arXiv subjects

Yi Zhang

Publications and source records attributed to Yi Zhang.

At least 325 records · Page 18Linked to original sources

arXiv2026

Mirage: Transmitting a Video as a Perceptual Illusion for 50,000X Speedup

The existing communication framework mainly aims at accurate reconstruction of source signals to ensure reliable transmission. However, this signal-level fidelity-oriented design often incurs high communication overhead and system complexity, particularly in video communication scenarios where mainstream frameworks rely on transmitting visual data itself, resulting in significant bandwidth consumption. To address this issue, we propose a visual data-free communication framework, Mirage, for extremely efficient video transmission while preserving semantic information. Mirage decomposes video content into two complementary components: temporal sequence information capturing motion dynamics and spatial appearance representations describing overall visual structure. Temporal information is preserved through video captioning, while key frames are encoded into compact semantic representations for spatial appearance. These representations are transmitted to the receiver, where videos are synthesized using generative video models. Since no raw visual data is transmitted, Mirage is inherently privacy-preserving. Mirage also supports personalized adaptation across deployment scenarios. The sender, network, and receiver can independently impose constraints on semantic representation, transmission, and generation, enabling flexible trade-offs between efficiency, privacy, control, and perceptual quality. Experimental results in video transmission demonstrate that Mirage achieves up to a 50000X data-level compression speedup over raw video transmission, with gains expected to scale with larger video content sizes.

cs.NI↗

arXiv2026

Learning to Self-Verify Makes Language Models Better Reasoners

Recent large language models (LLMs) achieve strong performance in generating promising reasoning paths for complex tasks. However, despite powerful generation ability, LLMs remain weak at verifying their own answers, revealing a persistent capability asymmetry between generation and self-verification. In this work, we conduct an in-depth investigation of this asymmetry throughout training evolution and show that, even on the same task, improving generation does not lead to corresponding improvements in self-verification. Interestingly, we find that the reverse direction of this asymmetry behaves differently: learning to self-verify can effectively improve generation performance, achieving accuracy comparable to standard generation training while yielding more efficient and effective reasoning traces. Building on this observation, we further explore integrating self-verification into generation training by formulating a multi-task reinforcement learning framework, where generation and self-verification are optimized as two independent but complementary objectives. Extensive experiments across benchmarks and models demonstrate performance gains over generation-only training in both generation and verification capabilities.

cs.CL↗

arXiv2026

CA-YOLO: Cross Attention Empowered YOLO for Biomimetic Localization

In modern complex environments, achieving accurate and efficient target localization is essential in numerous fields. However, existing systems often face limitations in both accuracy and the ability to recognize small targets. In this study, we propose a bionic stabilized localization system based on CA-YOLO, designed to enhance both target localization accuracy and small target recognition capabilities. Acting as the "brain" of the system, the target detection algorithm emulates the visual focusing mechanism of animals by integrating bionic modules into the YOLO backbone network. These modules include the introduction of a small target detection head and the development of a Characteristic Fusion Attention Mechanism (CFAM). Furthermore, drawing inspiration from the human Vestibulo-Ocular Reflex (VOR), a bionic pan-tilt tracking control strategy is developed, which incorporates central positioning, stability optimization, adaptive control coefficient adjustment, and an intelligent recapture function. The experimental results show that CA-YOLO outperforms the original model on standard datasets (COCO and VisDrone), with average accuracy metrics improved by 3.94%and 4.90%, respectively.Further time-sensitive target localization experiments validate the effectiveness and practicality of this bionic stabilized localization system.

cs.CV↗

arXiv2026

The Standard siren tests of viable $f(R)$ cosmologies

We constrain the Hu-Sawicki and Starobinsky $f(R)$ gravity models utilizing current electromagnetic (PP+CC, Planck and DESI2) datasets and simulate standard siren catalogs based on the resulting best-fit parameters. We demonstrate that the simulated SS data provide complementary sensitivity to the modified gravitational wave propagation friction term, thereby enhancing the discriminating power between $f(R)$ gravity and the $Λ$CDM model. However, we note that standard sirens do not offer a viable resolution to the Hubble tension in this analysis, as the inferred constraints are predominantly driven by the fiducial cosmologies adopted in the simulations. Regarding the specific models, we find that for the Hu-Sawicki scenario, several data combinations favor $F_{RR0}<0$, implying potential theoretical instabilities. And, for the Starobinsky model, while EM-only constraints are nearly symmetric between the two parameter branches ($b<0$ and $b>0$), the inclusion of SS constraints introduces mild asymmetries, revealing the sensitivity of SS observables to the curvature dependence of the theory. Future truly independent standard siren observations would be crucial for a definitive assessment of $f(R)$ gravity as an alternative to $Λ$CDM.

astro-ph.CO↗

arXiv2026

Polygons and multi-product of eigenfunctions

Let $M$ be a compact Riemannian manifold without boundary, with $L^2$-normalized Laplace-Beltrami eigenfunctions $\{e_j\}_j$, which satisfy $Δ_g e_j = -λ_j^2 e_j$. We study the following inner product of eigenfunctions \[ \langle e_{i_1} e_{i_2} \ldots e_{i_k}, e_{i_{k+1}} \rangle = \int e_{i_1} e_{i_2}\ldots e_{i_k} \overline{e_{i_{k+1}}} \, dV. \] We show that, after a mild averaging in the frequency variables, the main $\ell^2$-concentration of this inner product is determined by the measure of a set of configurations of $(k+1)$-gons whose side lengths are the frequencies $λ_{i_1}, λ_{i_2}, \dots, λ_{i_{k+1}}$. We prove that a rapidly vanishing proportion of this mass lies in the regime where $λ_{i_1}, λ_{i_2}, \dots, λ_{i_{k+1}}$ cannot occur as the side lengths of any $(k+1)$-gon.

math.AP↗

arXiv2026

A2Eval: Agentic and Automated Evaluation for Embodied Brain

Current embodied VLM evaluation relies on static, expert-defined, manually annotated benchmarks that exhibit severe redundancy and coverage imbalance. This labor intensive paradigm drains computational and annotation resources, inflates costs, and distorts model rankings, ultimately stifling iterative development. To address this, we propose Agentic Automatic Evaluation (A2Eval), the first agentic framework that automates benchmark curation and evaluation through two collaborative agents. The Data Agent autonomously induces capability dimensions and assembles a balanced, compact evaluation suite, while the Eval Agent synthesizes and validates executable evaluation pipelines, enabling fully autonomous, high-fidelity assessment. Evaluated across 10 benchmarks and 13 models, A2Eval compresses evaluation suites by 85%, reduces overall computational costs by 77%, and delivers a 4.6x speedup while preserving evaluation quality. Crucially, A2Eval corrects systematic ranking biases, improves human alignment to Spearman's rho=0.85, and maintains high ranking fidelity (Kendall's tau=0.81), establishing a new standard for high-fidelity, low-cost embodied assessment. Our code and data will be public soon.

cs.CL↗

arXiv2026

ExpAlign: Expectation-Guided Vision-Language Alignment for Open-Vocabulary Grounding

Open-vocabulary grounding requires accurate vision-language alignment under weak supervision, yet existing methods either rely on global sentence embeddings that lack fine-grained expressiveness or introduce token-level alignment with explicit supervision or heavy cross-attention designs. We propose ExpAlign, a theoretically grounded vision-language alignment framework built on a principled multiple instance learning formulation. ExpAlign introduces an Expectation Alignment Head that performs attention-based soft MIL pooling over token-region similarities, enabling implicit token and instance selection without additional annotations. To further stabilize alignment learning, we develop an energy-based multi-scale consistency regularization scheme, including a Top-K multi-positive contrastive objective and a Geometry-Aware Consistency Objective derived from a Lagrangian-constrained free-energy minimization. Extensive experiments show that ExpAlign consistently improves open-vocabulary detection and zero-shot instance segmentation, particularly on long-tail categories. Most notably, it achieves 36.2 AP$_r$ on the LVIS minival split, outperforming other state-of-the-art methods at comparable model scale, while remaining lightweight and inference-efficient.

cs.CV↗

arXiv2026

Training-Free Test-Time Adaptation with Brownian Distance Covariance in Vision-Language Models

Vision-language models suffer performance degradation under domain shift, limiting real-world applicability. Existing test-time adaptation methods are computationally intensive, rely on back-propagation, and often focus on single modalities. To address these issues, we propose Training-free Test-Time Adaptation with Brownian Distance Covariance (TaTa). TaTa leverages Brownian Distance Covariance-a powerful statistical measure that captures both linear and nonlinear dependencies via pairwise distances-to dynamically adapt VLMs to new domains without training or back-propagation. This not only improves efficiency but also enhances stability by avoiding disruptive weight updates. TaTa further integrates attribute-enhanced prompting to improve vision-language inference with descriptive visual cues. Combined with dynamic clustering and pseudo-label refinement, it effectively recalibrates the model for novel visual contexts. Experiments across diverse datasets show that TaTa significantly reduces computational cost while achieving state-of-the-art performance in domain and cross-dataset generalization.

cs.CV↗

arXiv2026

MM-OpenFGL: A Comprehensive Benchmark for Multimodal Federated Graph Learning

Multimodal-attributed graphs (MMAGs) provide a unified framework for modeling complex relational data by integrating heterogeneous modalities with graph structures. While centralized learning has shown promising performance, MMAGs in real-world applications are often distributed across isolated platforms and cannot be shared due to privacy concerns or commercial constraints. Federated graph learning (FGL) offers a natural solution for collaborative training under such settings; however, existing studies largely focus on single-modality graphs and do not adequately address the challenges unique to multimodal federated graph learning (MMFGL). To bridge this gap, we present MM-OpenFGL, the first comprehensive benchmark that systematically formalizes the MMFGL paradigm and enables rigorous evaluation. MM-OpenFGL comprises 19 multimodal datasets spanning 7 application domains, 8 simulation strategies capturing modality and topology variations, 6 downstream tasks, and 57 state-of-the-art methods implemented through a modular API. Extensive experiments investigate MMFGL from the perspectives of necessity, effectiveness, robustness, and efficiency, offering valuable insights for future research on MMFGL.

cs.LG↗

arXiv2026

HetGCoT: Heterogeneous Graph-Enhanced Chain-of-Thought LLM Reasoning for Academic Question Answering

Academic question answering (QA) in heterogeneous scholarly networks presents unique challenges requiring both structural understanding and interpretable reasoning. While graph neural networks (GNNs) capture structured graph information and large language models (LLMs) demonstrate strong capabilities in semantic comprehension, current approaches lack integration at the reasoning level. We propose HetGCoT, a framework enabling LLMs to effectively leverage and learn information from graphs to reason interpretable academic QA results. Our framework introduces three technical contributions: (1) a framework that transforms heterogeneous graph structural information into LLM-processable reasoning chains, (2) an adaptive metapath selection mechanism identifying relevant subgraphs for specific queries, and (3) a multi-step reasoning strategy systematically incorporating graph contexts into the reasoning process. Experiments on OpenAlex and DBLP datasets show our approach outperforms all sota baselines. The framework demonstrates adaptability across different LLM architectures and applicability to various scholarly question answering tasks.

cs.SI↗

arXiv2026

PLawBench: A Rubric-Based Benchmark for Evaluating LLMs in Real-World Legal Practice

As large language models (LLMs) are increasingly applied to legal domain-specific tasks, evaluating their ability to perform legal work in real-world settings has become essential. However, existing legal benchmarks rely on simplified and highly standardized tasks, failing to capture the ambiguity, complexity, and reasoning demands of real legal practice. Moreover, prior evaluations often adopt coarse, single-dimensional metrics and do not explicitly assess fine-grained legal reasoning. To address these limitations, we introduce PLawBench, a Practical Law Benchmark designed to evaluate LLMs in realistic legal practice scenarios. Grounded in real-world legal workflows, PLawBench models the core processes of legal practitioners through three task categories: public legal consultation, practical case analysis, and legal document generation. These tasks assess a model's ability to identify legal issues and key facts, perform structured legal reasoning, and generate legally coherent documents. PLawBench comprises 850 questions across 13 practical legal scenarios, with each question accompanied by expert-designed evaluation rubrics, resulting in approximately 12,500 rubric items for fine-grained assessment. Using an LLM-based evaluator aligned with human expert judgments, we evaluate 10 state-of-the-art LLMs. Experimental results show that none achieves strong performance on PLawBench, revealing substantial limitations in the fine-grained legal reasoning capabilities of current LLMs and highlighting important directions for future evaluation and development of legal LLMs. Data is available at: https://github.com/skylenage/PLawbench.

cs.CL↗

arXiv2026

Feature Projection Learning for Better Vision-Language Reasoning

Vision-Language Pre-Trained models, notably CLIP, that utilize contrastive learning have proven highly adept at extracting generalizable visual features. To inherit the well-learned knowledge of VLP models for downstream tasks, several approaches aim to adapt them efficiently with limited supervision. However, these methods either suffer from limited performance, excessive learnable parameters, or extended training times, all of which hinder their effectiveness in adapting the CLIP model to downstream tasks. In this work, we propose a simple yet efficient and effective method called \textit{\textbf{F}eature \textbf{P}rojection \textbf{L}earning(FPL)} to address these problems. Specifically, we develop a projection model that projects class prototype features into the query image feature space and reconstructs the query image feature map. The negative average squared reconstruction error is used as the class score. In this way, we transform the classification problem into a feature projection problem. The final output of this method is a combination of the prediction from the projection model and the original pre-trained CLIP. Comprehensive empirical evaluations confirm that FPL delivers superior accuracy, surpassing the current state-of-the-art methods by a substantial margin.

cs.CV↗

arXiv2026

PalmBridge: A Plug-and-Play Feature Alignment Framework for Open-Set Palmprint Verification

Palmprint recognition is widely used in biometric systems, yet real-world performance often degrades due to feature distribution shifts caused by heterogeneous deployment conditions. Most deep palmprint models assume a closed and stationary distribution, leading to overfitting to dataset-specific textures rather than learning domain-invariant representations. Although data augmentation is commonly used to mitigate this issue, it assumes augmented samples can approximate the target deployment distribution, an assumption that often fails under significant domain mismatch. To address this limitation, we propose PalmBridge, a plug-and-play feature-space alignment framework for open-set palmprint verification based on vector quantization. Rather than relying solely on data-level augmentation, PalmBridge learns a compact set of representative vectors directly from training features. During enrollment and verification, each feature vector is mapped to its nearest representative vector under a minimum-distance criterion, and the mapped vector is then blended with the original vector. This design suppresses nuisance variation induced by domain shifts while retaining discriminative identity cues. The representative vectors are jointly optimized with the backbone network using task supervision, a feature-consistency objective, and an orthogonality regularization term to form a stable and well-structured shared embedding space. Furthermore, we analyze feature-to-representative mappings via assignment consistency and collision rate to assess model's sensitivity to blending weights. Experiments on multiple palmprint datasets and backbone architectures show that PalmBridge consistently reduces EER in intra-dataset open-set evaluation and improves cross-dataset generalization with negligible to modest runtime overhead.

cs.CV↗

arXiv2026

A Style-Based Profiling Framework for Quantifying the Synthetic-to-Real Gap in Autonomous Driving Datasets

Ensuring the reliability of autonomous driving perception systems requires extensive environment-based testing, yet real-world execution is often impractical. Synthetic datasets have therefore emerged as a promising alternative, offering advantages such as cost-effectiveness, bias free labeling, and controllable scenarios. However, the domain gap between synthetic and real-world datasets remains a major obstacle to model generalization. To address this challenge from a data-centric perspective, this paper introduces a profile extraction and discovery framework for characterizing the style profiles underlying both synthetic and real image datasets. We propose Style Embedding Distribution Discrepancy (SEDD) as a novel evaluation metric. Our framework combines Gram matrix-based style extraction with metric learning optimized for intra-class compactness and inter-class separation to extract style embeddings. Furthermore, we establish a benchmark using publicly available datasets. Experiments are conducted on a variety of datasets and sim-to-real methods, and the results show that our method is capable of quantifying the synthetic-to-real gap. This work provides a standardized profiling-based quality control paradigm that enables systematic diagnosis and targeted enhancement of synthetic datasets, advancing future development of data-driven autonomous driving systems.

cs.CV↗

arXiv2026

PromptPrism: A Linguistically-Inspired Taxonomy for Prompts

Prompts are the interface for eliciting the capabilities of large language models (LLMs). Understanding their structure and components is critical for analyzing LLM behavior and optimizing performance. However, the field lacks a comprehensive framework for systematic prompt analysis and understanding. We introduce PromptPrism, a linguistically-inspired taxonomy that enables prompt analysis across three hierarchical levels: functional structure, semantic component, and syntactic pattern. By applying linguistic concepts to prompt analysis, PromptPrism bridges traditional language understanding and modern LLM research, offering insights that purely empirical approaches might miss. We show the practical utility of PromptPrism by applying it to three applications: (1) a taxonomy-guided prompt refinement approach that automatically improves prompt quality and enhances model performance across a range of tasks; (2) a multi-dimensional dataset profiling method that extracts and aggregates structural, semantic, and syntactic characteristics from prompt datasets, enabling comprehensive analysis of prompt distributions and patterns; (3) a controlled experimental framework for prompt sensitivity analysis by quantifying the impact of semantic reordering and delimiter modifications on LLM performance. Our experimental results validate the effectiveness of our taxonomy across these applications, demonstrating that PromptPrism provides a foundation for refining, profiling, and analyzing prompts.

cs.CL↗

arXiv2026

Coherent Mode Decoupling: A Versatile Framework for High-Throughput Partially Coherent Light Transport

Accurate and efficient wave-optics simulation of partially coherent light transport systems is critical for the design of advanced optical systems, ranging from computational lithography to diffraction-limited storage rings (DLSR). However, traditional approaches based on Coherent Mode Decomposition suffer from high computational costs due to the propagating massive sets of two-dimensional modes. In this paper, we propose the Coherent Mode Decoupling (CMDC) algorithm, a high-throughput computational framework designed to accelerate these simulations by orders of magnitude without compromising physical fidelity. The method factorizes 2D modes into efficient one-dimensional (1D) components, while crucially incorporating a subspace compression strategy to capture non-separable coupling effects. We demonstrated the generality and robustness of this framework in applications ranging from computational lithography to coherent beamlines of DLSR.

physics.optics↗

arXiv2026

De novo design of protein binders targeting the human sweet taste receptor as potential sweet proteins

Excessive consumption of dietary sugars is a major contributor to metabolic disorders, driving global interest in finding alternative sweeteners with reduced caloric impact. Natural sweet proteins, such as brazzein, offer exceptional sweetness intensity with little caloric contribution. However, their widespread use is limited by restricted natural diversity, low stability, and high production costs. Recent advances in structural biology and de novo protein design provide new opportunities to overcome these limitations through rational engineering. In this study, we report an integrated computational pipeline for the de novo design of protein binders targeting the human sweet taste receptor subunit TAS1R2, a key component of the heterodimeric class C G protein-coupled receptor mediating sweetness perception. The workflow combines diffusion-based backbone generation (RFdiffusion), neural network-guided sequence design (ProteinMPNN), structure-based filtering using Boltz-1, and binding energy evaluation via MM/GBSA calculations. Using the recently resolved cryo-EM structure of the TAS1R2 receptor, protein binders were designed to target both the Venus Flytrap Domain and the cysteine-rich domain of TAS1R2. A few designed binders exhibited favorable structural confidence and predicted binding energetics. In particular, Binder2 exhibited brazzein-like structural plausibility through specific short-range CRD contacts, while Binder1 displayed the strongest predicted binding affinity. Structural analyses of the binder-receptor complex revealed distinct binding modes and secondary structure profiles among the designs. This study demonstrates the feasibility of de novo designing protein binders that emulate key functional properties of natural sweet proteins, establishing a computational framework for the rational development of next-generation protein-based sweeteners.

q-bio.BM↗

arXiv2026

VILTA: A VLM-in-the-Loop Adversary for Enhancing Driving Policy Robustness

The safe deployment of autonomous driving (AD) systems is fundamentally hindered by the long-tail problem, where rare yet critical driving scenarios are severely underrepresented in real-world data. Existing solutions including safety-critical scenario generation and closed-loop learning often rely on rule-based heuristics, resampling methods and generative models learned from offline datasets, limiting their ability to produce diverse and novel challenges. While recent works leverage Vision Language Models (VLMs) to produce scene descriptions that guide a separate, downstream model in generating hazardous trajectories for agents, such two-stage framework constrains the generative potential of VLMs, as the diversity of the final trajectories is ultimately limited by the generalization ceiling of the downstream algorithm. To overcome these limitations, we introduce VILTA (VLM-In-the-Loop Trajectory Adversary), a novel framework that integrates a VLM into the closed-loop training of AD agents. Unlike prior works, VILTA actively participates in the training loop by comprehending the dynamic driving environment and strategically generating challenging scenarios through direct, fine-grained editing of surrounding agents' future trajectories. This direct-editing approach fully leverages the VLM's powerful generalization capabilities to create a diverse curriculum of plausible yet challenging scenarios that extend beyond the scope of traditional methods. We demonstrate that our approach substantially enhances the safety and robustness of the resulting AD policy, particularly in its ability to navigate critical long-tail events.

cs.CV↗