To further enhance the sampling process towards distribution regions with desirable metric values, we propose a joint preference alignment scheme applicable to both flow matching and Markov bridge frameworks. Furthermore, we extend our model to also explore the conformational landscape of the protein by jointly sampling side chain angles and molecules. Small molecules are the predominant class of FDA-approved drugs with a share of 85%, and more than 95% of known drugs target human or pathogen proteins (Santos et al., 2017). At the same time, the cost and duration of the development of new drugs are skyrocketing (Simoens & Huys, 2021). This sparks increasing interest in the computational design of small molecular compounds that bind specifically to disease-associated proteins and thus reduce the amount of costly experimental testing. In recent years, the machine learning community has contributed a plethora of generative tools addressing drug design from various angles (Du et al., 2024). However, these methods typically require careful tuning of the objective function to avoid exploiting imperfect computational oracles and overly maximizing one desired property (e.g. Additionally, one often aims to design a suitable 3D binding pose along with the chemical structure of the molecule, which substantially increases the degrees of freedom. Many optimization algorithms struggle to efficiently navigate such vast design spaces. Following a different approach, probabilistic generative models learn to generate drug-like molecules directly from data (Hoogeboom et al., 2022; Vignac et al., 2022). Here, the design objectives are implicitly encoded in the training data set. While these methods may not outperform direct optimization on isolated metrics, they are well suited for the multifaceted nature of drug design as they learn "what a drug looks like" in a more general way. Once trained on sufficient high-quality data, these models can capture a more holistic picture of the molecular space compared to models optimized for a limited set of target metrics. The strength of generative modeling lies in its ability to reproduce patterns seen in the training data.

This work elaborates on a High performance computing (HPC) architecture based on Simple Linux Utility for Resource Management (SLURM) [1] for deploying heterogeneous Large Language Models (LLMs) into a scalable inference engine. Dynamic resource scheduling and seamless integration of containerized microservices have been leveraged herein to manage CPU, GPU, and memory allocations efficiently in multi-node clusters. Extensive experiments, using Llama 3.2 (1B and 3B parameters) [2] and Llama 3.1 (8B and 70B) [3], probe throughput, latency, and concurrency and show that small models can handle up to 128 concurrent requests at sub-50 ms latency, while for larger models, saturation happens with as few as two concurrent users, with a latency of more than 2 seconds. This architecture includes Representational State Transfer Application Programming Interfaces (REST APIs) [4] endpoints for single and bulk inferences, as well as advanced workflows such as multi-step "tribunal" refinement. Experimental results confirm minimal overhead from container and scheduling activities and show that the approach scales reliably both for batch and interactive settings. We further illustrate real-world scenarios, including the deployment of chatbots with retrievalaugmented generation, which helps to demonstrate the flexibility and robustness of the architecture. The obtained results pave ways for significantly more efficient, responsive, and fault-tolerant LLM inference on large-scale HPC infrastructures.

Accurate trajectory prediction is vital for autonomous driving, robotics, and intelligent decision-making systems, yet traditional models typically rely on fixed-length output predictions, limiting their adaptability to dynamic real-world scenarios. In this paper, we introduce the FlexiSteps Network (FSN), a novel framework that dynamically adjusts prediction output time steps based on varying contextual conditions. Inspired by recent advancements addressing observation length discrepancies and dynamic feature extraction, FSN incorporates an pre-trained Adaptive Prediction Module (APM) to evaluate and adjust the output steps dynamically, ensuring optimal prediction accuracy and efficiency. To guarantee the plug-and-play of our FSN, we also design a Dynamic Decoder(DD). Additionally, to balance the prediction time steps and prediction accuracy, we design a scoring mechanism, which not only introduces the Fréchet distance to evaluate the geometric similarity between the predicted trajectories and the ground truth trajectories but the length of predicted steps is also considered. Extensive experiments conducted on benchmark datasets including Argoverse and INTERACTION demonstrate the effectiveness and flexibility of our proposed FSN framework.

Anomaly detection is fundamental for ensuring quality control and operational efficiency in industrial environments, yet conventional approaches face significant challenges when training data contains mislabeled samples-a common occurrence in real-world scenarios. This paper presents RAD, a robust anomaly detection framework that integrates Normalizing Flows with Model-Agnostic Meta-Learning to address the critical challenge of label noise in industrial settings. Our approach employs a bi-level optimization strategy where meta-learning enables rapid adaptation to varying noise conditions, while uncertainty quantification guides adaptive L2 regularization to maintain model stability. The framework incorporates multiscale feature processing through pretrained feature extractors and leverages the precise likelihood estimation capabilities of Normalizing Flows for robust anomaly scoring. Comprehensive evaluation on MVTec-AD and KSDD2 datasets demonstrates superior performance, achieving I-AUROC scores of 95.4% and 94.6% respectively under clean conditions, while maintaining robust detection capabilities above 86.8% and 92.1% even when 50% of training samples are mislabeled. The results highlight RAD's exceptional resilience to noisy training conditions and its ability to detect subtle anomalies across diverse industrial scenarios, making it a practical solution for real-world anomaly detection applications where perfect data curation is challenging.

Monitoring is a runtime verification technique that allows one to check whether an ongoing computation of a system (partial trace) satisfies a given formula. It does not need a complete model of the system, but it typically requires the construction of a deterministic automaton doubly exponential in the size of the formula (in the worst case), which limits its practicality. In this paper, we show that, when considering finite, discrete traces, monitoring of pure past (co)safety fragments of Signal Temporal Logic ( STL) can be reduced to trace checking, that is, evaluation of a formula over a trace, that can be performed in time polynomial in the size of the formula and the length of the trace. By exploiting such a result, we develop a GPU-accelerated framework for interpretable early failure detection based on vectorized trace checking, that employs genetic programming to learn temporal properties from historical trace data. The framework shows a 2-10% net improvement in key performance metrics compared to the state-of-the-art methods.

Supervised fine-tuning (SFT) of foundation models often leads to poor generalization, where prior capabilities deteriorate after tuning on new tasks or domains. Inspired by trust-region policy optimization (TRPO) and proximal policy optimization (PPO) in reinforcement learning (RL), we propose Proximal SFT (PSFT), a fine-tuning objective that incorporates the benefits of trust-region, effectively constraining policy drift during SFT while maintaining competitive tuning. By viewing SFT as a special case of policy gradient methods with constant positive advantages, we derive PSFT that stabilizes optimization and leads to generalization, while leaving room for further optimization in subsequent post-training stages . Experiments across mathematical and human-value domains show that PSFT matches SFT in-domain, outperforms it in out-of-domain generalization, remains stable under prolonged training without causing entropy collapse, and provides a stronger foundation for the subsequent optimization. Recently, post-training has become a crucial part of the overall training process. In particular, reinforcement learning (RL) algorithms, such as PPO (Schulman et al., 2017) and GRPO (Shao et al., 2024), have demonstrated significant effectiveness when applied to language models (LMs) focused on reasoning tasks. As RL is scaled over time, foundation models gain the capacity to address complex problems through more profound and extended reasoning (OpenAI, 2024; Guo et al., 2025). These reasoning models offer an abundant and valuable latent thoughts (Ruan et al., 2025) across the internet.

As deep learning models are increasingly deployed on mobile devices, modern mobile devices incorporate deep learning-specific accelerators to handle the growing computational demands, thus increasing their hardware heterogeneity. However, existing works on scheduling deep learning workloads across these processors have significant limitations: most studies focus on single-model scenarios rather than realistic multi-model scenarios, overlook performance variations from different hardware/software configurations, and struggle with accurate execution time estimation. To address these challenges, we propose a novel genetic algorithm-based methodology for scheduling multiple deep learning networks on heterogeneous processors by partitioning the networks into multiple subgraphs. Our approach incorporates three different types of chromosomes for partition/mapping/priority exploration, and leverages device-in-the-loop profiling and evaluation for accurate execution time estimation. Based on this methodology, our system, Puzzle, demonstrates superior performance in extensive evaluations with randomly generated scenarios involving nine state-of-the-art networks. The results demonstrate Puzzle can support 3.7 and 2.2 times higher request frequency on average compared to the two heuristic baselines, NPU Only and Best Mapping, respectively, while satisfying the equivalent level of real-time requirements.

Personalized search ranking systems are critical for driving engagement and revenue in modern e-commerce and short-video platforms. While existing methods excel at estimating users' broad interests based on the filtered historical behaviors, they typically under-exploit explicit alignment between a user's real-time intent (represented by the user query) and their past actions. In this paper, we propose DiffusionGS, a novel and scalable approach powered by generative models. Our key insight is that user queries can serve as explicit intent anchors to facilitate the extraction of users' immediate interests from long-term, noisy historical behaviors. Specifically, we formulate interest extraction as a conditional denoising task, where the user's query guides a conditional diffusion process to produce a robust, user intent-aware representation from their behavioral sequence. We propose the User-aware Denoising Layer (UDL) to incorporate user-specific profiles into the optimization of attention distribution on the user's past actions. By reframing queries as intent priors and leveraging diffusion-based denoising, our method provides a powerful mechanism for capturing dynamic user interest shifts. Extensive offline and online experiments demonstrate the superiority of DiffusionGS over state-of-the-art methods.

Electroencephalography (EEG) foundation models are poised to significantly advance brain signal analysis by learning robust representations from large-scale, unlabeled datasets. However, their rapid proliferation has outpaced the development of standardized evaluation benchmarks, which complicates direct model comparisons and hinders systematic scientific progress. This fragmentation fosters scientific inefficiency and obscures genuine architectural advancements. To address this critical gap, we introduce EEG-FM-Bench, the first comprehensive benchmark for the systematic and standardized evaluation of EEG foundation models (EEG-FMs). Our contributions are threefold: (1) we curate a diverse suite of downstream tasks and datasets from canonical EEG paradigms, implementing standardized processing and evaluation protocols within a unified open-source framework; (2) we benchmark prominent state-of-the-art foundation models to establish comprehensive baseline results for a clear comparison of the current landscape; (3) we perform qualitative analyses of the learned representations to provide insights into model behavior and inform future architectural design. Through extensive experiments, we find that fine-grained spatio-temporal feature interaction, multi-task unified training and neuropsychological priors would contribute to enhancing model performance and generalization capabilities. By offering a unified platform for fair comparison and reproducible research, EEG-FM-Bench seeks to catalyze progress and guide the community toward the development of more robust and generalizable EEG-FMs.

Large Language Models (LLMs) are widely used for downstream tasks such as tabular classification, where ensuring fairness in their outputs is critical for inclusivity, equal representation, and responsible AI deployment. This study introduces a novel approach to enhancing LLM performance and fairness through the concept of a dynamic validation set, which evolves alongside the test set, replacing the traditional static validation approach. We also propose an iterative algorithm, SMITE, to select optimal in-context examples, with each example set validated against its corresponding dynamic validation set. The in-context set with the lowest total error is used as the final demonstration set. Our experiments across four different LLMs show that our proposed techniques significantly improve both predictive accuracy and fairness compared to baseline methods. To our knowledge, this is the first study to apply dynamic validation in the context of in-context learning for LLMs.