 + 3 nm Al2O3), 10 percent Ga doped InO (IGO) channel and 4 percent W doped InO (IWO) channel FeFETs remain functional after annealing at temperatures up to 650 C for durations of up to 30 min and 10 min, respectively; further annealing results in irreversible loss of conduction and device failure. Detailed electrical analysis reveals that the MW enhancement originates from a preferential positive shift in the erased-state threshold voltage, while the programmed-state threshold voltage remains comparatively stable. Grazing-incidence X-ray diffraction measurements further indicate structural evolution in the IWO and IGO oxide channels with increasing annealing temperature, supporting the observed electrical trends.

cond-mat.mtrl-sci↗
arXiv2026

PathoSage: Towards Multi-Source Evidence Adjudication in Pathology via Experience-Aware Agentic Workflow

Recent advances in Multimodal Large Language Models (MLLMs) and agent workflows have shown strong promise for computational pathology, yet reliable patch-level reasoning remains challenging. End-to-end pathology MLLMs often hallucinate morphological features, while recent agentic systems usually merge tool outputs and retrieved knowledge into a shared context, making decisions vulnerable to conflicting evidence and context contamination. We propose PathoSage, a three-stage framework that explicitly separates knowledge retrieval, evidence collection, and evidence adjudication for patch-level pathology multimodal reasoning. Its core component, Structured Evidence Deliberation, independently evaluates heterogeneous evidence from tools, performs conflict analysis, and generates the final judgment in a fresh context to reduce anchoring bias. We further introduce a training-free Beta-Bernoulli experience system with continuous credit assignment to model long-term tool reliability and construct similarity-weighted priors for future tool use. Experiments show that PathoSage effectively mitigates VQA hallucinations and classifier disagreement, outperforming strong pathology MLLM and agentic baselines. Our results highlight explicit evidence adjudication and reliability-aware tool modeling as key ingredients for robust pathology agents.

cs.AI↗
arXiv2026

ALD Oxidant as A Tuning Knob for Memory Window Expansion in Ferroelectric FETs for Vertical NAND Applications

Dielectric inserts are widely used to expand the memory window (MW) in ferroelectric FETs (FeFETs) for vertical NAND applications, with prior efforts focused primarily on material selection and stack positioning. Here, we demonstrate that the ALD oxidant used for the Al2O3 interlayer serves as a process-level tuning knob for MW engineering. H2O-grown Al2O3 yields a significantly larger MW (7-8 V) compared to O3 (4 V) for both gate-injection (12/3) and tunnel dielectric (8/3/8) configurations. While the tunnel dielectric (8/3/8) stack maintains robust retention up to 1e4s at 125C despite the larger MW, the gate-injection (12/3) configuration exhibits pronounced retention degradation for the H2O case. The enhanced MW is attributed to higher interlayer leakage associated with H2O-based ALD. These results establish oxidant choice as a key process parameter for co-optimizing MW and retention in ferroelectric NAND technologies.

cond-mat.mtrl-sci↗
arXiv2026

ALD-Derived WO3-x Leads to Nearly Wake-Up-Free Ferroelectric Hf0.5Zr0.5O2 at Elevated Temperatures

Breaking the memory wall in advanced computing architectures will require complex 3D integration of emerging memory materials such as ferroelectrics-either within the back-end-of-line (BEOL) of CMOS front-end processes or through advanced 3D packaging technologies. Achieving this integration demands that memory materials exhibit high thermal resilience, with the capability to operate reliably at elevated temperatures such as 125C, due to the substantial heat generated by front-end transistors. However, silicon-compatible HfO2-based ferroelectrics tend to exhibit antiferroelectric-like behavior in this temperature range, accompanied by a more pronounced wake-up effect, posing significant challenges to their thermal reliability. Here, we report that by introducing a thin tungsten oxide (WO3-x) layer-known as an oxygen reservoir-and carefully tuning its oxygen content, ultra-thin Hf0.5Zr0.5O2 (5 nm) films can be made robust against the ferroelectric-to-antiferroelectric transition at elevated temperatures. This approach not only minimizes polarization loss in the pristine state but also effectively suppresses the wake-up effect, reducing the required wake-up cycles from 105 to only 10 at 125C- a qualifying temperature for back-end memory integrated with front-end logic, as defined by the JEDEC standard. First-principles density functional theory calculations reveal that WO3 enhances the stability of the ferroelectric orthorhombic phase at elevated temperatures by increasing the tetragonal-to-orthorhombic phase energy gap, and promoting favorable phonon mode evolution, thereby supporting o-phase formation under both thermodynamic and kinetic constraints.

cond-mat.mtrl-sci↗
arXiv2025

Pulse-Mode Operation and Reliability of BEOL-Compatible Ferroelectric Non-Volatile Capacitive Memories with Amorphous Oxide Semiconductor Channels

Non-volatile capacitive memories (nvCAPs) exhibiting AC small-signal capacitance on/off ratio (Con/Coff) with non-destructive read have emerged as a promising device for next-generation memory paradigms. Recently, BEOL-compatible ferroelectric nvCAPs with an amorphous oxide semiconductor channel have been reported, suggesting the possibility of monolithic 3D integration of nvCAPs on top of CMOS. So far, the characterization studies on oxide-channel ferroelectric nvCAPs have been done using dual DC sweep C-V measurements which are typically performed over a time scale of a few seconds. However, non-volatile memory arrays typically require nvCAPs to operate under pulse-mode. It is thus crucial to advance understanding of the behavior of oxide-channel ferroelectric nvCAPs under pulse-mode operation, governed by the unique interplay between ferroelectric layer and oxide channel physics. In this study, we provide a systematic study of the pulse-mode operation of ferroelectric nvCAPs with an amorphous oxide semiconductor channel, including its pulse-based write characteristics and reliability characteristics. We examine overlap area, wake-up and pulse-width dependent Con and Coff writing characteristics under pulse-mode. Further, we suggest the importance of optimizing ferroelectric depolarization for Con retention, while reducing read-after-delay for Coff retention under pulse-mode. Lastly, non-destructive read operation for >10^9 read stress cycles at |Vread|=1V is demonstrated.

cond-mat.mtrl-sci↗
arXiv2025

Revealing Phonon Bridge Effect for Amorphous vs Crystalline Metal-Silicide Layers at Si/Ti Interfaces by a Machine Learning Potential

Metal-semiconductor interfaces play a central role in micro and nano-electronic devices as heat dissipation or temperature drop across these interfaces can significantly affect device performance. Prediction of accurate thermal boundary resistance (TBR) across these interfaces, considering realistic structures and their correlation with underlying thermal transport, remains challenging. In this work we develop a unified Neuroevolution Potential (NEP) for the Si-Ti system that accurately reproduces energies, forces, and phonon properties of bulk Si, Ti, and TiSi2 and extends naturally to interfacial environments to analyze interfacial transport. An important development over current machine-learned interatomic potentials is the capability to model complex structures at metal-semiconductor interfaces, as the NEP enables large scale non-equilibrium molecular dynamics simulations of epitaxial Si/Ti interfaces to elucidate the effect of amorphous or crystalline silicide interfacial layers. Simulated TBRs show excellent agreement with our time-domain thermoreflectance (TDTR) measurements. Spectral analyses reveal that amorphous TiSi2 interfacial layer helps in efficient interfacial transport when the thickness is less than 1.5 nm compared to the crystalline TiSi2 layer, but this trend reverses when the interfacial layer thickness increases beyond 1.5 nm. Comparison of TBRs at Si/TiSi2 interface for different crystalline phases of TiSi2 establishes that C54 phase has reduced TBR compared to C49 phase, which is correlated with the difference in their phonon density of states (PDOS) overlap with Si. These results provide atomistic insight into the role of crystalline versus amorphous silicides in interfacial heat transport and demonstrate a transferable machine-learned potential for studying heat dissipation in advanced semiconductor devices.

cond-mat.mtrl-sci↗
arXiv2025

A Novel Radar Constant False Alarm Rate Detection Algorithm Based on VAMP Deep Unfolding

The combination of deep unfolding with vector approximate message passing (VAMP) algorithm, results in faster convergence and higher sparse recovery accuracy than traditional compressive sensing approaches. However, deep unfolding alters the parameters in traditional VAMP algorithm, resulting in the unattainable distribution parameter of the recovery error of non-sparse noisy estimation via traditional VAMP, which hinders the utilization of VAMP deep unfolding in constant false alarm rate (CFAR) detection in sub-Nyquist radar system. Based on VAMP deep unfolding, we provide a parameter convergence detector (PCD) to estimate the recovery error distribution parameter and implement CFAR detection. Compared to the state-of-the-art approaches, both the sparse solution and non-sparse noisy estimation are utilized to estimate the distribution parameter and implement CFAR detection in PCD, which leverages both the VAMP distribution property and the improved sparse recovery accuracy provided by deep unfolding. Simulation results indicate that PCD offers improved false alarm rate control performance and higher target detection rate.

eess.SP↗