arXiv subjects

Suwen Wang

Publications and source records attributed to Suwen Wang.

8 recordsLinked to original sources

arXiv2026

MIBE: Multi-subject Interaction Benchmark and Evaluator for Personalized Image Generation

Multi-subject personalized image generation requires the precise rendering of all requested reference identities and their specified interactions based on a guiding prompt. However, state-of-the-art models still struggle with this process, frequently omitting subjects, failing to preserve reference appearances, or misattributing interactions. Furthermore, existing metrics designed primarily for single-subject fidelity cannot reliably capture these errors, suffering severe degradation in ranking separability and failing to align with human preference as the subject count increases. To address this gap, we introduce Multi-subject Interaction Benchmark and Evaluator (MIBE), a unified framework comprising a Multi-subject Interaction Benchmark (MIB) and a Multi-subject Interaction Evaluator (MIE). MIB systematically covers diverse relation types and scene complexities through a decoupled data regime. This consists of a 60K-pair VLM-labeled Silver Set for scalable metric training and a 4K-pair double-blind Human Evaluation Gold Set covering a diverse range of state-of-the-art generators, with the Silver Set reaching 95.1% cross-VLM preference agreement. To demonstrate the utility of this benchmark, we present MIE, a lightweight, reference-conditioned evaluator trained exclusively on the Silver Set with a dual-head ranking and diagnosis objective. MIE exhibits strong cross-generator generalization on the Gold Set, achieving 0.922 overall pairwise accuracy against human preference, including 0.982 on seen generators and 0.884 on unseen generators. By outperforming a broad spectrum of baseline metrics, including CLIP and DINO variants, MIE demonstrates that diagnostic supervision can preserve ranking separability and human alignment where traditional evaluators collapse.

cs.CV↗

arXiv2026

EASE-TTT: Evidence-Aligned Selective Test-Time Training for Long-Context Question Answering

Long-context question answering (QA) remains challenging for smaller language models even when answer-bearing evidence is already present in the input. Existing within-context retrieval methods localize and expose candidate evidence chunks for the question, but they stop at input-level evidence exposure rather than adapting the query-side attention parameters that control how the model allocates attention over full-context positions. In contrast, lightweight test-time adaptation methods, such as query-only test-time training (qTTT), leave evidence localization unresolved because their generic span-level self-supervised objectives do not identify which context positions support the current answer. In this paper, we propose Evidence-Aligned SElective Test-Time Training (EASE-TTT), a within-context retrieval-augmented test-time training framework that converts selected evidence chunks into a soft attention supervision target over their token positions. Instead of replacing the full context with retrieved chunks, EASE-TTT uses the resulting attention target to guide query-side adaptation, with the adapted model generating the final answer from the original full context. Experiments on six LongBench QA tasks and three small decoder-only language models show that EASE-TTT achieves the strongest macro-average performance among full-context inference, retrieval-only baselines, and qTTT, supporting evidence-aligned test-time adaptation in long-context QA.

cs.CL↗

arXiv2025

Long-wavelength UV-LEDs and charge management in the detection of gravitational waves in space

For the charge management system in gravitational wave detection missions, a continuous discharge strategy is considered by continuously illuminating a test mass (TM) with weak light in such a way to strike a balance between the charging and discharging rates and at the same time avoids the requirement for frequent activation of charge measurements. Built on experiments by one of us based on a simple parallel plate model for inertial sensor, in the present work a more sophisticated inertial sensor model that mimics the surface properties and work function of a cubical TM of an inertial sensor in space (like that of the LISA Pathfinder) is employed to study bipolar charge management system that utilizes UV-LEDs with peak wavelengths of 269 nm, 275 nm, 280 nm, and 295 nm that are longer than the standard 255 nm commonly employed for direct TM illumination. Experimental results indicate that the 275 nm UV-LED achieves optimal performance, maintaining the TM potential closer to zero and at the same time accommodates both rapid discharge and continuous discharge strategies. The present work provides useful input in the future study of system design and optimization for the charge management system.

gr-qc↗

arXiv2025

A Passive UV-Based System for Discharging the Test Masses of Ground Based Gravitational Wave Detectors

We present a passive ultraviolet charge management system for the fused silica test masses in ground-based laser interferometric gravitational wave detectors. The system uses photoelectron emission from low work-function gold coatings illuminated by 275 to 285 nm UV light to neutralize unwanted electric charges on the electrically floating test masses, maintaining them at zero potential relative to surrounding components. Two implementation schemes are described: 1. distributed discharge tabs illuminated by UV LEDs mounted at the eight surrounding earthquake stops, and 2. a conductively linked tab design enabling a centralized discharge on the test mass barrel, with potential extension to annular coatings around the high-reflectivity and anti-reflective surfaces. Experimental results show photoelectric currents greater or equal to 10 pA for 1.0 mW of incident UV, enabling discharge rates greater than 10V/s for a 1 pF capacitance. With 0.2 mW UV power, charge neutralization to less or equal to 1 pC can be achieved in 5 to 75 minutes. This technique offers a vacuum-compatible alternative to ion sprayers, significantly reducing operational downtime. For the conductive-barrel configuration, we also propose a balanced electrostatic actuator using four parallel-plate capacitors for combined control of TM axial displacement, tilt, and azimuth, with reduced drive voltages.

physics.ins-det↗

arXiv2025

Test mass charge management in the detection of gravitational waves in space based on UV micro-LED

As an alternative to the ultraviolet light emitting diode(UV LED), the feasibility of utilizing UV micro-LED in the charge management in the detection of gravitational waves in space is experimentally studied. Compared with UV LED, micro-LED is more compact in size, has better current spreading, faster response time and longer operating life. Performance characteristics of micro-LEDs were measured, with peak wavelength of 254 nm, 262 nm, 274 nm, and 282 nm for each respective micro-LED, and the photoelectric effect was demonstrated. The effectiveness of micro-LED based charge management experiments were demonstrated using above micro-LEDs mounted on a cubical test mass, and different discharge rates were achieved by varying the drive current and duty cycle using pulse width modulation(PWM). Laboratory data was also shown to demonstrate the space qualification of the micro-LED device, the key electrical and optical characteristics of the micro-LEDs showed less than 5% variation. The results of the qualification bring the micro-LED device Technology Readiness Level(TRL) to TRL-5. TRL-6 will be reached provided additional radiation and thermal tests are conducted and in a position ready to be flown and further tested in space.

physics.ins-det↗

arXiv2023

Emotional Reaction Intensity Estimation Based on Multimodal Data

This paper introduces our method for the Emotional Reaction Intensity (ERI) Estimation Challenge, in CVPR 2023: 5th Workshop and Competition on Affective Behavior Analysis in-the-wild (ABAW). Based on the multimodal data provided by the originazers, we extract acoustic and visual features with different pretrained models. The multimodal features are mixed together by Transformer Encoders with cross-modal attention mechnism. In this paper, 1. better features are extracted with the SOTA pretrained models. 2. Compared with the baseline, we improve the Pearson's Correlations Coefficient a lot. 3. We process the data with some special skills to enhance performance ability of our model.

cs.CV↗

arXiv2023

A Step Toward Deep Online Aggregation (Extended Version)

For exploratory data analysis, it is often desirable to know what answers you are likely to get before actually obtaining those answers. This can potentially be achieved by designing systems to offer the estimates of a data operation result -- say op(data) -- earlier in the process based on partial data processing. Those estimates continuously refine as more data is processed and finally converge to the exact answer. Unfortunately, the existing techniques -- called Online Aggregation (OLA) -- are limited to a single operation; that is, we cannot obtain the estimates for op(op(data)) or op(...(op(data))). If this Deep OLA becomes possible, data analysts will be able to explore data more interactively using complex cascade operations. In this work, we take a step toward Deep OLA with evolving data frames (edf), a novel data model to offer OLA for nested ops -- op(...(op(data))) -- by representing an evolving structured data (with converging estimates) that is closed under set operations. That is, op(edf) produces yet another edf; thus, we can freely apply successive operations to edf and obtain an OLA output for each op. We evaluate its viability with Wake, an edf-based OLA system, by examining against state-of-the-art OLA and non-OLA systems. In our experiments on TPC-H dataset, Wake produces its first estimates 4.93x faster (median) -- with 1.3x median slowdown for exact answers -- compared to conventional systems. Besides its generality, Wake is also 1.92x faster (median) than existing OLA systems in producing estimates of under 1% relative errors.

cs.DB↗

arXiv2012

Corner-cube retro-reflector instrument for advanced lunar laser ranging

Lunar laser ranging (LLR) has made major contributions to our understanding of the Moon's internal structure and the dynamics of the Earth-Moon system. Because of the recent improvements of the ground-based laser ranging facilities, the present LLR measurement accuracy is limited by the retro-reflectors currently on the lunar surface, which are arrays of small corner-cubes. Because of lunar librations, the surfaces of these arrays do not, in general, point directly at the Earth. This effect results in a spread of arrival times, because each cube that comprises the retroreflector is at a slightly different distance from the Earth, leading to the reduced ranging accuracy. Thus, a single, wide aperture corner-cube could have a clear advantage. In addition, after nearly four decades of successful operations the retro-reflectors arrays currently on the Moon started to show performance degradation; as a result, they yield still useful, but much weaker return signals. Thus, fresh and bright instruments on the lunar surface are needed to continue precision LLR measurements. We have developed a new retro-reflector design to enable advanced LLR operations. It is based on a single, hollow corner cube with a large aperture for which preliminary thermal, mechanical, and optical design and analysis have been performed. The new instrument will be able to reach an Earth-Moon range precision of 1-mm in a single pulse while being subjected to significant thermal variations present on the lunar surface, and will have low mass to allow robotic deployment. Here we report on our design results and instrument development effort.

physics.ins-det↗