Yang Ding

Yang Ding, Ning Zhang, Helen Bao et al.

While female representation in social sciences is increasing, systemic gender disparities may persist in research funding and academic performance. Some argue that female scholars now receive equal opportunities, yet evidence suggests that gender imbalances remain, particularly in specific research areas. This study examines 12,945 National Science Foundation (NSF)-funded principal investigators in social sciences from 2000 to 2019 to assess gender disparities in grant allocation, research topics, and post-award academic performance. Findings reveal a dual imbalance. First, despite similar overall funding success rates, female scholars remain underrepresented in high-impact and traditionally male-dominated research topics. Males dominate most funded topics, especially STEM-related ones, while female-led topics align with traditional gender stereotypes. Second, post-award performance patterns suggest that females outperform males in male-dominated fields, whereas males excel in female-dominated ones, undermining any presumed advantage of female scholars in their own research areas. These disparities contribute to the risk of both genders prematurely exiting the science pipeline. Furthermore, early-career experiences shape these outcomes asymmetrically: postdoctoral experience benefits both genders in female-dominated fields, with stronger effects for males, but disadvantages females in male-dominated fields by reducing their output and citation impact. Longer postdoctoral tenure enhances male researchers' citation impact across all fields but has mixed effects for females depending on field gender composition. These findings underscore the need for policies that address not just overall funding equality, but also gendered disparities across research topics and career trajectories.

Yang Ding, Jing Yu, Bang Liu et al.

Knowledge-based visual question answering requires the ability of associating external knowledge for open-ended cross-modal scene understanding. One limitation of existing solutions is that they capture relevant knowledge from text-only knowledge bases, which merely contain facts expressed by first-order predicates or language descriptions while lacking complex but indispensable multimodal knowledge for visual understanding. How to construct vision-relevant and explainable multimodal knowledge for the VQA scenario has been less studied. In this paper, we propose MuKEA to represent multimodal knowledge by an explicit triplet to correlate visual objects and fact answers with implicit relations. To bridge the heterogeneous gap, we propose three objective losses to learn the triplet representations from complementary views: embedding structure, topological relation and semantic space. By adopting a pre-training and fine-tuning learning strategy, both basic and domain-specific multimodal knowledge are progressively accumulated for answer prediction. We outperform the state-of-the-art by 3.35% and 6.08% respectively on two challenging knowledge-required datasets: OK-VQA and KRVQA. Experimental results prove the complementary benefits of the multimodal knowledge with existing knowledge bases and the advantages of our end-to-end framework over the existing pipeline methods. The code is available at https://github.com/AndersonStra/MuKEA.

Zhengyang Tang, Yuxuan Liu, Xin Lai et al.

A central bottleneck for phone-use agents is that controllable, reproducible environments covering real mobile behavior are hard to build at scale. Existing mobile-agent benchmarks have made important progress on evaluation, but they do not by themselves provide a scalable way to construct many new phone-use environments. We present PhoneWorld, a reusable pipeline that converts real GUI trajectories and screenshots into controllable phone-use environments, executable tasks, automatic verifiers, and training rollouts. Rather than hand-building one mobile benchmark at a time, PhoneWorld uses real trajectories to recover which screens matter, how screens connect, which interactions must change environment state, and which user goals admit automatic verification. From these signals, it builds runnable mock Android apps backed by read-only app content and mutable state, then derives executable tasks, rule-based verifiers, and training rollouts from the same environments. In its current instantiation, PhoneWorld covers 34 apps across 16 domains, spanning common consumer mobile behaviors such as search, browsing, shopping, booking, media, and social interaction. Under a fixed training budget, replacing 10K steps from an auxiliary AndroidWorld corpus in an AndroidWorld-based baseline with broad PhoneWorld supervision improves all four evaluation benchmarks at once, raising HYMobileBench by 17.7 points, AndroidControl by 6.0 points, AndroidWorld by 14.7 points, and PhoneWorld by 52.5 points. We then study two additional scaling questions: increasing the amount of PhoneWorld supervision strongly improves PhoneWorld performance, and under a fixed PhoneWorld budget, expanding app coverage yields even larger gains. Overall, PhoneWorld shifts the focus from building one mobile benchmark at a time to scaling the supply of phone-use environments themselves.

Bin Wang, Zhengyuan Liu, Xin Huang et al.

We present SeaEval, a benchmark for multilingual foundation models. In addition to characterizing how these models understand and reason with natural language, we also investigate how well they comprehend cultural practices, nuances, and values. Alongside standard accuracy metrics, we investigate the brittleness of foundation models in the dimensions of semantics and multilinguality. Our analyses span both open-sourced and closed models, leading to empirical results across classic NLP tasks, reasoning, and cultural comprehension. Key findings indicate (1) Most models exhibit varied behavior when given paraphrased instructions. (2) Many models still suffer from exposure bias (e.g., positional bias, majority label bias). (3) For questions rooted in factual, scientific, and commonsense knowledge, consistent responses are expected across multilingual queries that are semantically equivalent. Yet, most models surprisingly demonstrate inconsistent performance on these queries. (4) Multilingually-trained models have not attained "balanced multilingual" capabilities. Our endeavors underscore the need for more generalizable semantic representations and enhanced multilingual contextualization. SeaEval can serve as a launchpad for more thorough investigations and evaluations for multilingual and multicultural scenarios.

Jiamin Zhuang, Jing Yu, Yang Ding et al.

Image-text retrieval requires the system to bridge the heterogenous gap between vision and language for accurate retrieval while keeping the network lightweight-enough for efficient retrieval. Existing trade-off solutions mainly study from the view of incorporating cross-modal interactions with the independent-embedding framework or leveraging stronger pretrained encoders, which still demand time-consuming similarity measurement or heavyweight model structure in the retrieval stage. In this work, we propose an image-text alignment module SelfAlign on top of the independent-embedding framework, which improves the retrieval accuracy while maintains the retrieval efficiency without extra supervision. SelfAlign contains two collaborative sub-modules that force image-text alignment at both concept level and context level by self-supervised contrastive learning. It does not require cross-modal embedding interactions during training while maintaining independent image and text encoders during retrieval. With comparable time cost, SelfAlign consistently boosts the accuracy of state-of-the-art non-pretraining independent-embedding models respectively by 9.1%, 4.2% and 6.6% in terms of R@sum score on Flickr30K, MSCOCO 1K and MS-COCO 5K datasets. The retrieval accuracy also outperforms most existing interactive-embedding models with orders of magnitude decrease in retrieval time. The source code is available at: https://github.com/Zjamie813/SelfAlign.

Yunfeng Gao, Yuxuan Xiao, Jiaming Zhang et al.

Education research occupies a distinctive position in public science because it is expected to advance scholarly knowledge while also informing learning, teaching, participation, and workforce development. This study examines how the intellectual characteristics of NSF-funded education proposals are associated with the subsequent academic performance of funded scholars. Linking 8,715 NSF education awards from 1990 to 2020 with 84,519 publications by principal investigators, the analysis focuses on four major NSF education divisions that collectively span undergraduate and graduate levels, formal and informal learning environments, and inclusive educational initiatives. Proposal novelty is measured as semantic distance from prior funded projects within the same division, topical diversity as breadth across latent research themes, and intellectual orientation as theoretical, practical, or balanced. The results show that NSF education funding is consistently associated with higher publication output across divisions. However, this increase is not accompanied by stronger citation performance or higher journal-level visibility; citation and CiteScore estimates are often negative, particularly in later decades. Proposal novelty shows limited and uneven associations with post-award outcomes, whereas topical diversity is more clearly related to publication growth in some divisions but weaker citation-based performance in others. Balanced proposals that integrate theoretical and practical aims display the most favourable overall profile, combining positive publication associations with fewer negative citation-based patterns. These findings highlight the importance of evaluating education research funding through multiple academic outcomes and division-specific research contexts.

Yang Ding

Geopolitical conflict poses significant challenges to research and innovation policy by disrupting scientific systems and talent mobility. This study analyzes the impact of the conflict between Russia and Ukraine, particularly the escalations in 2014 and 2022, on the academic landscapes of both countries. We analyzed publication data from 2000 to 2023, encompassing over 1.8 million papers, one million scholars, and 2300 institutions across Ukraine and Russia, alongside collaboration data spanning 193 regions. We tracked scholar migration, research topics, and evolving international networks. Significant migration followed the 2014 and 2022 events, causing severe talent loss and a sharp decline in domestic research visibility in Ukraine. Migrated Ukrainian scholars shifted toward internationalized basic sciences, whereas active scholars who remained focused on applied fields relevant to national resilience and reconstruction. Both groups experienced decreased output in resource dependent fields, particularly medical research. Global networks fractured: traditional ties between Russia and the West, as well as between Ukraine and Russia, dissolved. These were replaced by new alignments between Russia and neighboring countries, and between Ukraine and the West. Migrating Ukrainian scholars face challenges assuming key research roles, though academic communities in smaller host nations showed a trend toward leadership positions. Concurrently, Russian scholars saw a decline in research prominence across most countries due to international sanctions. These findings reveal how conflict disrupts national scientific capacity, fractures global research networks, and affects individual academic careers, highlighting the need for targeted policies to support vulnerable academic communities during crises.

Yang Ding, Yizhen Zhang, Xin Lai et al.

Multimodal Large Language Models (MLLMs) have achieved remarkable progress in vision-language tasks yet remain limited in long video understanding due to the limited context window. Consequently, prevailing approaches tend to rely on uniform frame sampling or static pre-selection, which might overlook critical evidence and unable to correct its initial selection error during its reasoning process. To overcome these limitations, we propose VideoZoomer, a novel agentic framework that enables MLLMs to dynamically control their visual focus during reasoning. Starting from a coarse low-frame-rate overview, VideoZoomer invokes a temporal zoom tool to obtain high-frame-rate clips at autonomously chosen moments, thereby progressively gathering fine-grained evidence in a multi-turn interactive manner. Accordingly, we adopt a two-stage training strategy: a cold-start supervised fine-tuning phase on a curated dataset of distilled exemplar and reflection trajectories, followed by reinforcement learning to further refine the agentic policy. Extensive experiments demonstrate that our 7B model delivers diverse and complex reasoning patterns, yielding strong performance across a broad set of long video understanding and reasoning benchmarks. These emergent capabilities allow it to consistently surpass existing open-source models and even rival proprietary systems on challenging tasks, while achieving superior efficiency under reduced frame budgets.

Xin Wang, Ling Feng, Huijun Zhang et al.

Stress haunts people in modern society, which may cause severe health issues if left unattended. With social media becoming an integral part of daily life, leveraging social media to detect stress has gained increasing attention. While the majority of the work focuses on classifying stress states and stress categories, this study introduce a new task aimed at estimating more specific stressors (like exam, writing paper, etc.) through users' posts on social media. Unfortunately, the diversity of stressors with many different classes but a few examples per class, combined with the consistent arising of new stressors over time, hinders the machine understanding of stressors. To this end, we cast the stressor estimation problem within a practical scenario few-shot learning setting, and propose a novel meta-learning based stressor estimation framework that is enhanced by a meta-knowledge inheritance mechanism. This model can not only learn generic stressor context through meta-learning, but also has a good generalization ability to estimate new stressors with little labeled data. A fundamental breakthrough in our approach lies in the inclusion of the meta-knowledge inheritance mechanism, which equips our model with the ability to prevent catastrophic forgetting when adapting to new stressors. The experimental results show that our model achieves state-of-the-art performance compared with the baselines. Additionally, we construct a social media-based stressor estimation dataset that can help train artificial intelligence models to facilitate human well-being. The dataset is now public at \href{https://www.kaggle.com/datasets/xinwangcs/stressor-cause-of-mental-health-problem-dataset}{\underline{Kaggle}} and \href{https://huggingface.co/datasets/XinWangcs/Stressor}{\underline{Hugging Face}}.

Yang Ding, Can Han, Sijia Du et al.

Real-time acquisition of accurate scene depth is essential for automated robotic minimally invasive surgery. Stereo matching with binocular endoscopy can provide this depth information. However, existing stereo matching methods, designed primarily for natural images, often struggle with endoscopic images due to fuzzy tissue boundaries and typically fail to meet real-time requirements for high-resolution endoscopic image inputs. To address these challenges, we propose \textbf{RRESM}, a real-time stereo matching method tailored for endoscopic images. Our approach integrates a 3D Mamba Coordinate Attention module that enhances cost aggregation through position-sensitive attention maps and long-range spatial dependency modeling via the Mamba block, generating a robust cost volume without substantial computational overhead. Additionally, we introduce a High-Frequency Disparity Optimization module that refines disparity predictions near tissue boundaries by amplifying high-frequency details in the wavelet domain. Evaluations on the SCARED and SERV-CT datasets demonstrate state-of-the-art matching accuracy with a real-time inference speed of 42 FPS. The code is available at https://github.com/Sonne-Ding/RRESM.

Zhengyang Tang, Yi Zhang, Chenxin Li et al.

When a phone-use agent avoids harm, does that show safety, or simply inability to act? Existing evaluations often cannot tell. A harmful outcome may be avoided because the agent recognized the risk and chose the safe action, or because it failed to understand the screen or execute any relevant action at all. These cases have different causes and call for different fixes, yet current benchmarks often merge them under task success, refusal, or final harmful outcome. We address this problem with PhoneSafety, a benchmark of 700 safety-critical moments drawn from real phone interactions across more than 130 apps. Each instance isolates the next decision at a risky moment and asks a simple question: does the model take the safe action, take the unsafe action, or fail to do anything useful? We evaluate eight representative phone-use agents under this framework. Our results reveal two main patterns. First, stronger general phone-use ability does not reliably imply safer choices at risky moments. Models that perform better on ordinary app tasks are not always the ones that behave more safely when the next action matters. Second, failures to do anything useful behave like a capability signal rather than a safety signal: they are concentrated in more visually and operationally demanding settings and remain stable when the evaluation protocol changes. Across models, failures split into two recurring patterns: unsafe choices in settings where the model can act but chooses wrongly, and inability to act in more visually and operationally demanding screens. Overall, a harmless outcome is not enough to count as evidence of safety. Evaluating phone-use agents requires separating unsafe judgment from inability to act.

Jiaming Zhang, Yang Ding, Yunfeng Gao

In this study, we delve into the Structured State Space Model (S4), Change Point Detection methodologies, and the Switching Non-linear Dynamics System (SNLDS). Our central proposition is an enhanced inference technique and long-range dependency method for SNLDS. The cornerstone of our approach is the fusion of S4 and SNLDS, leveraging the strengths of both models to effectively address the intricacies of long-range dependencies in switching time series. Through rigorous testing, we demonstrate that our proposed methodology adeptly segments and reproduces long-range dependencies in both the 1-D Lorenz dataset and the 2-D bouncing ball dataset. Notably, our integrated approach outperforms the standalone SNLDS in these tasks.

Yongchao Wang, Yang Ding, Jiansheng Yang et al.

Let $p$ be an odd prime. The factorization of the polynomial $x^{p+1}-1$ over the integer residue ring $\mathbb{Z}_{p^e}$ is pivotal for constructing cyclic codes with Hermitian symmetry, a critical resource for Linear Complementary Dual (LCD) codes and Entanglement-Assisted Quantum Error-Correcting Codes (EAQECC). Traditionally, lifting factorizations relies on the generic Hensel's Lemma, masking the underlying algebraic structure. In this paper, we establish a structural isomorphism between the lifting process and the roots of a special auxiliary polynomial $V(x)$, unveiling a deterministic link to Dickson polynomials. Based on this theory, we develop \texttt{Dickson-Engine}, a linear-time algorithm ($O(ep)$) that outperforms standard libraries by orders of magnitude. Applying this engine to $\mathbb{Z}_{169}$, we explicitly construct a family of classical LCD codes of length $n=182$ via the isometric Gray map. Our search reveals codes with parameters (e.g., $[182, 1, 168]_{13}$ and $[182, 2, 144]_{13}$) that are \textbf{near-optimal} with respect to the theoretical Griesmer Bound. Notably, we discover a ``robustness plateau'' starting from non-trivial dimensions ($k=4$), where the minimum distance remains stable ($d=120$) even as the dimension triples ($k=4 \rightarrow 12$). These codes provide exceptional resources for post-quantum cryptography and quantum error correction without entanglement consumption ($c=0$).

Yizhen Zhang, Yang Ding, Shuoshuo Zhang et al.

Inspired by the impressive reasoning capabilities demonstrated by reinforcement learning approaches like DeepSeek-R1, recent emerging research has begun exploring the use of reinforcement learning (RL) to enhance vision-language models (VLMs) for multimodal reasoning tasks. However, most existing multimodal reinforcement learning approaches remain limited to spatial reasoning within single-image contexts, yet still struggle to generalize to more complex and real-world scenarios involving multi-image positional reasoning, where understanding the relationships across images is crucial. To address this challenge, we propose a general reinforcement learning approach PeRL tailored for interleaved multimodal tasks, and a multi-stage strategy designed to enhance the exploration-exploitation trade-off, thereby improving learning efficiency and task performance. Specifically, we introduce permutation of image sequences to simulate varied positional relationships to explore more spatial and positional diversity. Furthermore, we design a rollout filtering mechanism for resampling to focus on trajectories that contribute most to learning optimal behaviors to exploit learned policies effectively. We evaluate our model on 5 widely-used multi-image benchmarks and 3 single-image benchmarks. Our experiments confirm that PeRL trained model consistently surpasses R1-related and interleaved VLM baselines by a large margin, achieving state-of-the-art performance on multi-image benchmarks, while preserving comparable performance on single-image tasks.

Li Cui, Yang Ding, Richard Hartley et al.

We propose a novel, vision-only object-level SLAM framework for automotive applications representing 3D shapes by implicit signed distance functions. Our key innovation consists of augmenting the standard neural representation by a normalizing flow network. As a result, achieving strong representation power on the specific class of road vehicles is made possible by compact networks with only 16-dimensional latent codes. Furthermore, the newly proposed architecture exhibits a significant performance improvement in the presence of only sparse and noisy data, which is demonstrated through comparative experiments on synthetic data. The module is embedded into the back-end of a stereo-vision based framework for joint, incremental shape optimization. The loss function is given by a combination of a sparse 3D point-based SDF loss, a sparse rendering loss, and a semantic mask-based silhouette-consistency term. We furthermore leverage semantic information to determine keypoint extraction density in the front-end. Finally, experimental results on real-world data reveal accurate and reliable performance comparable to alternative frameworks that make use of direct depth readings. The proposed method performs well with only sparse 3D points obtained from bundle adjustment, and eventually continues to deliver stable results even under exclusive use of the mask-consistency term.

Weiwen Xu, Ai Ti Aw, Yang Ding et al.

Neural Machine Translation (NMT) has achieved significant breakthrough in performance but is known to suffer vulnerability to input perturbations. As real input noise is difficult to predict during training, robustness is a big issue for system deployment. In this paper, we improve the robustness of NMT models by reducing the effect of noisy words through a Context-Enhanced Reconstruction (CER) approach. CER trains the model to resist noise in two steps: (1) perturbation step that breaks the naturalness of input sequence with made-up words; (2) reconstruction step that defends the noise propagation by generating better and more robust contextual representation. Experimental results on Chinese-English (ZH-EN) and French-English (FR-EN) translation tasks demonstrate robustness improvement on both news and social media text. Further fine-tuning experiments on social media text show our approach can converge at a higher position and provide a better adaptation.