As large language models (LLMs) are increasingly deployed in enterprise settings, controlling model behavior based on user roles becomes an essential requirement. Existing safety methods typically assume uniform access and focus on preventing harmful or toxic outputs, without addressing role-specific access constraints. In this work, we investigate whether LLMs can be fine-tuned to generate responses that reflect the access privileges associated with different organizational roles. We explore three modeling strategies: a BERT-based classifier, an LLM-based classifier, and role-conditioned generation. To evaluate these approaches, we construct two complementary datasets. The first is adapted from existing instruction-tuning corpora through clustering and role labeling, while the second is synthetically generated to reflect realistic, role-sensitive enterprise scenarios. We assess model performance across varying organizational structures and analyze robustness to prompt injection, role mismatch, and jailbreak attempts.

Modern sequential recommender systems commonly use transformer-based models for next-item prediction. While these models demonstrate a strong balance between efficiency and quality, integrating interleaving features - such as the query context (e.g., browse category) under which next-item interactions occur - poses challenges. Effectively capturing query context is crucial for refining ranking relevance and enhancing user engagement, as it provides valuable signals about user intent within a session. Unlike item features, historical query context is typically not aligned with item sequences and may be unavailable at inference due to privacy constraints or feature store limitations - making its integration into transformers both challenging and error-prone. This paper analyzes different strategies for incorporating query context into transformers trained with a causal language modeling procedure as a case study. We propose a new method that effectively fuses the item sequence with query context within the attention mechanism. Through extensive offline and online experiments on a large-scale online platform and open datasets, we present evidence that our proposed method is an effective approach for integrating query context to improve model ranking quality in terms of relevance and diversity.

As Multimodal Large Language Models (MLLMs) continue to evolve, their cognitive and reasoning capabilities have seen remarkable progress. However, challenges in visual fine-grained perception and commonsense causal inference persist. This paper introduces Argus Inspection, a multimodal benchmark with two levels of difficulty, emphasizing detailed visual recognition while incorporating real-world commonsense understanding to evaluate causal reasoning abilities. Expanding on it, we present the Eye of Panoptes framework, which integrates a binary parametric Sigmoid metric with an indicator function, enabling a more holistic evaluation of MLLMs' responses in opinion-based reasoning tasks. Experiments conducted on 26 mainstream MLLMs reveal that the highest performance in visual fine-grained reasoning reaches only 0.46, highlighting considerable potential for enhancement. Our research offers valuable perspectives for the continued refinement of MLLMs.

Anatomical changes during intensity-modulated proton therapy (IMPT) for head-and-neck cancer (HNC) can shift Bragg peaks, risking tumor underdosing and organ-at-risk overdosing. Treatment replanning is often required to maintain clinically acceptable treatment quality. However, current manual replanning processes are resource-intensive and time-consuming. We propose a patient-specific deep reinforcement learning (DRL) framework for automated IMPT replanning, with a reward-shaping mechanism based on a $150$-point plan quality score addressing competing clinical objectives. We formulate the planning process as a reinforcement learning problem where agents learn control policies to adjust optimization priorities, maximizing plan quality. Unlike population-based approaches, our framework trains agents for each patient using their planning Computed Tomography (CT) and augmented anatomies simulating anatomical changes (tumor progression and regression). This patient-specific approach leverages anatomical similarities along the treatment course, enabling effective plan adaptation. We implemented two DRL algorithms, Deep Q-Network and Proximal Policy Optimization, using dose-volume histograms (DVHs) as state representations and a $22$-dimensional action space of priority adjustments. Evaluation on eight HNC patients using actual replanning CT data showed that both agents improved initial plan scores from $120.78 \pm 17.18$ to $139.59 \pm 5.50$ (DQN) and $141.50 \pm 4.69$ (PPO), surpassing the replans manually generated by a human planner ($136.32 \pm 4.79$). Clinical validation confirms that improvements translate to better tumor coverage and OAR sparing across diverse anatomical changes. This work highlights DRL's potential in addressing geometric and dosimetric complexities of adaptive proton therapy, offering efficient offline adaptation solutions and advancing online adaptive proton therapy.

Harmful fine-tuning (HFT), performed directly on open-source LLMs or through Fine-tuning-as-a-Service, breaks safety alignment and poses significant threats. Existing methods aim to mitigate HFT risks by learning robust representation on alignment data or making harmful data unlearnable, but they treat each data sample equally, leaving data vulnerability patterns understudied. In this work, we reveal that certain subsets of alignment data are consistently more prone to forgetting during HFT across different fine-tuning tasks. Inspired by these findings, we propose Vulnerability-Aware Alignment (VAA), which estimates data vulnerability, partitions data into "vulnerable" and "invulnerable" groups, and encourages balanced learning using a group distributionally robust optimization (Group DRO) framework. Specifically, VAA learns an adversarial sampler that samples examples from the currently underperforming group and then applies group-dependent adversarial perturbations to the data during training, aiming to encourage a balanced learning process across groups. Experiments across four fine-tuning tasks demonstrate that VAA significantly reduces harmful scores while preserving downstream task performance, outperforming state-of-the-art baselines.

Despite recent progress in Language Models (LMs) for software engineering, collecting training data remains a significant pain point. Existing datasets are small, with at most 1,000s of training instances from 11 or fewer GitHub repositories. The procedures to curate such datasets are often complex, necessitating hundreds of hours of human labor; companion execution environments also take up several terabytes of storage, severely limiting their scalability and usability. To address this pain point, we introduce SWE-smith, a novel pipeline for generating software engineering training data at scale. Given any Python codebase, SWE-smith constructs a corresponding execution environment, then automatically synthesizes 100s to 1,000s of task instances that break existing test(s) in the codebase. Using SWE-smith, we create a dataset of 50k instances sourced from 128 GitHub repositories, an order of magnitude larger than all previous works. We train SWE-agent-LM-32B, achieving 40.2% Pass@1 resolve rate on the SWE-bench Verified benchmark, state of the art among open source models. We open source SWE-smith (collection procedure, task instances, trajectories, models) to lower the barrier of entry for research in LM systems for automated software engineering. All assets available at https://swesmith.com.

Climate change increases the frequency of extreme rainfall, placing a significant strain on urban infrastructures, especially Combined Sewer Systems (CSS). Overflows from overburdened CSS release untreated wastewater into surface waters, posing environmental and public health risks. Although traditional physics-based models are effective, they are costly to maintain and difficult to adapt to evolving system dynamics. Machine Learning (ML) approaches offer cost-efficient alternatives with greater adaptability. To systematically assess the potential of ML for modeling urban infrastructure systems, we propose a protocol for evaluating Neural Network architectures for CSS time series forecasting with respect to predictive performance, model complexity, and robustness to perturbations. In addition, we assess model performance on peak events and critical fluctuations, as these are the key regimes for urban wastewater management. To investigate the feasibility of lightweight models suitable for IoT deployment, we compare global models, which have access to all information, with local models, which rely solely on nearby sensor readings. Additionally, to explore the security risks posed by network outages or adversarial attacks on urban infrastructure, we introduce error models that assess the resilience of models. Our results demonstrate that while global models achieve higher predictive performance, local models provide sufficient resilience in decentralized scenarios, ensuring robust modeling of urban infrastructure. Furthermore, models with longer native forecast horizons exhibit greater robustness to data perturbations. These findings contribute to the development of interpretable and reliable ML solutions for sustainable urban wastewater management. The implementation is available in our GitHub repository.

This paper demonstrates the feasibility of democratizing AI-driven global weather forecasting models among university research groups by leveraging Graphics Processing Units (GPUs) and freely available AI models, such as NVIDIA's FourCastNetv2. FourCastNetv2 is an NVIDIA's advanced neural network for weather prediction and is trained on a 73-channel subset of the European Centre for Medium-Range Weather Forecasts (ECMWF) Reanalysis v5 (ERA5) dataset at single levels and different pressure levels. Although the training specifications for FourCastNetv2 are not released to the public, the training documentation of the model's first generation, FourCastNet, is available to all users. The training had 64 A100 GPUs and took 16 hours to complete. Although NVIDIA's models offer significant reductions in both time and cost compared to traditional Numerical Weather Prediction (NWP), reproducing published forecasting results presents ongoing challenges for resource-constrained university research groups with limited GPU availability. We demonstrate both (i) leveraging FourCastNetv2 to create predictions through the designated application programming interface (API) and (ii) utilizing NVIDIA hardware to train the original FourCastNet model. Further, this paper demonstrates the capabilities and limitations of NVIDIA A100's for resource-limited research groups in universities. We also explore data management, training efficiency, and model validation, highlighting the advantages and challenges of using limited high-performance computing resources. Consequently, this paper and its corresponding GitHub materials may serve as an initial guide for other university research groups and courses related to machine learning, climate science, and data science to develop research and education programs on AI weather forecasting, and hence help democratize the AI NWP in the digital economy.

Large language model (LLM) agents are increasingly employing retrieval-augmented generation (RAG) to improve the factuality of their responses. However, in practice, these systems often need to handle ambiguous user queries and potentially conflicting information from multiple sources while also suppressing inaccurate information from noisy or irrelevant documents. Prior work has generally studied and addressed these challenges in isolation, considering only one aspect at a time, such as handling ambiguity or robustness to noise and misinformation. We instead consider multiple factors simultaneously, proposing (i) RAMDocs (Retrieval with Ambiguity and Misinformation in Documents), a new dataset that simulates complex and realistic scenarios for conflicting evidence for a user query, including ambiguity, misinformation, and noise; and (ii) MADAM-RAG, a multi-agent approach in which LLM agents debate over the merits of an answer over multiple rounds, allowing an aggregator to collate responses corresponding to disambiguated entities while discarding misinformation and noise, thereby handling diverse sources of conflict jointly. We demonstrate the effectiveness of MADAM-RAG using both closed and open-source models on AmbigDocs -- which requires presenting all valid answers for ambiguous queries -- improving over strong RAG baselines by up to 11.40% and on FaithEval -- which requires suppressing misinformation -- where we improve by up to 15.80% (absolute) with Llama3.3-70B-Instruct. Furthermore, we find that RAMDocs poses a challenge for existing RAG baselines (Llama3.3-70B-Instruct only obtains 32.60 exact match score). While MADAM-RAG begins to address these conflicting factors, our analysis indicates that a substantial gap remains especially when increasing the level of imbalance in supporting evidence and misinformation.

This paper presents SPIE: a novel approach for semantic and structural post-training of instruction-based image editing diffusion models, addressing key challenges in alignment with user prompts and consistency with input images. W e introduce an online reinforcement learning framework that aligns the diffusion model with human preferences without relying on extensive human annotations or curat-ing a large dataset. Our method significantly improves the alignment with instructions and realism in two ways. First, SPIE captures fine nuances in the desired edit by leveraging a visual prompt, enabling detailed control over visual edits without lengthy textual prompts. Second, it achieves precise and structurally coherent modifications in complex scenes while maintaining high fidelity in instruction-irrelevant areas. This approach simplifies users' efforts to achieve highly specific edits, requiring only 5 reference images depicting a certain concept for training. Experimental results demonstrate that SPIE can perform intricate edits in complex scenes, after just 10 training steps. Finally, we showcase the versatility of our method by applying it to robotics, where targeted image edits enhance the visual realism of simulated environments, which improves their utility as proxy for real-world settings.