arXiv subjects

Shuxiang Zhang

Publications and source records attributed to Shuxiang Zhang.

5 recordsLinked to original sources

arXiv2026

PIPBench: A Profile-Inclusive Framework for Personalized Image Generation Evaluation

Recent text-to-image models such as DALLE-3 excel at following diverse prompts yet remain blind to individual aesthetic preferences. We study personalized image generation, where models must align outputs with a user's implicit visual preferences based on a few historically preferred images and a short prompt. To this end, we introduce PIPBench, the first profile-inclusive benchmark for evaluating personalized image generation. We further propose a novel data construction pipeline that leverages psychological and demographic profiling dimensions for both real-user data collection and scalable agent-based data generation. Using PIPBench, we conduct a thorough evaluation of representative line of methods. Our experiments reveal key limitations in existing methods, suggesting new challenges and opportunities for personalized text-to-image synthesis. Project page: https://wuyuhang05.github.io/PIPBench/

cs.CV↗

arXiv2026

PIVOTSBench: Evaluating Fine-Grained Interpersonal Relationship Reasoning in Multimodal Large Language Models

Humans possess an innate ability to understand fine-grained interpersonal relationships, which is central to everyday social interactions. Although such reasoning is inherently multimodal, it remains largely unexplored by existing multimodal large language models (MLLMs). To address this gap, we introduce PIVOTS, the first benchmark built from Social-IQ 2.0 and YouTube data to evaluate MLLMs' ability to predict bidirectional interpersonal relationship dimensions grounded in established psychology research. In addition, PIVOTS includes auxiliary tasks that assess models' ability to identify and leverage the critical visual cues underlying such predictions. We evaluate both proprietary and open-source MLLMs and conduct detailed ablation studies to analyze the effects of visual modalities and explicit social role information in conversational utterances. We further examine how joint and pairwise prediction settings benefit MLLMs in scoring bidirectional PIVOTS dimensions. Project page: https://ciossayin.github.io/pivots-bench/

cs.CL↗

arXiv2025

In-Situ Tweedie Discrete Diffusion Models

While diffusion models excel at generating continuous data such as images, adapting them to discrete tasks has relied on indirect approaches that either operate in continuous embedding spaces or use token masking mechanisms, both of which deviate from modeling the true discrete data distribution that can be theoretically guaranteed by Tweedie's formula. We propose in-situ Tweedie Discrete Diffusion (TDD), a framework that performs diffusion guaranteed by Tweedie's formula directly within the discrete one-hot space, hence "in-situ." Unlike prior methods that diffuse continuous embeddings or mask tokens, TDD directly corrupts one-hot vectors with Gaussian noise and performs iterative denoising through a timestep-conditioned cross-entropy objective rather than mean-squared-error reconstruction. At each denoising step, the model predicts class probabilities, applies argmax to obtain discrete predictions, converts them to one-hot vectors, and feeds them into the next iteration with progressively reduced noise. This process naturally unifies discriminative classification and generative modeling under a single framework. Experiments demonstrate that TDD achieves strong performance on both image classification and text generation tasks, with extensive ablation studies confirming the effectiveness of each design component. Our work establishes a principled approach to discrete diffusion that preserves the core characteristics of diffusion models while operating natively in discrete space.

cs.CV↗

arXiv2023

Cross-correlated quantum thermometry using diamond containing dual-defect centers

The contactless temperature measurement at micro/nanoscale is vital to a broad range of fields in modern science and technology. The nitrogen vacancy (NV) center, a kind of diamond defect with unique spin-dependent photoluminescence, has been recognized as one of the most promising nanothermometers. However, this quantum thermometry technique has been prone to a number of possible perturbations, which will unavoidably degrade its actual temperature sensitivity. Here, for the first time, we have developed a cross-validated optical thermometry method using a bulk diamond sample containing both NV centers and silicon vacancy (SiV) centers. Particularly, the latter allowing all-optical method has been intrinsically immune to those influencing perturbations for the NV-based quantum thermometry, hence serving as a real-time cross validation system. As a proof-of-concept demonstration, we have shown a trustworthy temperature measurement under the influence of varying magnetic fields. This multi-modality approach allows a synchronized cross-validation of the measured temperature, which is required for micro/nanoscale quantum thermometry in complicated environments such as a living cell.

quant-ph↗

arXiv2023

Quantum-Enhanced Diamond Molecular Tension Microscopy for Quantifying Cellular Forces

The constant interplay and information exchange between cells and their micro-environment are essential to their survival and ability to execute biological functions. To date, a few leading technologies such as traction force microscopy, have been broadly used in measuring cellular forces. However, the considerable limitations, regarding the sensitivity and ambiguities in data interpretation, are hindering our thorough understanding of mechanobiology. Herein, we propose an innovative approach, namely quantum-enhanced diamond molecular tension microscopy (QDMTM), to precisely quantify the integrin-based cell adhesive forces. Specifically, we construct a force sensing platform by conjugating the magnetic nanotags labeled, force-responsive polymer to the surface of diamond membrane containing nitrogen vacancy (NV) centers. Thus, the coupled mechanical information can be quantified through optical readout of spin relaxation of NV centers modulated by those magnetic nanotags. To validate QDMTM, we have carefully performed corresponding measurements both in control and real cell samples. Particularly, we have obtained the quantitative cellular adhesion force mapping by correlating the measurement with established theoretical model. We anticipate that our method can be routinely used in studying important issues like cell-cell or cell-material interactions and mechanotransduction.

q-bio.CB↗