Research on emergency and mass casualty incident (MCI) triage has been limited by the absence of openly usable, reproducible benchmarks. Yet these scenarios demand rapid identification of the patients most in need, where accurate deterioration prediction can guide timely interventions. While the MIMIC-IV-ED database is openly available to credentialed researchers, transforming it into a triage-focused benchmark requires extensive preprocessing, feature harmonization, and schema alignment -- barriers that restrict accessibility to only highly technical users. We address these gaps by first introducing an open, LLM-assisted emergency triage benchmark for deterioration prediction (ICU transfer, in-hospital mortality). The benchmark then defines two regimes: (i) a hospital-rich setting with vitals, labs, notes, chief complaints, and structured observations, and (ii) an MCI-like field simulation limited to vitals, observations, and notes. Large language models (LLMs) contributed directly to dataset construction by (i) harmonizing noisy fields such as AVPU and breathing devices, (ii) prioritizing clinically relevant vitals and labs, and (iii) guiding schema alignment and efficient merging of disparate tables. We further provide baseline models and SHAP-based interpretability analyses, illustrating predictive gaps between regimes and the features most critical for triage. Together, these contributions make triage prediction research more reproducible and accessible -- a step toward dataset democratization in clinical AI.

Recently, we have witnessed great progress in image editing with natural language instructions. Several closed-source models like GPT-Image-1, Seedream, and Google-Nano-Banana have shown highly promising progress. However, the open-source models are still lagging. The main bottleneck is the lack of a reliable reward model to scale up high-quality synthetic training data. To address this critical bottleneck, we built \mname, trained with our new large-scale human preference dataset, meticulously annotated by trained experts following a rigorous protocol containing over 200K preference pairs. \mname demonstrates superior alignment with human preferences in instruction-guided image editing tasks. Experiments show that \mname achieves state-of-the-art human correlation on established benchmarks such as GenAI-Bench, AURORA-Bench, ImagenHub, and our new \benchname, outperforming a wide range of VLM-as-judge models. Furthermore, we use \mname to select a high-quality subset from the existing noisy ShareGPT-4o-Image dataset. We train Step1X-Edit on the selected subset, which shows significant improvement over training on the full set. This demonstrates \mname's ability to serve as a reward model to scale up high-quality training data for image editing. Furthermore, its strong alignment suggests potential for advanced applications like reinforcement learning-based post-training and test-time scaling of image editing models. \mname with its training dataset will be released to help the community build more high-quality image editing training datasets.

Large language models (LLMs) have emerged as effective action policies for sequential decision-making (SDM) tasks due to their extensive prior knowledge. However, this broad yet general knowledge is often insufficient for specific decision-making tasks with limited task-related data, making it challenging to efficiently adapt LLMs to specific SDM tasks. To address this challenge, we propose a memory-driven self-improvement framework that combines LLM general prior knowledge with a compact memory of domain-specific experiences. Memory retains past interactions and associated Q-values, thereby capturing decision-relevant knowledge that facilitates accurate value estimation and informs the LLM prior refinement. The refined LLM prior, in turn, generates higher-reward trajectories that further enrich memory, forming a natural self-improvement framework where memory and LLM prior mutually reinforce each other. Experiments show that our memory-driven approach significantly outperforms both traditional RL and LLM-based baselines, e.g., improving performance by over 40\% on in-distribution tasks and over 75\% when generalized to unseen tasks in ALFWorld.

The Transformer Machine Learning (ML) architecture has been gaining considerable momentum in recent years. In particular, computational High-Energy Physics tasks such as jet tagging and particle track reconstruction (tracking), have either achieved proper solutions, or reached considerable milestones using Transformers. On the other hand, the use of specialised hardware accelerators, especially FPGAs, is an effective method to achieve online, or pseudo-online latencies. The development and integration of Transformer-based ML to FPGAs is still ongoing and the support from current tools is very limited to non-existent. Additionally, FPGA resources present a significant constraint. Considering the model size alone, while smaller models can be deployed directly, larger models are to be partitioned in a meaningful and ideally, automated way . We aim to develop methodologies and tools for monolithic, or partitioned Transformer synthesis, specifically targeting inference. Our primary use-case involves two machine learning model designs for tracking, derived from the TrackFormers project. We elaborate our development approach, present preliminary results, and provide comparisons.

The rapid advancement of LLMs sparked significant interest in their potential to augment or automate managerial functions. One of the most recent trends in AI benchmarking is performance of Large Language Models (LLMs) over longer time horizons. While LLMs excel at tasks involving natural language and pattern recognition, their capabilities in multi-step, strategic business decision-making remain largely unexplored. Few studies demonstrated how results can be different from benchmarks in short-term tasks, as Vending-Bench revealed. Meanwhile, there is a shortage of alternative benchmarks for long-term coherence. This research analyses a novel benchmark using a business game for the decision making in business. The research contributes to the recent literature on AI by proposing a reproducible, open-access management simulator to the research community for LLM benchmarking. This novel framework is used for evaluating the performance of five leading LLMs available in free online interface: Gemini, ChatGPT, Meta AI, Mistral AI, and Grok. LLM makes decisions for a simulated retail company. A dynamic, month-by-month management simulation provides transparently in spreadsheet model as experimental environment. In each of twelve months, the LLMs are provided with a structured prompt containing a full business report from the previous period and are tasked with making key strategic decisions: pricing, order size, marketing budget, hiring, dismissal, loans, training expense, R&D expense, sales forecast, income forecast The methodology is designed to compare the LLMs on quantitative metrics: profit, revenue, and market share, and other KPIs. LLM decisions are analyzed in their strategic coherence, adaptability to market changes, and the rationale provided for their decisions. This approach allows to move beyond simple performance metrics for assessment of the long-term decision-making.

Large audio-language models are advancing rapidly, yet most evaluations emphasize speech or globally sourced sounds, overlooking culturally distinctive cues. This gap raises a critical question: can current models generalize to localized, non-semantic audio that communities instantly recognize but outsiders do not? To address this, we present TAU (Taiwan Audio Understanding), a benchmark of everyday Taiwanese "soundmarks." TAU is built through a pipeline combining curated sources, human editing, and LLM-assisted question generation, producing 702 clips and 1,794 multiple-choice items that cannot be solved by transcripts alone. Experiments show that state-of-the-art LALMs, including Gemini 2.5 and Qwen2-Audio, perform far below local humans. TAU demonstrates the need for localized benchmarks to reveal cultural blind spots, guide more equitable multimodal evaluation, and ensure models serve communities beyond the global mainstream.

Autoregressive (AR) large language models (LLMs) have achieved remarkable performance across a wide range of natural language tasks, yet their inherent sequential decoding limits inference efficiency. In this work, we propose Fast-dLLM v2, a carefully designed block diffusion language model (dLLM) that efficiently adapts pretrained AR models into dLLMs for parallel text generation, requiring only approximately 1B tokens of fine-tuning. This represents a 500x reduction in training data compared to full-attention diffusion LLMs such as Dream (580B tokens), while preserving the original model's performance. Our approach introduces a novel training recipe that combines a block diffusion mechanism with a complementary attention mask, enabling blockwise bidirectional context modeling without sacrificing AR training objectives. To further accelerate decoding, we design a hierarchical caching mechanism: a block-level cache that stores historical context representations across blocks, and a sub-block cache that enables efficient parallel generation within partially decoded blocks. Coupled with our parallel decoding pipeline, Fast-dLLM v2 achieves up to 2.5x speedup over standard AR decoding without compromising generation quality. Extensive experiments across diverse benchmarks demonstrate that Fast-dLLM v2 matches or surpasses AR baselines in accuracy, while delivering state-of-the-art efficiency among dLLMs - marking a significant step toward the practical deployment of fast and accurate LLMs. Code and model will be publicly released.

Supervised fine-tuning (SFT) is the predominant method for adapting large language models (LLMs), yet it often struggles with generalization compared to reinforcement learning (RL). In this work, we posit that this performance disparity stems not just from the loss function, but from a more fundamental difference: SFT learns from a fixed, pre-collected dataset, whereas RL utilizes on-policy data sampled from the current policy. Building on this hypothesis, we introduce one-token rollout (OTR), a novel fine-tuning algorithm that guides SFT with the policy gradient method. At each step, it performs a Monte Carlo "rollout" by sampling multiple candidate tokens from the current policy's distribution. The ground-truth token from the supervised data is then used to provide a reward signal to these samples. Through extensive experiments on a diverse suite of challenging benchmarks spanning mathematical reasoning, code generation, and general domain reasoning, we demonstrate that OTR consistently outperforms standard SFT. Our findings establish OTR as a powerful and practical alternative for fine-tuning LLMs and provide compelling evidence that the on-policy nature of data is a critical driver of generalization, offering a promising new direction for fine-tuning LLMs. Supervised fine-tuning (SFT) has become a cornerstone for adapting large language models (LLMs) to downstream tasks (Ouyang et al., 2022; Chung et al., 2022; Zhang et al., 2025).

The capacity of Large Language Models (LLMs) to follow complex instructions and generate factually accurate text is critical for their real-world application. However, standard decoding methods often fail to robustly satisfy these requirements, while existing control techniques frequently degrade general output quality. In this work, we introduce Attribution-Guided Decoding (AGD), an interpretability-based decoding strategy. Instead of directly manipulating model activations, AGD considers a set of high-probability output token candidates and selects the one that exhibits the highest attribution to a user-defined Region of Interest (ROI). This ROI can be flexibly defined over different parts of the model's input or internal components, allowing AGD to steer generation towards various desirable behaviors. We demonstrate AGD's efficacy across three challenging domains. For instruction following, we show that AGD significantly boosts adherence (e.g., improving the overall success rate on Llama 3.1 from 66.0% to 79.1%). For knowledge-intensive tasks, we show that guiding generation towards usage of internal knowledge components or contextual sources can reduce hallucinations and improve factual accuracy in both closed-book and open-book settings. Furthermore, we propose an adaptive, entropy-based variant of AGD that mitigates quality degradation and reduces computational overhead by applying guidance only when the model is uncertain. Our work presents a versatile, more interpretable, and effective method for enhancing the reliability of modern LLMs. Large Language Models (LLMs) have emerged as powerful tools capable of generating fluent, coherent and contextually relevant text across numerous applications (Brown et al., 2020; Ouyang et al., 2022; Achiam et al., 2023). Despite their success, their reliability is undermined by critical failures, most notably inconsistent adherence to user instructions (Sun et al., 2023; Zhou et al., 2023a; Zeng et al., 2024) and a tendency to generate non-factual, or hallucinated (Wei et al., 2024), information.

Dialogue summarization aims to distill the core meaning of a conversation into a concise text. This is crucial for reducing the complexity and noise inherent in dialogue-heavy applications. While recent approaches typically train language models to mimic human-written summaries, such supervision is costly and often results in outputs that lack task-specific focus limiting their effectiveness in downstream applications, such as medical tasks. In this paper, we propose \app, a framework for task-oriented utility-based dialogue summarization. \app starts by generating multiple summaries and task-oriented question-answer pairs from a dialogue in a zero-shot manner using a pool of large language models (LLMs). The quality of the generated summaries is evaluated by having LLMs answer task-related questions before \textit{(i)} selecting the best candidate answers and \textit{(ii)} identifying the most informative summary based on these answers. Finally, we fine-tune the best LLM on the selected summaries. When validated on multiple datasets, \app demonstrates its effectiveness by achieving competitive results in various zero-shot settings, rivaling fully-supervised State-of-the-Art (SotA) methods.