Opinion dynamics models such as the bounded confidence models (BCMs) describe how a population can reach consensus, fragmentation, or polarization, depending on a few parameters. Connecting such models to real-world data could help understanding such phenomena, testing model assumptions. To this end, estimation of model parameters is a key aspect, and maximum likelihood estimation provides a principled way to tackle it. Here, our goal is to outline the properties of statistical estimators of the two key BCM parameters: the confidence bound and the convergence rate. We find that their maximum likelihood estimators present different characteristics: the one for the confidence bound presents a small-sample bias but is consistent, while the estimator of the convergence rate shows a persistent bias. Moreover, the joint parameter estimation is affected by identifiability issues for specific regions of the parameter space, as several local maxima are present in the likelihood function. Our results show how the analysis of the likelihood function is a fruitful approach for better understanding the pitfalls and possibilities of estimating the parameters of opinion dynamics models, and more in general, agent-based models, and for offering formal guarantees for their calibration.
Recently, hyperspectral image generation has received increasing attention, but existing generative models rely on conditional generation schemes, which limits the diversity of generated images. Diffusion models are popular for their ability to generate high-quality samples, but adapting these models from RGB to hyperspectral data presents the challenge of high dimensionality and physical constraints. To address these challenges, we propose a novel diffusion model guided by hyperspectral unmixing. Our model comprises two key modules: an unmixing autoencoder module and an abundance diffusion module. The unmixing autoencoder module leverages unmixing guidance to shift the generative task from the image space to the low-dimensional abundance space, significantly reducing computational complexity while preserving high fidelity. The abundance diffusion module generates samples that satisfy the constraints of non-negativity and unity, ensuring the physical consistency of the reconstructed HSIs. Additionally, we introduce two evaluation metrics tailored to hyperspectral data. Empirical results, evaluated using both traditional metrics and our proposed metrics, indicate that our model is capable of generating high-quality and diverse hyperspectral images, offering an advancement in hyperspectral data generation.
Discrete choice modelling is a theory-driven modelling framework for understanding and forecasting choice behaviour. To obtain behavioural insights, modellers test several competing model specifications in their attempts to discover the 'true' data generation process. This trial-and-error process requires expertise, is time-consuming, and relies on subjective theoretical assumptions. Although metaheuristics have been proposed to assist choice modellers, they treat model specification as a classic optimisation problem, relying on static strategies, applying predefined rules, and neglecting outcomes from previous estimated models. As a result, current metaheuristics struggle to prioritise promising search regions, adapt exploration dynamically, and transfer knowledge to other modelling tasks. To address these limitations, we introduce a deep reinforcement learning-based framework where an 'agent' specifies models by estimating them and receiving rewards based on goodness-of-fit and parsimony. Results demonstrate the agent dynamically adapts its strategies to identify promising specifications across data generation processes, showing robustness and potential transferability, without prior domain knowledge.
Speaker recognition systems are often limited to classification tasks and struggle to generate detailed speaker characteristics or provide context-rich descriptions. These models primarily extract embeddings for speaker identification but fail to capture demographic attributes such as dialect, gender, and age in a structured manner. This paper introduces CoLMbo, a Speaker Language Model (SLM) that addresses these limitations by integrating a speaker encoder with prompt-based conditioning. This allows for the creation of detailed captions based on speaker embeddings. CoLMbo utilizes user-defined prompts to adapt dynamically to new speaker characteristics and provides customized descriptions, including regional dialect variations and age-related traits. This innovative approach not only enhances traditional speaker profiling but also excels in zero-shot scenarios across diverse datasets, marking a significant advancement in the field of speaker recognition.
Background: The growing demand for efficient and deployable language models has led to increased interest in Small Language Models (SLMs). However, existing research remains fragmented, lacking a unified lifecycle perspective. Objective: This study aims to define a comprehensive lifecycle framework for SLMs by synthesizing insights from academic literature and practitioner sources. Method: We conducted a comprehensive survey of 36 works, analyzing and categorizing lifecycle-relevant techniques. Results: We propose a modular lifecycle model structured into main, optional, and cross-cutting components. The model captures key interconnections across stages, supporting method reuse, co-adaptation, and lifecycle-awareness. Conclusion: Our framework provides a coherent foundation for developing and maintaining SLMs, bridging theory and practice, and guiding future research and tool development.
Model stealing poses a significant security risk in machine learning by enabling attackers to replicate a black-box model without access to its training data, thus jeopardizing intellectual property and exposing sensitive information. Recent methods that use pre-trained diffusion models for data synthesis improve efficiency and performance but rely heavily on manually crafted prompts, limiting automation and scalability, especially for attackers with little expertise. To assess the risks posed by open-source pre-trained models, we propose a more realistic threat model that eliminates the need for prompt design skills or knowledge of class names. In this context, we introduce Stealix, the first approach to perform model stealing without predefined prompts. Stealix uses two open-source pre-trained models to infer the victim model's data distribution, and iteratively refines prompts through a genetic algorithm, progressively improving the precision and diversity of synthetic images. Our experimental results demonstrate that Stealix significantly outperforms other methods, even those with access to class names or fine-grained prompts, while operating under the same query budget. These findings highlight the scalability of our approach and suggest that the risks posed by pre-trained generative models in model stealing may be greater than previously recognized.
Recently, we have witnessed the great success of the generalist model in natural language processing. The generalist model is a general framework trained with massive data and is able to process various downstream tasks simultaneously. Encouraged by their impressive performance, an increasing number of researchers are venturing into the realm of applying these models to computer vision tasks. However, the inputs and outputs of vision tasks are more diverse, and it is difficult to summarize them as a unified representation. In this paper, we provide a comprehensive overview of the vision generalist models, delving into their characteristics and capabilities within the field. First, we review the background, including the datasets, tasks, and benchmarks. Then, we dig into the design of frameworks that have been proposed in existing research, while also introducing the techniques employed to enhance their performance. To better help the researchers comprehend the area, we take a brief excursion into related domains, shedding light on their interconnections and potential synergies. To conclude, we provide some real-world application scenarios, undertake a thorough examination of the persistent challenges, and offer insights into possible directions for future research endeavors.
Multi-modal graphs, which integrate diverse multi-modal features and relations, are ubiquitous in real-world applications. However, existing multi-modal graph learning methods are typically trained from scratch for specific graph data and tasks, failing to generalize across various multi-modal graph data and tasks. To bridge this gap, we explore the potential of Multi-modal Graph Large Language Models (MG-LLM) to unify and generalize across diverse multi-modal graph data and tasks. We propose a unified framework of multi-modal graph data, task, and model, discovering the inherent multi-granularity and multi-scale characteristics in multi-modal graphs. Specifically, we present five key desired characteristics for MG-LLM: 1) unified space for multi-modal structures and attributes, 2) capability of handling diverse multi-modal graph tasks, 3) multi-modal graph in-context learning, 4) multi-modal graph interaction with natural language, and 5) multi-modal graph reasoning. We then elaborate on the key challenges, review related works, and highlight promising future research directions towards realizing these ambitious characteristics. Finally, we summarize existing multi-modal graph datasets pertinent for model training. We believe this paper can contribute to the ongoing advancement of the research towards MG-LLM for generalization across multi-modal graph data and tasks.
The development lifecycle of generative AI systems requires continual evaluation, data acquisition, and annotation, which is costly in both resources and time. In practice, rapid iteration often makes it necessary to rely on synthetic annotation data because of the low cost, despite the potential for substantial bias. In this paper, we develop novel, cost-aware methods for actively balancing the use of a cheap, but often inaccurate, weak rater -- such as a model-based autorater that is designed to automatically assess the quality of generated content -- with a more expensive, but also more accurate, strong rater alternative such as a human. More specifically, the goal of our approach is to produce a low variance, unbiased estimate of the mean of the target "strong" rating, subject to some total annotation budget. Building on recent work in active and prediction-powered statistical inference, we derive a family of cost-optimal policies for allocating a given annotation budget between weak and strong raters so as to maximize statistical efficiency. Using synthetic and real-world data, we empirically characterize the conditions under which these policies yield improvements over prior methods. We find that, especially in tasks where there is high variability in the difficulty of examples, our policies can achieve the same estimation precision at a far lower total annotation budget than standard evaluation methods.
This work addresses a fundamental barrier in recommender systems: the inability to generalize across domains without extensive retraining. Traditional ID-based approaches fail entirely in cold-start and cross-domain scenarios where new users or items lack sufficient interaction history. Inspired by foundation models' cross-domain success, we develop a foundation model for sequential recommendation that achieves genuine zero-shot generalization capabilities. Our approach fundamentally departs from existing ID-based methods by deriving item representations exclusively from textual features. This enables immediate embedding of any new item without model retraining. We introduce unified item tokenization with Finite Scalar Quantization that transforms heterogeneous textual descriptions into standardized discrete tokens. This eliminates domain barriers that plague existing systems. Additionally, the framework features hybrid bidirectional-causal attention that captures both intra-item token coherence and inter-item sequential dependencies. An efficient catalog-aware beam search decoder enables real-time token-to-item mapping. Unlike conventional approaches confined to their training domains, RecGPT naturally bridges diverse recommendation contexts through its domain-invariant tokenization mechanism. Comprehensive evaluations across six datasets and industrial scenarios demonstrate consistent performance advantages.
Recent advancements in large language models (LLMs), such as DeepSeek-R1 and OpenAI-o1, have demonstrated the significant effectiveness of test-time scaling, achieving substantial performance gains across various benchmarks. These advanced models utilize deliberate "thinking" steps to systematically enhance answer quality. In this paper, we propose leveraging these high-quality outputs generated by reasoning-intensive models to improve less computationally demanding, non-reasoning models. We explore and compare methodologies for utilizing the answers produced by reasoning models to train and improve non-reasoning models. Through straightforward Supervised Fine-Tuning (SFT) experiments on established benchmarks, we demonstrate consistent improvements across various benchmarks, underscoring the potential of this approach for advancing the ability of models to answer questions directly.
We study the off-dynamics offline reinforcement learning problem, where the goal is to learn a policy from offline datasets collected from source and target domains with mismatched transition. Existing off-dynamics offline RL methods typically either filter source transitions that resemble those of the target domain or apply reward augmentation to source data, both constrained by the limited transitions available from the target domain. As a result, the learned policy is unable to explore target domain beyond the offline datasets. We propose MOBODY, a Model-Based Off-Dynamics offline RL algorithm that addresses this limitation by enabling exploration of the target domain via learned dynamics. MOBODY generates new synthetic transitions in the target domain through model rollouts, which are used as data augmentation during offline policy learning. Unlike existing model-based methods that learn dynamics from a single domain, MOBODY tackles the challenge of mismatched dynamics by leveraging both source and target datasets. Directly merging these datasets can bias the learned model toward source dynamics. Instead, MOBODY learns target dynamics by discovering a shared latent representation of states and transitions across domains through representation learning. To stabilize training, MOBODY incorporates a behavior cloning loss that regularizes the policy. Specifically, we introduce a Q-weighted behavior cloning loss that regularizes the policy toward actions with high target-domain Q-values, rather than uniformly imitating all actions in the dataset. These Q-values are learned from an enhanced target dataset composed of offline target data, augmented source data, and rollout data from the learned target dynamics. We evaluate MOBODY on MuJoCo benchmarks and show that it significantly outperforms state-of-the-art baselines, with especially pronounced improvements in challenging scenarios.
Reward models are used throughout the post-training of language models to capture nuanced signals from preference data and provide a training target for optimization across instruction following, reasoning, safety, and more domains. The community has begun establishing best practices for evaluating reward models, from the development of benchmarks that test capabilities in specific skill areas to others that test agreement with human preferences. At the same time, progress in evaluation has not been mirrored by the effectiveness of reward models in downstream tasks -- simpler direct alignment algorithms are reported to work better in many cases. This paper introduces RewardBench 2, a new multi-skill reward modeling benchmark designed to bring new, challenging data for accuracy-based reward model evaluation -- models score about 20 points on average lower on RewardBench 2 compared to the first RewardBench -- while being highly correlated with downstream performance. Compared to most other benchmarks, RewardBench 2 sources new human prompts instead of existing prompts from downstream evaluations, facilitating more rigorous evaluation practices. In this paper, we describe our benchmark construction process and report how existing models perform on it, while quantifying how performance on the benchmark correlates with downstream use of the models in both inference-time scaling algorithms, like best-of-N sampling, and RLHF training algorithms like proximal policy optimization.
Large language models are quickly becoming the foundation for intelligent agents that are capable of using tools. However, training such agents is challenging because it requires human creation and annotation of a diverse set of tasks, tools, and evaluation criteria. In this paper, we propose the Self-Challenging framework for training an agent on high-quality tasks that are generated by itself. The agent first plays the role of challenger and generates a task after interacting with the given tools. The tasks take the form of a novel general class of problems termed Code-as-Task, which are defined by an instruction, a verification function and solution and failure cases which serve as tests, allowing to filter only for high-quality tasks. The agent then takes an executor role and trains on those tasks with reinforcement learning using the evaluation feedback as a reward. Evaluation on two existing multi-turn tool-use agent benchmarks, M3ToolEval and TauBench, shows the Self-Challenging framework achieves over a two-fold improvement in Llama-3.1-8B-Instruct, despite using only self-generated training data.
Large Reasoning Models (LRMs) excel at complex tasks using Chain-of-Thought (CoT) reasoning. However, their tendency to overthinking leads to unnecessarily lengthy reasoning chains, dramatically increasing inference costs. To mitigate this issue, we introduce VeriThinker, a novel approach for CoT compression. Unlike conventional methods that fine-tune LRMs directly on the original reasoning task using synthetic concise CoT data, we innovatively fine-tune the model solely through an auxiliary verification task. By training LRMs to accurately verify the correctness of CoT solutions, the LRMs inherently become more discerning about the necessity of subsequent self-reflection steps, thereby effectively suppressing overthinking. Extensive experiments validate that VeriThinker substantially reduces reasoning chain lengths while maintaining or even slightly improving accuracy. When applied to DeepSeek-R1-Distill-Qwen-7B, our approach reduces reasoning tokens on MATH500 from 3790 to 2125 while improving accuracy by 0.8% (94.0% to 94.8%), and on AIME25, tokens decrease from 14321 to 10287 with a 2.1% accuracy gain (38.7% to 40.8%). Additionally, our experiments demonstrate that VeriThinker can also be zero-shot generalized to speculative reasoning. Code is available at https://github.com/czg1225/VeriThinker
Transformer LMs show emergent reasoning that resists mechanistic understanding. We offer a statistical physics framework for continuous-time chain-of-thought reasoning dynamics. We model sentence-level hidden state trajectories as a stochastic dynamical system on a lower-dimensional manifold. This drift-diffusion system uses latent regime switching to capture diverse reasoning phases, including misaligned states or failures. Empirical trajectories (8 models, 7 benchmarks) show a rank-40 projection (balancing variance capture and feasibility) explains ~50% variance. We find four latent reasoning regimes. An SLDS model is formulated and validated to capture these features. The framework enables low-cost reasoning simulation, offering tools to study and predict critical transitions like misaligned states or other LM failures.
While many neural networks focus on layers to process information, the GAIN model uses a grid-based structure to improve biological plausibility and the dynamics of the model. The grid structure helps neurons to interact with their closest neighbors and improve their connections with one another, which is seen in biological neurons. While also being implemented with the Izhikevich model this approach allows for a computationally efficient and biologically accurate simulation that can aid in the development of neural networks, large scale simulations, and the development in the neuroscience field. This adaptation of the Izhikevich model can improve the dynamics and accuracy of the model, allowing for its uses to be specialized but efficient.
Modern deepfake detection models have achieved strong performance even on the challenging cross-dataset task. However, detection performance under non-ideal conditions remains very unstable, limiting success on some benchmark datasets and making it easy to circumvent detection. Inspired by the move to a more real-world degradation model in the area of image super-resolution, we have developed a Practical Manipulation Model (PMM) that covers a larger set of possible forgeries. We extend the space of pseudo-fakes by using Poisson blending, more diverse masks, generator artifacts, and distractors. Additionally, we improve the detectors' generality and robustness by adding strong degradations to the training images. We demonstrate that these changes not only significantly enhance the model's robustness to common image degradations but also improve performance on standard benchmark datasets. Specifically, we show clear increases of $3.51\%$ and $6.21\%$ AUC on the DFDC and DFDCP datasets, respectively, over the s-o-t-a LAA backbone. Furthermore, we highlight the lack of robustness in previous detectors and our improvements in this regard. Code can be found at https://github.com/BenediktHopf/PMM
Neural networks (NNs) have achieved tremendous success over the past decade, yet they are still extremely difficult to interpret. In contrast, linear models are less expressive but offer inherent interpretability. Linear coefficients are interpretable as the marginal effect of a feature on the prediction, assuming all other features are kept fixed. To combine the benefits of both approaches, we introduce NIMO (Nonlinear Interpretable MOdel). The key idea is to define a model where the NN is designed to learn nonlinear corrections to the linear model predictions, while also maintaining the original interpretability of the linear coefficients. Relevantly, we develop an optimization algorithm based on profile likelihood that elegantly allows for optimizing over the NN parameters while updating the linear coefficients analytically. By relying on adaptive ridge regression we can easily incorporate sparsity constraints as well. We show empirically that we can recover the underlying linear coefficients while significantly improving the predictive accuracy. Compared to other hybrid interpretable approaches, our model is the only one that actually maintains the same interpretability of linear coefficients as in linear models. We also achieve higher performance on various regression and classification settings.
The control of spatio-temporally chaos is challenging because of high dimensionality and unpredictability. Model-free reinforcement learning (RL) discovers optimal control policies by interacting with the system, typically requiring observations of the full physical state. In practice, sensors often provide only partial and noisy measurements (observations) of the system. The objective of this paper is to develop a framework that enables the control of chaotic systems with partial and noisy observability. The proposed method, data-assimilated model-informed reinforcement learning (DA-MIRL), integrates (i) low-order models to approximate high-dimensional dynamics; (ii) sequential data assimilation to correct the model prediction when observations become available; and (iii) an off-policy actor-critic RL algorithm to adaptively learn an optimal control strategy based on the corrected state estimates. We test DA-MIRL on the spatiotemporally chaotic solutions of the Kuramoto-Sivashinsky equation. We estimate the full state of the environment with (i) a physics-based model, here, a coarse-grained model; and (ii) a data-driven model, here, the control-aware echo state network, which is proposed in this paper. We show that DA-MIRL successfully estimates and suppresses the chaotic dynamics of the environment in real time from partial observations and approximate models. This work opens opportunities for the control of partially observable chaotic systems.