Searcharxiv⌕ Search

arXiv subjects

Yunqi Li

Publications and source records attributed to Yunqi Li.

At least 19 recordsLinked to original sources
arXiv2026

Bolo: Verified Model Hub for Next-Generation AI Databases

Verified, ready-to-use inference pipelines are a cornerstone of future AI databases. They allow multi-modal databases to incorporate specialized language, vision, and tabular models that can deliver both high accuracy and efficiency. Unfortunately, existing model platforms such as Hugging Face fall short of this goal. While they host millions of model repositories, many contain only raw weights without runnable pipelines. Even well-documented models often fail due to missing dependencies, unsupported model classes, or incorrect task assignments. Moreover, different models fail for different reasons, with no uniform solution. Constructing a large-scale, verified model hub is nearly impossible with human effort alone. We argue that AI agents can achieve this at scale. We present \system, a model platform that hosts verified, ready-to-use inference pipelines, powered by a multi-stage agentic system for model remediation. For models that fail under standard usage, the agent inspects errors and repairs broken pipelines (Type~I). For models outside the scope of existing interfaces, it synthesizes pipelines from scratch using model metadata and documentation (Type~II \& III). To prevent incorrect pipelines from entering the database, the agent applies multi-stage verification---checking not only program structure but also semantic model behavior, ensuring pipelines produce meaningful outputs rather than merely executing without error. In preliminary experiments, \system achieves 97.27\% and 86.08\% runnable coverage for Type~II and Type~III models, respectively, demonstrating that agentic synthesis with targeted verification can transform large collections of unusable model weights into a verified database of ready-to-use inference pipelines. The preliminary database is open-sourced at \textcolor{blue}{https://bolobao.ai/}.

cs.DB↗
arXiv2026

CatPAL: Task-Aware Learning for Categorical Palette Recommendation

Designing effective categorical palettes requires balancing a range of factors, including perceptual distinctiveness, category count, and task effectiveness. The effectiveness of categorical encodings can vary substantially depending on the target analytical tasks; however, existing recommendation tools largely ignore task context when evaluating palette quality, resulting in inconsistent performance across tasks. We synthesize findings from a series of multi-stage user studies into a unified model of task-based effectiveness for color encodings, shape encodings, and their redundant combination across category counts and seven common scatterplot tasks. Our results show that task and palette choice jointly influence perceptual accuracy: different color and shape palettes exhibit varying levels of robustness across tasks, indicating that palette effectiveness is task-dependent. We estimate task-specific perceptual strengths for 39 colors and 39 shapes using Bradley-Terry models, refined through adaptive sampling to target uncertain and task-sensitive comparisons. We further quantify cross-channel interactions using a redundant gain Delta G metric to model performance across color and shape pairings. We then train a predictive model that scores candidate palettes based on task, category count, and perceptual features. This model drives effective palette recommendations in CatPAL, a task-aware palette recommendation system grounded in empirical data responsive to user constraints. Our findings highlight the importance of selecting categorical palettes aligned with specific analytical tasks and demonstrate how task-aware modeling enables more reliable palette design. CatPAL translates empirical results into a practical tool that supports user-specified colors or shapes and returns ranked palette recommendations adaptable to a range of tasks.

cs.HC↗
arXiv2026

Hierarchy-Guided Multimodal Representation Learning for Taxonomic Inference

Accurate biodiversity identification from large-scale field data is a foundational problem with direct impact on ecology, conservation, and environmental monitoring. In practice, the core task is taxonomic prediction - inferring order, family, genus, or species from imperfect inputs such as specimen images, DNA barcodes, or both. Existing multimodal methods often treat taxonomy as a flat label space and therefore fail to encode the hierarchical structure of biological classification, which is critical for robustness under noise and missing modalities. We present two end-to-end variants for hierarchy-aware multimodal learning: CLiBD-HiR, which introduces Hierarchical Information Regularization (HiR) to shape embedding geometry across taxonomic levels, yielding structured and noise-robust representations; and CLiBD-HiR-Fuse, which additionally trains a lightweight fusion predictor that supports image-only, DNA-only, or joint inference and is resilient to modality corruption. Across large-scale biodiversity benchmarks, our approach improves taxonomic classification accuracy by over 14 percent compared to strong multimodal baselines, with particularly large gains under partial and corrupted DNA conditions. These results highlight that explicitly encoding biological hierarchy, together with flexible fusion, is key for practical biodiversity foundation models.

cs.CV↗
arXiv2026

Weak Zero-Knowledge and One-Way Functions

We study the implications of the existence of weak Zero-Knowledge (ZK) protocols for worst-case hard languages. These are protocols that have completeness, soundness, and zero-knowledge errors (denoted $\epsilon_c$, $\epsilon_s$, and $\epsilon_z$, respectively) that might not be negligible. Under the assumption that there are worst-case hard languages in NP, we show the following: 1. If all languages in NP have NIZK proofs or arguments satisfying $ \epsilon_c+\epsilon_s+ \epsilon_z < 1 $, then One-Way Functions (OWFs) exist. This covers all possible non-trivial values for these error rates. It additionally implies that if all languages in NP have such NIZK proofs and $\epsilon_c$ is negligible, then they also have NIZK proofs where all errors are negligible. Previously, these results were known under the more restrictive condition $ \epsilon_c+\sqrt{\epsilon_s}+\epsilon_z < 1 $ [Chakraborty et al., CRYPTO 2025]. 2. If all languages in NP have $k$-round public-coin ZK proofs or arguments satisfying $ \epsilon_c+\epsilon_s+(2k-1).\epsilon_z < 1 $, then OWFs exist. 3. If, for some constant $k$, all languages in NP have $k$-round public-coin ZK proofs or arguments satisfying $ \epsilon_c+\epsilon_s+k.\epsilon_z < 1 $, then infinitely-often OWFs exist.

cs.CR↗
arXiv2025

Decoding Balanced Linear Codes With Preprocessing

Prange's information set algorithm is a decoding algorithm for arbitrary linear codes. It decodes corrupted codewords of any $\mathbb{F}_2$-linear code $C$ of message length $n$ up to relative error rate $O(\log n / n)$ in $\mathsf{poly}(n)$ time. We show that the error rate can be improved to $O((\log n)^2 / n)$, provided: (1) the decoder has access to a polynomial-length advice string that depends on $C$ only, and (2) $C$ is $n^{-\Omega(1)}$-balanced. As a consequence we improve the error tolerance in decoding random linear codes if inefficient preprocessing of the code is allowed. This reveals potential vulnerabilities in cryptographic applications of Learning Noisy Parities with low noise rate. Our main technical result is that the Hamming weight of $Hw$, where $H$ is a random sample of *short dual* codewords, measures the proximity of a word $w$ to the code in the regime of interest. Given such $H$ as advice, our algorithm corrects errors by locally minimizing this measure. We show that for most codes, the error rate tolerated by our decoder is asymptotically optimal among all algorithms whose decision is based on thresholding $Hw$ for an arbitrary polynomial-size advice matrix $H$.

cs.CC↗
arXiv2025

Unpacking Discourses on Childbirth and Parenthood in Popular Social Media Platforms Across China, Japan, and South Korea

Social media use has been shown to be associated with low fertility desires. However, we know little about the discourses surrounding childbirth and parenthood that people consume online. We analyze 219,127 comments on 668 short videos related to reproduction and parenthood from Douyin and Tiktok in China, South Korea, and Japan, a region famous for its extremely low fertility level, to examine the topics and sentiment expressed online. BERTopic model is used to assist thematic analysis, and a large language model QWen is applied to label sentiment. We find that comments focus on childrearing costs in all countries, utility of children, particularly in Japan and South Korea, and individualism, primarily in China. Comments from Douyin exhibit the strongest anti-natalist sentiments, while the Japanese and Korean comments are more neutral. Short video characteristics, such as their stances or account type, significantly influence the responses, alongside regional socioeconomic indicators, including GDP, urbanization, and population sex ratio. This work provides one of the first comprehensive analyses of online discourses on family formation via popular algorithm-fed video sharing platforms in regions experiencing low fertility rates, making a valuable contribution to our understanding of the spread of family values online.

cs.SI↗
arXiv2025

Does Learning Mathematical Problem-Solving Generalize to Broader Reasoning?

There has been a growing interest in enhancing the mathematical problem-solving (MPS) capabilities of large language models. While the majority of research efforts concentrate on creating specialized models to solve mathematical problems, it remains unknown how learning mathematical problem-solving generalizes to help develop other reasoning abilities. In this paper, we present an empirical investigation into the generalization potential of various MPS training approaches, such as continual pretraining, instruction tuning, and rule-based reinforcement learning across various data sources, including both short and long chain-of-thought (CoT) samples. Evaluation on 5 mathematical and 8 general reasoning benchmarks show that continual pretraining on math text is able to generalize to general reasoning tasks to some extent. In constrast, instruction tuning on conventional, short MPS samples provides limited benefits and, in many cases, even impairs generalization performance. Notably, training with long CoT responses for MPS samples and incorporating rule-based reinforcement learning on MPS queries exhibit distinct behavior, significantly enhancing generalization by extending the model's reasoning processes into other domains. These results suggest that traditional approaches to learning MPS with short reasoning chains largely fail to achieve robust generalization. However, the emerging paradigm of longer reasoning chains, coupled with self-reflection, offers a promising direction for improving generalized reasoning abilities through learning from specialized domains.

cs.CL↗
arXiv2025

ReasonGen-R1: CoT for Autoregressive Image generation models through SFT and RL

Although chain-of-thought reasoning and reinforcement learning (RL) have driven breakthroughs in NLP, their integration into generative vision models remains underexplored. We introduce ReasonGen-R1, a two-stage framework that first imbues an autoregressive image generator with explicit text-based "thinking" skills via supervised fine-tuning on a newly generated reasoning dataset of written rationales, and then refines its outputs using Group Relative Policy Optimization. To enable the model to reason through text before generating images, We automatically generate and release a corpus of model crafted rationales paired with visual prompts, enabling controlled planning of object layouts, styles, and scene compositions. Our GRPO algorithm uses reward signals from a pretrained vision language model to assess overall visual quality, optimizing the policy in each update. Evaluations on GenEval, DPG, and the T2I benchmark demonstrate that ReasonGen-R1 consistently outperforms strong baselines and prior state-of-the-art models. More: aka.ms/reasongen.

cs.CV↗
arXiv2024

Estimating Body and Hand Motion in an Ego-sensed World

We present EgoAllo, a system for human motion estimation from a head-mounted device. Using only egocentric SLAM poses and images, EgoAllo guides sampling from a conditional diffusion model to estimate 3D body pose, height, and hand parameters that capture a device wearer's actions in the allocentric coordinate frame of the scene. To achieve this, our key insight is in representation: we propose spatial and temporal invariance criteria for improving model performance, from which we derive a head motion conditioning parameterization that improves estimation by up to 18%. We also show how the bodies estimated by our system can improve hand estimation: the resulting kinematic and temporal constraints can reduce world-frame errors in single-frame estimates by 40%. Project page: https://egoallo.github.io/

cs.CV↗
arXiv2024

A Survey on Large Language Model-empowered Autonomous Driving

Artificial intelligence (AI) plays a crucial role in autonomous driving (AD) research, propelling its development towards intelligence and efficiency. Currently, the development of AD technology follows two main technical paths: modularization and end-to-end. Modularization decompose the driving task into modules such as perception, prediction, planning, and control, and train them separately. Due to the inconsistency of training objectives between modules, the integrated effect suffers from bias. End-to-end attempts to address this issue by utilizing a single model that directly maps from sensor data to control signals. This path has limited learning capabilities in a comprehensive set of features and struggles to handle unpredictable long-tail events and complex urban traffic scenarios. In the face of challenges encountered in both paths, many researchers believe that large language models (LLMs) with powerful reasoning capabilities and extensive knowledge understanding may be the solution, expecting LLMs to provide AD systems with deeper levels of understanding and decision-making capabilities. In light of the challenges faced by both paths, many researchers believe that LLMs, with their powerful reasoning abilities and extensive knowledge, could offer a solution. To understand if LLMs could enhance AD, this paper conducts a thorough analysis of the potential applications of LLMs in AD systems, including exploring their optimization strategies in both modular and end-to-end approaches, with a particular focus on how LLMs can tackle the problems and challenges present in current solutions. Furthermore, we discuss an important question: Can LLM-based artificial general intelligence (AGI) be a key to achieve high-level AD? We further analyze the potential limitations and challenges that LLMs may encounter in promoting the development of AD technology.

cs.AI↗
arXiv2024

Fairness of ChatGPT

Understanding and addressing unfairness in LLMs are crucial for responsible AI deployment. However, there is a limited number of quantitative analyses and in-depth studies regarding fairness evaluations in LLMs, especially when applying LLMs to high-stakes fields. This work aims to fill this gap by providing a systematic evaluation of the effectiveness and fairness of LLMs using ChatGPT as a study case. We focus on assessing ChatGPT's performance in high-takes fields including education, criminology, finance and healthcare. To conduct a thorough evaluation, we consider both group fairness and individual fairness metrics. We also observe the disparities in ChatGPT's outputs under a set of biased or unbiased prompts. This work contributes to a deeper understanding of LLMs' fairness performance, facilitates bias mitigation and fosters the development of responsible AI systems.

cs.LG↗
arXiv2024

A Survey on Trustworthy Recommender Systems

Recommender systems (RS), serving at the forefront of Human-centered AI, are widely deployed in almost every corner of the web and facilitate the human decision-making process. However, despite their enormous capabilities and potential, RS may also lead to undesired effects on users, items, producers, platforms, or even the society at large, such as compromised user trust due to non-transparency, unfair treatment of different consumers, or producers, privacy concerns due to extensive use of user's private data for personalization, just to name a few. All of these create an urgent need for Trustworthy Recommender Systems (TRS) so as to mitigate or avoid such adverse impacts and risks. In this survey, we will introduce techniques related to trustworthy recommendation, including but not limited to explainable recommendation, fairness in recommendation, privacy-aware recommendation, robustness in recommendation, user-controllable recommendation, as well as the relationship between these different perspectives in terms of trustworthy recommendation. Through this survey, we hope to deliver readers with a comprehensive view of the research area and raise attention to the community about the importance, existing research achievements, and future research directions on trustworthy recommendation.

cs.IR↗
arXiv2023

Causal Collaborative Filtering

Many of the traditional recommendation algorithms are designed based on the fundamental idea of mining or learning correlative patterns from data to estimate the user-item correlative preference. However, pure correlative learning may lead to Simpson's paradox in predictions, and thus results in sacrificed recommendation performance. Simpson's paradox is a well-known statistical phenomenon, which causes confusions in statistical conclusions and ignoring the paradox may result in inaccurate decisions. Fortunately, causal and counterfactual modeling can help us to think outside of the observational data for user modeling and personalization so as to tackle such issues. In this paper, we propose Causal Collaborative Filtering (CCF) -- a general framework for modeling causality in collaborative filtering and recommendation. We provide a unified causal view of CF and mathematically show that many of the traditional CF algorithms are actually special cases of CCF under simplified causal graphs. We then propose a conditional intervention approach for $do$-operations so that we can estimate the user-item causal preference based on the observational data. Finally, we further propose a general counterfactual constrained learning framework for estimating the user-item preferences. Experiments are conducted on two types of real-world datasets -- traditional and randomized trial data -- and results show that our framework can improve the recommendation performance and reduce the Simpson's paradox problem of many CF algorithms.

cs.IR↗
arXiv2023

Fairness in Recommendation: Foundations, Methods and Applications

As one of the most pervasive applications of machine learning, recommender systems are playing an important role on assisting human decision making. The satisfaction of users and the interests of platforms are closely related to the quality of the generated recommendation results. However, as a highly data-driven system, recommender system could be affected by data or algorithmic bias and thus generate unfair results, which could weaken the reliance of the systems. As a result, it is crucial to address the potential unfairness problems in recommendation settings. Recently, there has been growing attention on fairness considerations in recommender systems with more and more literature on approaches to promote fairness in recommendation. However, the studies are rather fragmented and lack a systematic organization, thus making it difficult to penetrate for new researchers to the domain. This motivates us to provide a systematic survey of existing works on fairness in recommendation. This survey focuses on the foundations for fairness in recommendation literature. It first presents a brief introduction about fairness in basic machine learning tasks such as classification and ranking in order to provide a general overview of fairness research, as well as introduce the more complex situations and challenges that need to be considered when studying fairness in recommender systems. After that, the survey will introduce fairness in recommendation with a focus on the taxonomies of current fairness definitions, the typical techniques for improving fairness, as well as the datasets for fairness studies in recommendation. The survey also talks about the challenges and opportunities in fairness research with the hope of promoting the fair recommendation research area and beyond.

cs.IR↗
arXiv2023

Counterfactual Explainable Recommendation

By providing explanations for users and system designers to facilitate better understanding and decision making, explainable recommendation has been an important research problem. In this paper, we propose Counterfactual Explainable Recommendation (CountER), which takes the insights of counterfactual reasoning from causal inference for explainable recommendation. CountER is able to formulate the complexity and the strength of explanations, and it adopts a counterfactual learning framework to seek simple (low complexity) and effective (high strength) explanations for the model decision. Technically, for each item recommended to each user, CountER formulates a joint optimization problem to generate minimal changes on the item aspects so as to create a counterfactual item, such that the recommendation decision on the counterfactual item is reversed. These altered aspects constitute the explanation of why the original item is recommended. The counterfactual explanation helps both the users for better understanding and the system designers for better model debugging. Another contribution of the work is the evaluation of explainable recommendation, which has been a challenging task. Fortunately, counterfactual explanations are very suitable for standard quantitative evaluation. To measure the explanation quality, we design two types of evaluation metrics, one from user's perspective (i.e. why the user likes the item), and the other from model's perspective (i.e. why the item is recommended by the model). We apply our counterfactual learning algorithm on a black-box recommender system and evaluate the generated explanations on five real-world datasets. Results show that our model generates more accurate and effective explanations than state-of-the-art explainable recommendation models.

cs.IR↗
arXiv2023

Transferable Fairness for Cold-Start Recommendation

With the increasing use and impact of recommender systems in our daily lives, how to achieve fairness in recommendation has become an important problem. Previous works on fairness-aware recommendation mainly focus on a predefined set of (usually warm-start) users. However, recommender systems often face more challenging fairness issues for new users or cold-start users due to their insufficient amount of interactions. Therefore, it is essential to study whether the trained model still performs fairly for a new set of cold-start users. This paper considers the scenario where the recommender system meets new users who only have limited or even no interaction with the platform, and aims at providing high-quality and fair recommendations to such users effectively. The sufficient interaction data from warm users is treated as the source user domain, while the data from new users is treated as the target user domain, and we consider to transfer the counterfactual fairness from the source users to the target users. To this end, we introduce a framework to achieve transferable counterfactual fairness in recommendation. The proposed method is able to transfer the knowledge of a fair model learned from the source users to the target users with the hope of improving the recommendation performance and keeping the fairness property on the target users. Experiments on two real-world datasets with representative recommendation algorithms show that our method not only promotes fairness for the target users, but also outperforms comparative models in terms of recommendation performance.

cs.IR↗
arXiv2023

Causal Inference for Recommendation: Foundations, Methods and Applications

Recommender systems are important and powerful tools for various personalized services. Traditionally, these systems use data mining and machine learning techniques to make recommendations based on correlations found in the data. However, relying solely on correlation without considering the underlying causal mechanism may lead to various practical issues such as fairness, explainability, robustness, bias, echo chamber and controllability problems. Therefore, researchers in related area have begun incorporating causality into recommendation systems to address these issues. In this survey, we review the existing literature on causal inference in recommender systems. We discuss the fundamental concepts of both recommender systems and causal inference as well as their relationship, and review the existing work on causal methods for different problems in recommender systems. Finally, we discuss open problems and future directions in the field of causal inference for recommendations.

cs.IR↗
arXiv2022

Elements of effective machine learning datasets in astronomy

In this work, we identify elements of effective machine learning datasets in astronomy and present suggestions for their design and creation. Machine learning has become an increasingly important tool for analyzing and understanding the large-scale flood of data in astronomy. To take advantage of these tools, datasets are required for training and testing. However, building machine learning datasets for astronomy can be challenging. Astronomical data is collected from instruments built to explore science questions in a traditional fashion rather than to conduct machine learning. Thus, it is often the case that raw data, or even downstream processed data is not in a form amenable to machine learning. We explore the construction of machine learning datasets and we ask: what elements define effective machine learning datasets? We define effective machine learning datasets in astronomy to be formed with well-defined data points, structure, and metadata. We discuss why these elements are important for astronomical applications and ways to put them in practice. We posit that these qualities not only make the data suitable for machine learning, they also help to foster usable, reusable, and replicable science practices.

astro-ph.IM↗