用户建模

Autoregressive models have emerged as a powerful framework for modeling exchangeable sequences---i.i.d. observations when conditioned on some latent factor---enabling direct modeling of uncertainty from missing data (rather than a latent). Motivated by the critical role posterior inference plays as a subroutine in decision-making (e.g., active learning, bandits), we study the inferential and architectural inductive biases that are most effective for exchangeable sequence modeling. For the inference stage, we highlight a fundamental limitation of the prevalent single-step generation approach: its inability to distinguish between epistemic and aleatoric uncertainty. Instead, a long line of works in Bayesian statistics advocates for multi-step autoregressive generation; we demonstrate this "correct approach" enables superior uncertainty quantification that translates into better performance on downstream decision-making tasks. This naturally leads to the next question: which architectures are best suited for multi-step inference? We identify a subtle yet important gap between recently proposed Transformer architectures for exchangeable sequences (Müller et al., 2022; Nguyen & Grover, 2022; Ye & Namkoong, 2024), and prove that they in fact cannot guarantee exchangeability despite introducing significant computational overhead. Through empirical evaluation, we find that these custom architectures can significantly underperform compared to standard causal masking, highlighting the need for new architectural innovations in Transformer-based modeling of exchangeable sequences.

The role of hidden units in recurrent neural networks is typically seen as modeling memory, with research focusing on enhancing information retention through gating mechanisms. A less explored perspective views hidden units as active participants in the computation performed by the network, rather than passive memory stores. In this work, we revisit bilinear operations, which involve multiplicative interactions between hidden units and input embeddings. We demonstrate theoretically and empirically that they constitute a natural inductive bias for representing the evolution of hidden states in state tracking tasks. These are the simplest type of tasks that require hidden units to actively contribute to the behavior of the network. We also show that bilinear state updates form a natural hierarchy corresponding to state tracking tasks of increasing complexity, with popular linear recurrent networks such as Mamba residing at the lowest-complexity center of that hierarchy.

Forecasting multi-step user behavior trajectories requires reasoning over structured preferences across future actions, a challenge overlooked by traditional sequential recommendation. This problem is critical for applications such as personalized commerce and adaptive content delivery, where anticipating a user’s complete action sequence enhances both satisfaction and business outcomes. We identify an essential limitation of existing paradigms: their inability to capture global, listwise dependencies among sequence items. To address this, we formulate User Behavior Trajectory Prediction (UBTP) as a new task setting that explicitly models longterm user preferences. We introduce Listwise Preference Diffusion Optimization (LPDO), a diffusion-based training framework that directly optimizes structured preferences over entire item sequences. LPDO incorporates a Plackett–Luce supervision signal and derives a tight variational lower bound aligned with listwise ranking likelihoods, enabling coherent preference generation across denoising steps and overcoming the independent-token assumption of prior diffusion methods. To rigorously evaluate multi-step prediction quality, we propose the task-specific metric: Sequential Match (SeqMatch), which measures exact trajectory agreement, and adopt Perplexity (PPL), which assesses probabilistic fidelity. Extensive experiments on real-world user behavior benchmarks demonstrate that LPDO consistently outperforms state-of-the-art baselines, establishing a new benchmark for structured preference learning with diffusion models.

The attention mechanism is a core component of the Transformer architecture. Various methods have been developed to compute attention scores, including multi-head attention (MHA), multi-query attention, group-query attention and so on. We further analyze the MHA and observe that its performance improves as the number of attention heads increases, provided the hidden size per head remains sufficiently large. Therefore, increasing both the head count and hidden size per head with minimal parameter overhead can lead to significant performance gains at a low cost. Motivated by this insight, we introduce Simulated Attention Score (SAS), which **maintains a compact model size while simulating a larger number of attention heads and hidden feature dimension per head.** This is achieved by projecting a low-dimensional head representation into a higher-dimensional space, effectively increasing attention capacity without increasing parameter count. Beyond the head representations, we further extend the simulation approach to feature dimension of the key and query embeddings, enhancing expressiveness by mimicking the behavior of a larger model while preserving the original model size. **To control the parameter cost, we also propose Parameter-Efficient Attention Aggregation (PEAA).** Comprehensive experiments on a variety of datasets and tasks demonstrate the effectiveness of the proposed SAS method, achieving significant improvements over different attention variants.

3D generation from natural language offers significant potential to reduce expert manual modeling efforts and enhance accessibility to 3D assets. However, existing methods often yield unstructured meshes and exhibit poor interactivity, making them impractical for artistic workflows. To address these limitations, we represent 3D assets as shape programs and introduce ShapeCraft, a novel multi-agent framework for text-to-3D generation. At its core, we propose a Graph-based Procedural Shape (GPS) representation that decomposes complex natural language into a structured graph of sub-tasks, thereby facilitating accurate LLM comprehension and interpretation of spatial relationships and semantic shape details. Specifically, LLM agents hierarchically parse user input to initialize GPS, then iteratively refine procedural modeling and painting to produce structured, textured, and interactive 3D assets. Qualitative and quantitative experiments demonstrate ShapeCraft's superior performance in generating geometrically accurate and semantically rich 3D assets compared to existing LLM-based agents. We further show the versatility of ShapeCraft through examples of animated and user-customized editing, highlighting its potential for broader interactive applications.

We explore a novel problem in streaming submodular maximization, inspired by the dynamics of news-recommendation platforms. We consider a setting where users can visit a news web\-site at any time, and upon each visit, the web\-site must display up to $k$ news items. User interactions are inherently stochastic: each news item presented to the user is consumed with a certain acceptance probability by the user, and each news item covers certain topics. Our goal is to design a streaming algorithm that maximizes the expected total topic coverage. To address this problem, we establish a connection to submodular maximization subject to a matroid constraint. We show that we can effectively adapt previous methods to address our problem when the number of user visits is known in advance or linear-size memory in the stream length is available. However, in more realistic scenarios where only an upper bound on the visits and sublinear memory is available, the algorithms fail to guarantee any bounded performance. To overcome these limitations, we introduce a new online streaming algorithm that achieves a competitive ratio of $1/8\delta$, where $\delta$ controls the approximation quality. Moreover, it requires only a single pass over the stream, and uses memory independent of the stream length. Empirically, our algorithms consistently outperform the baselines.

We study the _multinomial logit_ (MNL) contextual bandit problem for sequential assortment selection. Although most existing research assumes utility functions to be linear in item features, this linearity assumption restricts the modeling of intricate interactions between items and user preferences. A recent work (Zhang & Luo, 2024) has investigated general utility function classes, yet its method faces fundamental trade-offs between computational tractability and statistical efficiency. To address this limitation, we propose a computationally efficient algorithm for MNL contextual bandits leveraging the upper confidence bound principle, specifically designed for non-linear parametric utility functions, including those modeled by neural networks. Under a realizability assumption and a mild geometric condition on the utility function class, our algorithm achieves a regret bound of $\tilde{\mathcal{O}}(\sqrt{T})$, where $T$ denotes the total number of rounds. Our result establishes that sharp $\tilde{\mathcal{O}}(\sqrt{T})$-regret is attainable even with neural network-based utilities, without relying on strong assumptions such as neural tangent kernel approximations. To the best of our knowledge, our proposed method is the first computationally tractable algorithm for MNL contextual bandits with non-linear utilities that provably attains $\tilde{\mathcal{O}}(\sqrt{T})$ regret. Comprehensive numerical experiments validate the effectiveness of our approach, showing robust performance not only in realizable settings but also in scenarios with model misspecification.

Linearly transforming stimulus representations of deep neural networks yields high-performing models of behavioral and neural responses to complex stimuli. But does the test accuracy of such predictions identify genuine representational alignment? We addressed this question through a large-scale model-recovery study. Twenty diverse vision models were linearly aligned to 4.5 million behavioral judg- ments from the THINGS odd-one-out dataset and calibrated to reproduce human response variability. For each model in turn, we sampled synthetic responses from its probabilistic predictions, fitted all candidate models to the synthetic data, and tested whether the data-generating model would re-emerge as the best predictor of the simulated data. Model recovery accuracy improved with training-set size but plateaued below 80%, even at millions of simulated trials. Regression analyses linked misidentification primarily to shifts in representational geometry induced by the linear transformation, as well as to the effective dimensionality of the transformed features. These findings demonstrate that, even with massive behavioral data, overly flexible alignment metrics may fail to guide us toward artificial representations that are genuinely more human-aligned. Model comparison experiments must be designed to balance the trade-off between predictive accuracy and identifiability—ensuring that the best-fitting model is also the right one.

The classic Mallows model is a foundational tool for modeling user preferences. However, it has limitations in capturing real-world scenarios, where users often focus only on a limited set of preferred items and are indifferent to the rest. To address this, extensions such as the top-$k$ Mallows model have been proposed, aligning better with practical applications. In this paper, we address several challenges related to the generalized top-$k$ Mallows model, with a focus on analyzing buyer choices. Our key contributions are: (1) a novel sampling scheme tailored to generalized top-$k$ Mallows models, (2) an efficient algorithm for computing choice probabilities under this model, and (3) an active learning algorithm for estimating the model parameters from observed choice data. These contributions provide new tools for analysis and prediction in critical decision-making scenarios. We present a rigorous mathematical analysis for the performance of our algorithms. Furthermore, through extensive experiments on synthetic data and real-world data, we demonstrate the scalability and accuracy of our proposed methods, and we compare the predictive power of Mallows model for top-$k$ lists compared to the simpler Multinomial Logit model.

In photography, an All-in-Focus (AiF) image may not always effectively convey the creator’s intent. Professional photographers manipulate Depth of Field (DoF) to control which regions appear sharp or blurred, achieving compelling artistic effects. For general users, the ability to flexibly adjust DoF enhances creative expression and image quality. In this paper, we propose UiD, a User-Instructed DoF control framework, that allows users to specify refocusing regions using text, box, or point prompts, and our UiD automatically simulates in-focus and out-of-focus (OoF) regions in the given images. However, controlling defocus blur in a single-lens camera remains challenging due to the difficulty in estimating depth-aware aberrations and the suboptimal quality of reconstructed AiF images. To address this, we leverage dual-pixel (DP) sensors, commonly found in DSLR-style and mobile cameras. DP sensors provide a small-baseline stereo pair in a single snapshot, enabling depth-aware aberration estimation. Our approach first establishes an invertible mapping between OoF and AiF images to learn spatially varying defocus kernels and the disparity features. These depth-aware kernels enable bidirectional image transformation—deblurring out-of-focus (OoF) images into all-in-focus (AiF) representations, and conversely reblurring AiF images into OoF outputs—by seamlessly switching between the kernel and its inverse form. These depth-aware kernels enable both deblurring of OoF images into AiF representations and reblurring AiF images into OoF representations by flexibly switching its original form to its inverse one. For user-guided refocusing, we first generate masks based on user prompts using SAM, which modulates disparity features in closed form, allowing dynamic kernel re-estimation for reblurring. This achieves user-controlled refocusing effects. Extensive experiments on both common datasets and the self-collected dataset demonstrate that UiD offers superior flexibility and quality in DoF manipulation imaging.

We study the problem of aligning a generative model's response with a user's preferences. Recent works have proposed several different formulations for personalized alignment; however, they either require a large amount of user preference queries or require that the preference be explicitly specified as a text input. In this paper, we propose a novel inference-time personalized alignment method, UserAlign, that elicits the user's preferences with a few queries as pairwise response comparisons. In particular, UserAlign builds on the theoretical framework of best-arm identification in logistic bandits and selects a personalized response from a fixed pool of the model's generated responses. The key idea is to consider the user's feedback consistent and noise-free, and incorporate it into the theoretical framework to identify the best response quickly. Experimental results across several tasks, involving personalized text and image generation, showcase the effectiveness of UserAlign in achieving personalized alignment.

As AI systems become more capable, deceptive behaviors can undermine evaluation and mislead users at deployment. Recent work has shown that lie detectors can accurately classify deceptive behavior, but they are not typically used in the training pipeline due to concerns around contamination and objective hacking. We examine these concerns by incorporating a lie detector into the labelling step of LLM post-training and evaluating whether the learned policy is genuinely more honest, or instead learns to fool the lie detector while remaining deceptive. Using DolusChat, a novel 65k-example dataset with paired truthful/deceptive responses, we identify three key factors that determine the honesty of learned policies: amount of exploration during preference learning, lie detector accuracy, and KL regularization strength. We find that preference learning with lie detectors and GRPO can lead to policies which evade lie detectors, with deception rates of over 85\%. However, if the lie detector true positive rate (TPR) or KL regularization is sufficiently high, GRPO learns honest policies. In contrast, off-policy algorithms (DPO) consistently lead to deception rates under 25\% for realistic TPRs. Our results illustrate a more complex picture than previously assumed: depending on the context, lie-detector-enhanced training can be a powerful tool for scalable oversight, or a counterproductive method encouraging undetectable misalignment.

Local field potentials (LFPs) can be routinely recorded alongside spiking activity in intracortical neural experiments, measure a larger complementary spatiotemporal scale of brain activity for scientific inquiry, and can offer practical advantages over spikes, including greater long-term stability, robustness to electrode degradation, and lower power requirements. Despite these advantages, recent neural modeling frameworks have largely focused on spiking activity since LFP signals pose inherent modeling challenges due to their aggregate, population-level nature, often leading to lower predictive power for downstream task variables such as motor behavior. To address this challenge, we introduce a cross-modal knowledge distillation framework that transfers high-fidelity representational knowledge from pretrained multi-session spike transformer models to LFP transformer models. Specifically, we first train a teacher spike model across multiple recording sessions using a masked autoencoding objective with a session-specific neural tokenization strategy. We then align the latent representations of the student LFP model to those of the teacher spike model. Our results show that the distilled LFP models consistently outperform single- and multi-session LFP baselines in both fully unsupervised and supervised settings, and can generalize to other sessions without additional distillation while maintaining superior performance. These findings demonstrate that cross-modal knowledge distillation is a powerful and scalable approach for leveraging high-performing spike models to develop more accurate LFP models.

As large language models (LLMs) are increasingly used as personalized user assistants, effectively adapting to users' evolving preferences is critical for delivering high-quality personalized responses. While user preferences are often stable in content, their relative strengths shift over time due to changing goals and contexts. Therefore, modeling these dynamic preference strengths can enable finer-grained personalization. However, current methods face two major challenges: (i) limited user feedback makes it difficult to estimate preference strengths accurately, and (ii) natural language ambiguity limits the controllability of preference-guided generation. To address these issues, we propose AdaPA-Agent, a LLM-agent personalization framework that models dynamic preference strengths via Adaptive Preference Arithmetic. First, instead of requiring additional user feedback, AdaPA-Agent employs an alignment-based strength estimation module to estimate the strength of user preferences from the existing user-agent interaction. Then, it guides controllable personalized generation by linearly combining next-token distributions, weighted by the estimated strengths of individual preferences. Experiments on two personalization tasks-conversational recommendation and personalized web interaction-demonstrate that AdaPA-Agent better aligning with users' changing intents, and has achieved over 18.9\% and 14.2\% improvements compared to ReAct, the widely-used agent framework.

Understanding user intent is essential for situational and context-aware decision-making. Motivated by a real-world scenario, this work addresses intent predictions of smart device users in the vicinity of vehicles by modeling sequential spatiotemporal data. However, in real-world scenarios, environmental factors and sensor limitations can result in non-stationary and irregularly sampled data, posing significant challenges. To address these issues, we propose STaRFormer, a Transformer-based approach that can serve as a universal framework for sequential modeling. STaRFormer utilizes a new dynamic attention-based regional masking scheme combined with a novel semi-supervised contrastive learning paradigm to enhance task-specific latent representations. Comprehensive experiments on 56 datasets varying in types (including non-stationary and irregularly sampled), tasks, domains, sequence lengths, training samples, and applications demonstrate the efficacy of STaRFormer, achieving notable improvements over state-of-the-art approaches.

The neural activity in the visual processing is influenced by both external stimuli and internal brain states. Ideally, a neural predictive model should account for both of them. Currently, there are no dynamic encoding models that explicitly model a latent state and the entire neuronal response distribution. We address this gap by proposing a probabilistic model that predicts the joint distribution of the neuronal responses from video stimuli and stimulus-independent latent factors. After training and testing our model on mouse V1 neuronal responses, we find that it outperforms video-only models in terms of log-likelihood and achieves improvements in likelihood and correlation when conditioned on responses from other neurons. Furthermore, we find that the learned latent factors strongly correlate with mouse behavior and that they exhibit patterns related to the neurons’ position on the visual cortex, although the model was trained without behavior and cortical coordinates. Our findings demonstrate that unsupervised learning of latent factors from population responses can reveal biologically meaningful structure that bridges sensory processing and behavior, without requiring explicit behavioral annotations during training. The code is attached to the submission.

Recommenders aim to rank items from a discrete item corpus in line with user interests, yet suffer from extremely sparse user preference data. Recent advances in diffusion models have inspired diffusion-based recommenders, which alleviate sparsity by injecting noise during a forward process to prevent collapse of perturbed preference distributions. However, current diffusion‑based recommenders predominantly rely on continuous Gaussian noise, which is intrinsically mismatched with the discrete nature of user preference data in recommendation. In this paper, building upon recent advances in discrete diffusion, we propose \textbf{PreferGrow}, a discrete diffusion-based recommender modeling preference ratios by fading and growing user preferences over the discrete item corpus. PreferGrow differs from existing diffusion-based recommenders in three core aspects: (1) Discrete modeling of preference ratios: PreferGrow models relative preference ratios between two items, where a positive value indicates a more preferred one over another less preferred. This formulation aligns naturally with the discrete and ranking-oriented nature of recommendation tasks. (2) Perturbing via preference fading: Instead of injecting continuous noise, PreferGrow fades user preferences by replacing the preferred item with alternatives---physically akin to negative sampling---thereby eliminating the need for any prior noise assumption. (3) Preference reconstruction via growing: PreferGrow reconstructs user preferences by iteratively growing the preference signal from the estimated ratios. We further provide theoretical analysis showing that PreferGrow preserves key properties of discrete diffusion processes. PreferGrow provides a well-defined matrix‑based formulation for discrete diffusion-based recommendation and empirically outperforms existing diffusion‑based recommenders across five benchmark datasets, underscoring its superior effectiveness. Our codes are available at \url{https://anonymous.4open.science/r/PreferGrow_Commit-2259/}.

Reward modeling, crucial for aligning large language models (LLMs) with human preferences, is often bottlenecked by the high cost of preference data. Existing textual data synthesis methods are computationally expensive. We propose a novel framework LENS for synthesizing preference data directly in the LLM's latent embedding space. Our method employs a Variational Autoencoder (VAE) to learn a structured latent representation of response embeddings. By performing controlled perturbations in this latent space and decoding back to the embedding space, we efficiently generate diverse, semantically consistent synthetic preference pairs, bypassing costly text generation and annotation. We provide theoretical guarantees that our synthesized pairs approximately preserve original preference ordering and improve reward model generalization. Empirically, our latent-space synthesis significantly outperforms text-based augmentation on standard benchmarks, achieving superior results while being 18× faster in generation and using a 16,000× smaller model. Our work offers a scalable and effective alternative for enhancing reward modeling through efficient data augmentation. Code is publicly available at https://github.com/deeplearning-wisc/lens.

Transformers have become the cornerstone of modern large-scale language models, but their reliance on softmax attention poses a computational bottleneck at both training and inference. Recurrent models offer high efficiency, but compressing the full sequence into a fixed-size and holistic representation can suffer from memory degradation in long contexts and limit fine-grained retrieval. To address this, we propose RAT, an intermediate design that bridges the efficiency of RNNs and capacity of attention. RAT partitions the input into chunks, applies recurrence within each chunk for local dependencies, and softmax-based attention across chunks for long-range interactions. This design mitigates memory degradation and enables direct access to distant tokens, while retaining computational efficiency. Empirically, with a chunk size of 16, the RAT block achieves a $7\times$ improvement in training speed for 100K sequence length and $9\times$ in generation at the 4K position, while maintaining similar performance compared to standard attention. We demonstrate this by training 1.3B parameter models from scratch and performing large-scale evaluations, including short- and long-context benchmarks, as well as supervised fine-tuning (SFT). We further propose a hybrid architecture that interleaves RAT with local attention. By combining efficient long-range modeling with strong local interactions, this hybrid design not only improves inference speed and reduces cache memory usage, but also consistently enhances performance and shows the overall best results. Code is available at \url{https://github.com/CLAIRE-Labo/RAT}.

Recent work analyzing in-context learning (ICL) has identified a broad set of strategies that describe model behavior in different experimental conditions. We aim to unify these findings by asking why a model learns these disparate strategies in the first place. Specifically, we start with the observation that when trained to learn a mixture of tasks, as is popular in the literature, the strategies learned by a model for performing ICL can be captured by a family of Bayesian predictors: a memorizing predictor, which assumes a discrete prior on the set of seen tasks, and a generalizing predictor, where the prior matches the underlying task distribution. Adopting the normative lens of rational analysis, where a learner’s behavior is explained as an optimal adaptation to data given computational constraints, we develop a hierarchical Bayesian framework that almost perfectly predicts Transformer next- token predictions throughout training—without assuming access to its weights. Under this framework, pretraining is viewed as a process of updating the posterior probability of different strategies, and inference-time behavior as a posterior- weighted average over these strategies’ predictions. Our framework draws on common assumptions about neural network learning dynamics, which make explicit a tradeoff between loss and complexity among candidate strategies: beyond how well it explains the data, a model’s preference towards implementing a strategy is dictated by its complexity. This helps explain well-known ICL phenomena, while offering novel predictions: e.g., we show a superlinear trend in the timescale for transitioning from generalization to memorization as task diversity increases. Overall, our work advances an explanatory and predictive account of ICL grounded in tradeoffs between strategy loss and complexity.