Hongyi Wen

Jinnuo Liu, Yue Peng, Jinhan Niu et al.

Large language models for code generation often need to use APIs that are absent from their pretraining data. This requires more than recalling a function name: models must coordinate signatures, module paths, input-output contracts, semantics, and executable usage patterns. Existing novel-API benchmarks are typically static, rely on coarse pass/fail metrics, or use synthetic APIs that may not reflect real library evolution. We introduce NovelAPIBench, a fully automated dynamic benchmark that, for any base model and target library, discovers novel APIs, extracts decomposed knowledge bundles, generates executable coding tasks, and assigns failed samples to six diagnostic categories. Across about 1.9K tasks, four base models, and five domains, we compare knowledge injected through retrieval with knowledge internalized through parametric adaptation. We find that knowledge components are not interchangeable: usage examples are the strongest standalone signal, while the best two-component setting pairs signatures with either mechanisms or examples depending on the domain and backbone. Adding more context, especially source code, can hurt by increasing import-path errors. Parametric adaptation also does not replace retrieval once external knowledge is removed; rather, fine-tuning mainly teaches models how to use provided bundles, and this ability transfers to held-out libraries. These results suggest that retrieval and tuning play complementary roles: retrieval supplies volatile API content, while tuning improves procedural integration.

Yuanhe Guo, Haoming Liu, Hongyi Wen

Recommender Systems are built to retrieve relevant items to satisfy users' information needs. The candidate corpus usually consists of a finite set of items that are ready to be served, such as videos, products, or articles. With recent advances in Generative AI such as GPT and Diffusion models, a new form of recommendation task is yet to be explored where items are to be created by generative models with personalized prompts. Taking image generation as an example, with a single prompt from the user and access to a generative model, it is possible to generate hundreds of new images in a few minutes. How shall we attain personalization in the presence of "infinite" items? In this preliminary study, we propose a two-stage framework, namely Prompt-Model Retrieval and Generated Item Ranking, to approach this new task formulation. We release GEMRec-18K, a prompt-model interaction dataset with 18K images generated by 200 publicly-available generative models paired with a diverse set of 90 textual prompts. Our findings demonstrate the promise of generative model recommendation as a novel personalization problem and the limitations of existing evaluation metrics. We highlight future directions for the RecSys community to advance towards generative recommender systems. Our code and dataset are available at https://github.com/MAPS-research/GEMRec.

Sihang, Zhao, Kangrui Yu et al.

Large Language Models (LLMs) have been widely explored in educational scenarios. We identify a critical vulnerability in current educational LLMs, pedagogical jailbreaks, where students use answer-inducing prompts to elicit solutions rather than scaffolded instructions. To enable systematic study, we unify and formalize safe, helpful, and pedagogical behaviors with a knowledge-mastery graph and introduce SHAPE, a benchmark of 9,087 student-question pairs for evaluating tutoring behavior under adversarial pressure. We propose a graph-augmented tutoring pipeline that infers prerequisite concepts from queries, identifies mastery gaps, and routes generation between instructing and problem-solving via explicit gating. Experiments across multiple LLMs show that our method yields significantly improved safety under two pedagogical jailbreak settings, while maintaining near-ceiling helpfulness under the same evaluation protocol. Our code and data are available at https://github.com/MAPS-research/SHaPE

Ziyun Yu, Yiru Zhou, Chen Zhao et al.

Using Large Language Models (LLMs) to simulate user opinions has received growing attention. Yet LLMs, especially trained with reinforcement learning from human feedback (RLHF), are known to exhibit biases toward dominant viewpoints, raising concerns about their ability to represent users from diverse demographic and cultural backgrounds. In this work, we examine the extent to which LLMs can simulate human responses to cross-domain survey questions through direct prompting and chain-of-thought prompting. We further propose a claim diversification method CLAIMSIM, which elicits viewpoints from LLM parametric knowledge as contextual input. Experiments on the survey question answering task indicate that, while CLAIMSIM produces more diverse responses, both approaches struggle to accurately simulate users. Further analysis reveals two key limitations: (1) LLMs tend to maintain fixed viewpoints across varying demographic features, and generate single-perspective claims; and (2) when presented with conflicting claims, LLMs struggle to reason over nuanced differences among demographic features, limiting their ability to adapt responses to specific user profiles.

Haoming Liu, Jinnuo Liu, Yanhao Li et al.

Flow-based diffusion models have emerged as a leading paradigm for training generative models across images and videos. However, their memorization-generalization behavior remains poorly understood. In this work, we revisit the flow matching (FM) objective and study its marginal velocity field, which admits a closed-form expression, allowing exact computation of the oracle FM target. Analyzing this oracle velocity field reveals that flow-based diffusion models inherently formulate a two-stage training target: an early stage guided by a mixture of data modes, and a later stage dominated by the nearest data sample. The two-stage objective leads to distinct learning behaviors: the early navigation stage generalizes across data modes to form global layouts, whereas the later refinement stage increasingly memorizes fine-grained details. Leveraging these insights, we explain the effectiveness of practical techniques such as timestep-shifted schedules, classifier-free guidance intervals, and latent space design choices. Our study deepens the understanding of diffusion model training dynamics and offers principles for guiding future architectural and algorithmic improvements.

Yuanhe Guo, Linxi Xie, Zhuoran Chen et al.

We introduce ImageGem, a dataset for studying generative models that understand fine-grained individual preferences. We posit that a key challenge hindering the development of such a generative model is the lack of in-the-wild and fine-grained user preference annotations. Our dataset features real-world interaction data from 57K users, who collectively have built 242K customized LoRAs, written 3M text prompts, and created 5M generated images. With user preference annotations from our dataset, we were able to train better preference alignment models. In addition, leveraging individual user preference, we investigated the performance of retrieval models and a vision-language model on personalized image retrieval and generative model recommendation. Finally, we propose an end-to-end framework for editing customized diffusion models in a latent weight space to align with individual user preferences. Our results demonstrate that the ImageGem dataset enables, for the first time, a new paradigm for generative model personalization.

Linxi Xie, Xin Teng, Shichang Ke et al.

Large language model (LLM) unlearning has demonstrated effectiveness in removing the influence of undesirable data (also known as forget data). Existing approaches typically assume full access to the forget dataset, overlooking two key challenges: (1) Forget data is often privacy-sensitive, rare, or legally regulated, making it expensive or impractical to obtain (2) The distribution of available forget data may not align with how that information is represented within the model. To address these limitations, we propose a ``Reveal-and-Release'' method to unlearn with self-generated data, where we prompt the model to reveal what it knows using optimized instructions. To fully utilize the self-generated forget data, we propose an iterative unlearning framework, where we make incremental adjustments to the model's weight space with parameter-efficient modules trained on the forget data. Experimental results demonstrate that our method balances the tradeoff between forget quality and utility preservation.

Haoming Liu, Yuanhe Guo, Shengjie Wang et al.

Diffusion models, capable of high-quality image generation, receive unparalleled popularity for their ease of extension. Active users have created a massive collection of domain-specific diffusion models by fine-tuning base models on self-collected datasets. Recent work has focused on improving a single diffusion model by uncovering semantic and visual information encoded in various architecture components. However, those methods overlook the vastly available set of fine-tuned diffusion models and, therefore, miss the opportunity to utilize their combined capacity for novel generation. In this work, we propose Diffusion Cocktail (Ditail), a training-free method that transfers style and content information between multiple diffusion models. This allows us to perform diversified generations using a set of diffusion models, resulting in novel images unobtainable by a single model. Ditail also offers fine-grained control of the generation process, which enables flexible manipulations of styles and contents. With these properties, Ditail excels in numerous applications, including style transfer guided by diffusion models, novel-style image generation, and image manipulation via prompts or collage inputs.

Sasha Stoikov, Hongyi Wen

High quality user feedback data is essential to training and evaluating a successful music recommendation system, particularly one that has to balance the needs of multiple stakeholders. Most existing music datasets suffer from noisy feedback and self-selection biases inherent in the data collected by music platforms. Using the Piki Music dataset of 500k ratings collected over a two-year time period, we evaluate the performance of classic recommendation algorithms on three important stakeholders: consumers, well-known artists and lesser-known artists. We show that a matrix factorization algorithm trained on both likes and dislikes performs significantly better compared to one trained only on likes for all three stakeholders.

Weishen Pan, Sen Cui, Hongyi Wen et al.

Selection bias is prevalent in the data for training and evaluating recommendation systems with explicit feedback. For example, users tend to rate items they like. However, when rating an item concerning a specific user, most of the recommendation algorithms tend to rely too much on his/her rating (feedback) history. This introduces implicit bias on the recommendation system, which is referred to as user feedback-loop bias in this paper. We propose a systematic and dynamic way to correct such bias and to obtain more diverse and objective recommendations by utilizing temporal rating information. Specifically, our method includes a deep-learning component to learn each user's dynamic rating history embedding for the estimation of the probability distribution of the items that the user rates sequentially. These estimated dynamic exposure probabilities are then used as propensity scores to train an inverse-propensity-scoring (IPS) rating predictor. We empirically validated the existence of such user feedback-loop bias in real world recommendation systems and compared the performance of our method with the baseline models that are either without de-biasing or with propensity scores estimated by other methods. The results show the superiority of our approach.

Jiaxi Tang, Hongyi Wen, Ke Wang

Recommender systems play an important role in modern information and e-commerce applications. While increasing research is dedicated to improving the relevance and diversity of the recommendations, the potential risks of state-of-the-art recommendation models are under-explored, that is, these models could be subject to attacks from malicious third parties, through injecting fake user interactions to achieve their purposes. This paper revisits the adversarially-learned injection attack problem, where the injected fake user `behaviors' are learned locally by the attackers with their own model -- one that is potentially different from the model under attack, but shares similar properties to allow attack transfer. We found that most existing works in literature suffer from two major limitations: (1) they do not solve the optimization problem precisely, making the attack less harmful than it could be, (2) they assume perfect knowledge for the attack, causing the lack of understanding for realistic attack capabilities. We demonstrate that the exact solution for generating fake users as an optimization problem could lead to a much larger impact. Our experiments on a real-world dataset reveal important properties of the attack, including attack transferability and its limitations. These findings can inspire useful defensive methods against this possible existing attack.