arXiv subjects

Yunlong Tang

Publications and source records attributed to Yunlong Tang.

At least 19 recordsLinked to original sources

arXiv2026

Silicon-compatible ideal antiferroelectricity with large digital electromechanical responses enabled by thermal-strain domain engineering

Antiferroelectrics exhibit reversible antipolar-polar transformations, offering a compelling platform for multiple functionalities in modern nanoelectronics, yet deterministic control of antiferroelectric domains and switching pathways remain elusive. Moreover, their integration with ubiquitous silicon-based electronic devices has been limited by the structural and chemical incompatibilities of conventional oxide platforms. Here, we convert the conventional drawback of thermal mismatch into a functional advantage and realize ideal antiferroelectricity in epitaxial PbZrO3 thin films on silicon through thermal tensile-strain engineering, a strain regime unattainable on conventional perovskite substrates. Combined theoretical and experimental studies show that tensile strain stabilizes the (004)o domain, enabling a direct one-step switching, whereas compressive-strain-stabilized (240)o domains switch through intermediate ferrielectric states. The resulting films exhibit near-zero remanent polarization, square double hysteresis, nanosecond switching (~75ns), large reversible electrostrain (~0.6%) and robust operation windows. These findings provide key insights into domain-engineered ideal antiferroelectricity on silicon, opening a viable route toward high-performance antiferroelectric nano-electronic devices.

cond-mat.mtrl-sci↗

arXiv2026

Unlocking Cryogenic Energy Storage by Constructing Dipole Glass with Unit-cell-level Polar Disorder

Cryogenic energy storage is vital for frontier technologies including deep-space exploration and quantum computing, yet conventional electrochemical energy systems fail below ~230 K due to frozen ion migration. While relaxor-based dielectric capacitors provide high efficiency at room temperature, the intrinsic freezing/growth of polar nanodomains at extended cryogenic regime limits their applications with deteriorated hysteresis losses. Here, we realize superior cryogenic energy-storage performance by designing unit-cell-level disordered dipole-glass state in Pb0.6Sr0.4ZrO3 thin films with composition near antiferroelectric-paraelectric phase boundary. The antiferroelectric-derived dipole-glass introduces enhanced unit-cell-level complexity of dipole interaction that suppresses long-range ferroelectric order. This enables ultralow-hysteresis operation (efficiency > 88%) down to 4 K, delivering record-high energy density (211 J/cm^3) at 9 MV/cm, stability over 10^8 charge/discharge cycles and microsecond-scale charge/discharge capability. This work establishes a dipole-glass paradigm for cryogenic dielectric capacitors, opening a new avenue to highly-efficient energy-storage systems with broad applications in frontier nanoelectronics.

cond-mat.mtrl-sci↗

arXiv2025

ToolMem: Enhancing Multimodal Agents with Learnable Tool Capability Memory

Agents utilizing tools powered by large language models (LLMs) or vision-language models (VLMs) have demonstrated remarkable progress in diverse tasks across text and visual modalities. Unlike traditional tools such as calculators, which give deterministic outputs, neural tools perform uncertainly across task scenarios. While different tools for a task may excel in varied scenarios, existing agents typically rely on fixed tools, thus limiting the flexibility in selecting the most suitable tool for specific tasks. In contrast, humans snowball their understanding of the capabilities of different tools by interacting with them, and apply this knowledge to select the optimal tool when solving a future task. To build agents that similarly benefit from this process, we propose ToolMem that enables agents to develop memories of tool capabilities from previous interactions, by summarizing their strengths and weaknesses and storing them in memory; at inference, the agent can retrieve relevant entries from ToolMem, and select the best tool to solve individual tasks more accurately. We evaluate ToolMem on learning varied text generation and text-to-image generation neural tools. Compared to no-memory, generic agents, we find ToolMem-augmented agents predict tool performance 14.8% and 28.7% more accurately across text and multimodal generation scenarios. Moreover, ToolMem facilitates optimal tool selection among multiple choices by 21% and 24% absolute increases in respective scenarios.

cs.CL↗

arXiv2025

VQualA 2025 Challenge on Engagement Prediction for Short Videos: Methods and Results

This paper presents an overview of the VQualA 2025 Challenge on Engagement Prediction for Short Videos, held in conjunction with ICCV 2025. The challenge focuses on understanding and modeling the popularity of user-generated content (UGC) short videos on social media platforms. To support this goal, the challenge uses a new short-form UGC dataset featuring engagement metrics derived from real-world user interactions. This objective of the Challenge is to promote robust modeling strategies that capture the complex factors influencing user engagement. Participants explored a variety of multi-modal features, including visual content, audio, and metadata provided by creators. The challenge attracted 97 participants and received 15 valid test submissions, contributing significantly to progress in short-form UGC video engagement prediction.

cs.CV↗

arXiv2025

Enhancing ferroelectric stability: Wide-range of adaptive control in epitaxial HfO2/ZrO2 superlattices

The metastability of the polar phase in HfO2, despite its excellent compatibility with the complementary metal-oxide-semiconductor process, remains a key obstacle for its industrial applications. Traditional stabilization approaches, such as doping, often induce crystal defects and impose constraints on the thickness of ferroelectric HfO2 thin films. These limitations render the ferroelectric properties vulnerable to degradation, particularly due to phase transitions under operational conditions. Here, we demonstrate robust ferroelectricity in high-quality epitaxial (HfO2)n/(ZrO2)n superlattices, which exhibit significantly enhanced ferroelectric stability across an extended thickness range. Optimized-period superlattices maintain stable ferroelectricity from up to 100 nm, excellent fatigue resistance exceeding 109 switching cycles, and a low coercive field of ~0.85 MV/cm. First-principles calculations reveal that the kinetic energy barrier of phase transition and interfacial formation energy are crucial factors in suppressing the formation of non-polar phases. This work establishes a versatile platform for exploring high-performance fluorite-structured superlattices and advances the integration of HfO2-based ferroelectrics into a broader range of applications.

cond-mat.mtrl-sci↗

arXiv2025

Can Sound Replace Vision in LLaVA With Token Substitution?

What happens when we push audio-visual alignment to its absolute limits? To systematically investigate this question, we needed datasets with granular alignment quality annotations, but existing datasets treat alignment as binary, either synchronized or not. To address this limitation, we developed a comprehensive dataset featuring detailed alignment scores that reveal the hidden spectrum of audio-visual perceptual correspondence. Using these precise scores, we create "superaligned" representations by training exclusively on the most perfectly matched audio-visual pairs, then conduct our systematic investigation into how this extreme alignment transforms perceptual model behavior across retrieval and generation tasks. The encoders under study fall into two main groups consisting of image-centric encoders that were pretrained using visual modalities as intermediary hubs for connecting modalities, and text-centric encoders that were pretrained with direct audio-language alignment. We first measure the baseline performance of these encoders on two key tasks, namely cross-modal retrieval and text description generation in vision-language models. Subsequently, we realign all encoders with the CLIP space using highly coherent audio-visual data and observe the performance changes. Our findings reveal that the initial architectural type of the encoder determines how it responds to the alignment process. Image-centric encoders, which are inherently designed for alignment, demonstrate exceptional performance in cross-modal retrieval, but this intensive alignment causes compression of unique linguistic information and reduces the quality of their text description generation in vision-language models. In contrast, text-centric encoders, which possess stronger linguistic authenticity, are able to maintain a better balance between the two objectives.

cs.MM↗

arXiv2025

ZeroSep: Separate Anything in Audio with Zero Training

Audio source separation is fundamental for machines to understand complex acoustic environments and underpins numerous audio applications. Current supervised deep learning approaches, while powerful, are limited by the need for extensive, task-specific labeled data and struggle to generalize to the immense variability and open-set nature of real-world acoustic scenes. Inspired by the success of generative foundation models, we investigate whether pre-trained text-guided audio diffusion models can overcome these limitations. We make a surprising discovery: zero-shot source separation can be achieved purely through a pre-trained text-guided audio diffusion model under the right configuration. Our method, named ZeroSep, works by inverting the mixed audio into the diffusion model's latent space and then using text conditioning to guide the denoising process to recover individual sources. Without any task-specific training or fine-tuning, ZeroSep repurposes the generative diffusion model for a discriminative separation task and inherently supports open-set scenarios through its rich textual priors. ZeroSep is compatible with a variety of pre-trained text-guided audio diffusion backbones and delivers strong separation performance on multiple separation benchmarks, surpassing even supervised methods.

cs.SD↗

arXiv2025

MMIG-Bench: Towards Comprehensive and Explainable Evaluation of Multi-Modal Image Generation Models

Recent multimodal image generators such as GPT-4o, Gemini 2.0 Flash, and Gemini 2.5 Pro excel at following complex instructions, editing images and maintaining concept consistency. However, they are still evaluated by disjoint toolkits: text-to-image (T2I) benchmarks that lacks multi-modal conditioning, and customized image generation benchmarks that overlook compositional semantics and common knowledge. We propose MMIG-Bench, a comprehensive Multi-Modal Image Generation Benchmark that unifies these tasks by pairing 4,850 richly annotated text prompts with 1,750 multi-view reference images across 380 subjects, spanning humans, animals, objects, and artistic styles. MMIG-Bench is equipped with a three-level evaluation framework: (1) low-level metrics for visual artifacts and identity preservation of objects; (2) novel Aspect Matching Score (AMS): a VQA-based mid-level metric that delivers fine-grained prompt-image alignment and shows strong correlation with human judgments; and (3) high-level metrics for aesthetics and human preference. Using MMIG-Bench, we benchmark 17 state-of-the-art models, including Gemini 2.5 Pro, FLUX, DreamBooth, and IP-Adapter, and validate our metrics with 32k human ratings, yielding in-depth insights into architecture and data design.

cs.CV↗

arXiv2025

Harnessing the Computation Redundancy in ViTs to Boost Adversarial Transferability

Vision Transformers (ViTs) have demonstrated impressive performance across a range of applications, including many safety-critical tasks. However, their unique architectural properties raise new challenges and opportunities in adversarial robustness. In particular, we observe that adversarial examples crafted on ViTs exhibit higher transferability compared to those crafted on CNNs, suggesting that ViTs contain structural characteristics favorable for transferable attacks. In this work, we investigate the role of computational redundancy in ViTs and its impact on adversarial transferability. Unlike prior studies that aim to reduce computation for efficiency, we propose to exploit this redundancy to improve the quality and transferability of adversarial examples. Through a detailed analysis, we identify two forms of redundancy, including the data-level and model-level, that can be harnessed to amplify attack effectiveness. Building on this insight, we design a suite of techniques, including attention sparsity manipulation, attention head permutation, clean token regularization, ghost MoE diversification, and test-time adversarial training. Extensive experiments on the ImageNet-1k dataset validate the effectiveness of our approach, showing that our methods significantly outperform existing baselines in both transferability and generality across diverse model architectures.

cs.CV↗

arXiv2025

The Tenth NTIRE 2025 Efficient Super-Resolution Challenge Report

This paper presents a comprehensive review of the NTIRE 2025 Challenge on Single-Image Efficient Super-Resolution (ESR). The challenge aimed to advance the development of deep models that optimize key computational metrics, i.e., runtime, parameters, and FLOPs, while achieving a PSNR of at least 26.90 dB on the $\operatorname{DIV2K\_LSDIR\_valid}$ dataset and 26.99 dB on the $\operatorname{DIV2K\_LSDIR\_test}$ dataset. A robust participation saw \textbf{244} registered entrants, with \textbf{43} teams submitting valid entries. This report meticulously analyzes these methods and results, emphasizing groundbreaking advancements in state-of-the-art single-image ESR techniques. The analysis highlights innovative approaches and establishes benchmarks for future research in the field.

cs.CV↗

arXiv2025

Caption Anything in Video: Fine-grained Object-centric Captioning via Spatiotemporal Multimodal Prompting

We present CAT-V (Caption AnyThing in Video), a training-free framework for fine-grained object-centric video captioning that enables detailed descriptions of user-selected objects through time. CAT-V integrates three key components: a Segmenter based on SAMURAI for precise object segmentation across frames, a Temporal Analyzer powered by TRACE-Uni for accurate event boundary detection and temporal analysis, and a Captioner using InternVL-2.5 for generating detailed object-centric descriptions. Through spatiotemporal visual prompts and chain-of-thought reasoning, our framework generates detailed, temporally-aware descriptions of objects' attributes, actions, statuses, interactions, and environmental contexts without requiring additional training data. CAT-V supports flexible user interactions through various visual prompts (points, bounding boxes, and irregular regions) and maintains temporal sensitivity by tracking object states and interactions across different time segments. Our approach addresses limitations of existing video captioning methods, which either produce overly abstract descriptions or lack object-level precision, enabling fine-grained, object-specific descriptions while maintaining temporal coherence and spatial accuracy. The GitHub repository for this project is available at https://github.com/yunlong10/CAT-V

cs.CV↗

arXiv2025

Why Reasoning Matters? A Survey of Advancements in Multimodal Reasoning (v1)

Reasoning is central to human intelligence, enabling structured problem-solving across diverse tasks. Recent advances in large language models (LLMs) have greatly enhanced their reasoning abilities in arithmetic, commonsense, and symbolic domains. However, effectively extending these capabilities into multimodal contexts-where models must integrate both visual and textual inputs-continues to be a significant challenge. Multimodal reasoning introduces complexities, such as handling conflicting information across modalities, which require models to adopt advanced interpretative strategies. Addressing these challenges involves not only sophisticated algorithms but also robust methodologies for evaluating reasoning accuracy and coherence. This paper offers a concise yet insightful overview of reasoning techniques in both textual and multimodal LLMs. Through a thorough and up-to-date comparison, we clearly formulate core reasoning challenges and opportunities, highlighting practical methods for post-training optimization and test-time inference. Our work provides valuable insights and guidance, bridging theoretical frameworks and practical implementations, and sets clear directions for future research.

cs.CL↗

arXiv2025

FreSca: Scaling in Frequency Space Enhances Diffusion Models

Latent diffusion models (LDMs) have achieved remarkable success in a variety of image tasks, yet achieving fine-grained, disentangled control over global structures versus fine details remains challenging. This paper explores frequency-based control within latent diffusion models. We first systematically analyze frequency characteristics across pixel space, VAE latent space, and internal LDM representations. This reveals that the "noise difference" term, derived from classifier-free guidance at each step t, is a uniquely effective and semantically rich target for manipulation. Building on this insight, we introduce FreSca, a novel and plug-and-play framework that decomposes noise difference into low- and high-frequency components and applies independent scaling factors to them via spatial or energy-based cutoffs. Essentially, FreSca operates without any model retraining or architectural change, offering model- and task-agnostic control. We demonstrate its versatility and effectiveness in improving generation quality and structural emphasis on multiple architectures (e.g., SD3, SDXL) and across applications including image generation, editing, depth estimation, and video synthesis, thereby unlocking a new dimension of expressive control within LDMs.

cs.CV↗

arXiv2025

VERIFY: A Benchmark of Visual Explanation and Reasoning for Investigating Multimodal Reasoning Fidelity

Visual reasoning is central to human cognition, enabling individuals to interpret and abstractly understand their environment. Although recent Multimodal Large Language Models (MLLMs) have demonstrated impressive performance across language and vision-language tasks, existing benchmarks primarily measure recognition-based skills and inadequately assess true visual reasoning capabilities. To bridge this critical gap, we introduce VERIFY, a benchmark explicitly designed to isolate and rigorously evaluate the visual reasoning capabilities of state-of-the-art MLLMs. VERIFY compels models to reason primarily from visual information, providing minimal textual context to reduce reliance on domain-specific knowledge and linguistic biases. Each problem is accompanied by a human-annotated reasoning path, making it the first to provide in-depth evaluation of model decision-making processes. Additionally, we propose novel metrics that assess visual reasoning fidelity beyond mere accuracy, highlighting critical imbalances in current model reasoning patterns. Our comprehensive benchmarking of leading MLLMs uncovers significant limitations, underscoring the need for a balanced and holistic approach to both perception and reasoning. For more teaser and testing, visit our project page (https://verify-eqh.pages.dev/).

cs.CV↗

arXiv2025

Fatigue-free ferroelectricity in Hf0.5Zr0.5O2 ultrathin films via interfacial design

Due to traits of CMOS compatibility and scalability, HfO2-based ferroelectrics are promising candidates for next-generation memory devices. However, their commercialization has been greatly hindered by reliability issues, with fatigue being a major impediment. We report the fatigue-free behavior in interface-designed Hf0.5Zr0.5O2-based heterostructures. A coherent CeO2-x/Hf0.5Zr0.5O2 heterointerface is constructed, wherein CeO2-x acts as an oxygen sponge, capable of reversibly accepting and releasing oxygen vacancies. This design effectively alleviates defect aggregation at the electrode-ferroelectric interface, enabling improved switching characteristics. Further, a symmetric capacitor architecture is designed to minimize the imprint, thereby suppressing the cycling-induced oriented defect drift. The two-pronged technique mitigates oxygen-voltammetry-generated chemical/energy fluctuations, suppressing the formation of paraelectric phase and polarization degradation. The design ensures a fatigue-free feature exceeding 10^11 switching cycles and an endurance lifetime surpassing 10^12 cycles for Hf0.5Zr0.5O2-based capacitors, along with excellent temperature stability and retention. These findings pave the way for developing ultra-stable hafnia-based ferroelectric devices.

cond-mat.mtrl-sci↗

arXiv2024

Unveiling Visual Perception in Language Models: An Attention Head Analysis Approach

Recent advancements in Multimodal Large Language Models (MLLMs) have demonstrated remarkable progress in visual understanding. This impressive leap raises a compelling question: how can language models, initially trained solely on linguistic data, effectively interpret and process visual content? This paper aims to address this question with systematic investigation across 4 model families and 4 model scales, uncovering a unique class of attention heads that focus specifically on visual content. Our analysis reveals a strong correlation between the behavior of these attention heads, the distribution of attention weights, and their concentration on visual tokens within the input. These findings enhance our understanding of how LLMs adapt to multimodal tasks, demonstrating their potential to bridge the gap between textual and visual understanding. This work paves the way for the development of AI systems capable of engaging with diverse modalities.

cs.CV↗

arXiv2024

Scaling Concept With Text-Guided Diffusion Models

Text-guided diffusion models have revolutionized generative tasks by producing high-fidelity content from text descriptions. They have also enabled an editing paradigm where concepts can be replaced through text conditioning (e.g., a dog to a tiger). In this work, we explore a novel approach: instead of replacing a concept, can we enhance or suppress the concept itself? Through an empirical study, we identify a trend where concepts can be decomposed in text-guided diffusion models. Leveraging this insight, we introduce ScalingConcept, a simple yet effective method to scale decomposed concepts up or down in real input without introducing new elements. To systematically evaluate our approach, we present the WeakConcept-10 dataset, where concepts are imperfect and need to be enhanced. More importantly, ScalingConcept enables a variety of novel zero-shot applications across image and audio domains, including tasks such as canonical pose generation and generative sound highlighting or removal.

cs.CV↗

arXiv2024

Large Enhancement of Properties in Strained Lead-free Multiferroic Solid Solutions with Strong Deviation from Vegard's Law

Efforts to combine the advantages of multiple systems to enhance functionlities through solid solution design present a great challenge due to the constraint imposed by the classical Vegard law. Here, we successfully navigate this trade off by leveraging the synergistic effect of chemical doping and strain engineering in solid solution system of BiFeO3 BaTiO3. Unlike bulks, a significant deviation from the Vegard law accompanying with enhanced multiferroism is observed in the strained solid solution epitaxial films, where we achieve a pronounced tetragonality, enhanced saturated magnetization, substantial polarization, high ferroelectric Curie temperature, all while maintaining impressively low leakage current. These characteristics surpass the properties of their parent BiFeO3 and BaTiO3 films. Moreover, the superior ferroelectricity has never been reported in corresponding bulks. These findings underscore the potential of strained BiFeO3 BaTiO3 films as lead-free, room-temperature multiferroics.

cond-mat.mtrl-sci↗