Federated Learning (FL) allows collaboration between different parties, while ensuring that the data across these parties is not shared. However, not every collaboration is helpful in terms of the resulting model performance. Therefore, it is an important challenge to select the correct participants in a collaboration. As it currently stands, most of the efforts in participant selection in the literature have focused on Horizontal Federated Learning (HFL), which assumes that all features are the same across all participants, disregarding the possibility of different features across participants which is captured in Vertical Federated Learning (VFL). To close this gap in the literature, we propose a novel method VFL-RPS for participant selection in VFL, as a pre-training step. We have tested our method on several data sets performing both regression and classification tasks, showing that our method leads to comparable results as using all data by only selecting a few participants. In addition, we show that our method outperforms existing methods for participant selection in VFL.

Multi-Objective Alignment (MOA) aims to align LLMs' responses with multiple human preference objectives, with Direct Preference Optimization (DPO) emerging as a prominent approach. However, we find that DPO-based MOA approaches suffer from widespread preference conflicts in the data, where different objectives favor different responses. This results in conflicting optimization directions, hindering the optimization on the Pareto Front. To address this, we propose to construct Pareto-optimal responses to resolve preference conflicts. To efficiently obtain and utilize such responses, we propose a self-improving DPO framework that enables LLMs to self-generate and select Pareto-optimal responses for self-supervised preference alignment. Extensive experiments on two datasets demonstrate the superior Pareto Front achieved by our framework compared to various baselines. Code is available at \url{https://github.com/zyttt-coder/SIPO}.

A BSTRACT Direct Preference Optimization (DPO) has gained attention as an efficient alternative to reinforcement learning from human feedback (RLHF) for aligning large language models (LLMs) with human preferences. Despite its advantages, DPO suffers from a length bias, generating responses longer than those from the reference model. Existing solutions like SimPO and SamPO address this issue but uniformly treat the contribution of rewards across sequences, overlooking temporal dynamics. To this end, we propose an enhanced preference optimization method that incorporates a temporal decay factor controlled by a gamma parameter. This dynamic weighting mechanism adjusts the influence of each reward based on its position in the sequence, prioritizing earlier tokens that are more critical for alignment. By adaptively focusing on more relevant feedback, our approach mitigates overfitting to less pertinent data and remains responsive to evolving human preferences. Experimental results on several benchmarks show that our approach consistently outperforms vanilla DPO by 5.9-8.8 points on AlpacaEval 2 and 3.3-9.7 points on Arena-Hard across different model architectures and sizes. Furthermore, additional experiments on mathematical and reasoning benchmarks (MMLU, GSM8K, and MA TH) confirm that our method enhances performance without compromising general capabilities. Our codebase would be available at https://github.com/LotuSrc/D2PO . 1 I NTRODUCTION Direct Preference Optimization (DPO) (Rafailov et al., 2023) has recently emerged as a highly efficient alternative for aligning large language models (LLMs) with human preferences (Askell et al., 2021; Ouyang et al., 2022). Unlike reinforcement learning from human feedback (RLHF), which involves training a reward model followed by iterative policy updates, DPO reframes the problem as a binary classification task directly over human preference data. Compared to supervised fine-tuning, DPO enables the model not only to learn what is good but also to be aware of what is bad. This formulation allows DPO to optimize preference alignment in a single-stage training process, bypassing the complexities of reinforcement learning, such as policy sampling or extensive hyperparameter tuning.

Information in text is communicated in a way that supports a goal for its reader. Product reviews, for example, contain opinions, tips, product descriptions, and many other types of information that provide both direct insights, as well as unexpected signals for downstream applications. We devise a typology of 24 communicative goals in sentences from the product review domain, and employ a zero-shot multi-label classifier that facilitates large-scale analyses of review data. In our experiments, we find that the combination of classes in the typology forecasts helpfulness and sentiment of reviews, while supplying explanations for these decisions. In addition, our typology enables analysis of review intent, effectiveness and rhetorical structure. Characterizing the types of information in reviews unlocks many opportunities for more effective consumption of this genre.

Large language models (LLMs) regularly demonstrate new and impressive performance on a wide range of language, knowledge, and reasoning benchmarks. Such rapid progress has led many commentators to argue that LLM general cognitive capabilities have likewise rapidly improved, with the implication that such models are becoming progressively more capable on various real-world tasks. Here I summarise theoretical and empirical considerations to challenge this narrative. I argue that inherent limitations with the benchmarking paradigm, along with specific limitations of existing benchmarks, render benchmark performance highly unsuitable as a metric for generalisable competence over cognitive tasks. I also contend that alternative methods for assessing LLM capabilities, including adversarial stimuli and interpretability techniques, have shown that LLMs do not have robust competence in many language and reasoning tasks, and often fail to learn representations which facilitate generalisable inferences. I conclude that benchmark performance should not be used as a reliable indicator of general LLM cognitive capabilities.

Personalized alignments for individual users have been a long-standing goal in large language models (LLMs). We introduce Drift, a novel framework that personalizes LLMs at decoding time with implicit user preferences. Traditional Reinforcement Learning from Human Feedback (RLHF) requires thousands of annotated examples and expensive gradient updates. In contrast, Drift personalizes LLMs in a training-free manner, using only a few dozen examples to steer a frozen model through efficient preference modeling. Our approach models user preferences as a composition of predefined, interpretable attributes and aligns them at decoding time to enable personalized generation. Experiments on both a synthetic persona dataset (Perspective) and a real human-annotated dataset (PRISM) demonstrate that Drift significantly outperforms RLHF baselines while using only 50-100 examples. Our results and analysis show that Drift is both computationally efficient and interpretable.

Recent advancements in event-based recognition have demonstrated significant promise, yet most existing approaches rely on extensive training, limiting their adaptability for efficient processing of event-driven visual content. Meanwhile, large language models (LLMs) have exhibited remarkable zero-shot capabilities across diverse domains, but their application to event-based visual recognition remains largely unexplored. To bridge this gap, we propose \textbf{LLM-EvGen}, an event representation generator that produces LLM-compatible event representations \textbf{LLM-EvRep}, thereby enhancing the performance of LLMs on event recognition tasks. The generator is trained using a self-supervised framework, aligning the generated representations with semantic consistency and structural fidelity. Comprehensive experiments were conducted on three datasets: N-ImageNet, N-Caltech101, and N-MNIST. The results demonstrate that our method, \textbf{LLM-EvRep}, outperforms the event-to-video method, E2VID, by 15.93\%, 0.82\%, and 50.21\%, respectively, in recognition tasks when evaluated using GPT-4o.

We present Neural Attention Search (NAtS), a framework that automatically evaluates the importance of each token within a sequence and determines if the corresponding token can be dropped after several steps. This approach can efficiently reduce the KV cache sizes required by transformer-based models during inference and thus reduce inference costs. In this paper, we design a search space that contains three token types: (i) Global Tokens will be preserved and queried by all the following tokens. (ii) Local Tokens survive until the next global token appears. (iii) Sliding Window Tokens have an impact on the inference of a fixed size of the next following tokens. Similar to the One-Shot Neural Architecture Search approach, this token-type information can be learned jointly with the architecture weights via a learnable attention mask. Experiments on both training a new transformer from scratch and fine-tuning existing large language models show that NAtS can efficiently reduce the KV cache size required for the models while maintaining the models' performance.

Predicting missing segments in partially observed functions is challenging due to infinite-dimensionality, complex dependence within and across observations, and irregular noise. These challenges are further exacerbated by the existence of two distinct sources of variation in functional data, termed amplitude (variation along the $y$-axis) and phase (variation along the $x$-axis). While registration can disentangle them from complete functional data, the process is more difficult for partial observations. Thus, existing methods for functional data prediction often ignore phase variation. Furthermore, they rely on strong parametric assumptions, and require either precise model specifications or computationally intensive techniques, such as bootstrapping, to construct prediction intervals. To tackle this problem, we propose a unified registration and prediction approach for partially observed functions under the conformal prediction framework, which separately focuses on the amplitude and phase components. By leveraging split conformal methods, our approach integrates registration and prediction while ensuring exchangeability through carefully constructed predictor-response pairs. Using a neighborhood smoothing algorithm, the framework produces pointwise prediction bands with finite-sample marginal coverage guarantees under weak assumptions. The method is easy to implement, computationally efficient, and suitable for parallelization. Numerical studies and real-world data examples clearly demonstrate the effectiveness and practical utility of the proposed approach.

Adversarial robustness of machine learning models is critical to ensuring reliable performance under data perturbations. Recent progress has been on point estimators, and this paper considers distributional predictors. First, using the link between exponential families and Bregman divergences, we formulate an adversarial Bregman divergence loss as an adversarial negative log-likelihood. Using the geometric properties of Bregman divergences, we compute the adversarial perturbation for such models in closed-form. Second, under such losses, we introduce \emph{adversarially robust posteriors}, by exploiting the optimization-centric view of generalized Bayesian inference. Third, we derive the \emph{first} rigorous generalization certificates in the context of an adversarial extension of Bayesian linear regression by leveraging the PAC-Bayesian framework. Finally, experiments on real and synthetic datasets demonstrate the superior robustness of the derived adversarially robust posterior over Bayes posterior, and also validate our theoretical guarantees.