Large language models offer opportunities to simulate multi-party deliberation, but realistic modeling remains limited by a lack of speaker-attributed data. Transcripts produced via automatic speech recognition (ASR) assign anonymous speaker labels (e.g., Speaker_1), preventing models from capturing consistent human behavior. This work introduces a reproducible pipeline to transform public Zoom recordings into speaker-attributed transcripts with metadata like persona profiles and pragmatic action tags (e.g., [propose_motion]). We release three local government deliberation datasets: Appellate Court hearings, School Board meetings, and Municipal Council sessions. Fine-tuning LLMs to model specific participants using this "action-aware" data produces a 67% reduction in perplexity and nearly doubles classifier-based performance metrics for speaker fidelity and realism. Turing-style human evaluations show our simulations are often indistinguishable from real deliberations, providing a practical and scalable method for complex realistic civic simulations.

Large language models require significant computational resources for deployment, making quantization essential for practical applications. However, the main obstacle to effective quantization lies in systematic outliers in activations and weights, which cause substantial LLM performance degradation, especially at low-bit settings. While existing transformation-based methods like affine and rotation transformations successfully mitigate outliers, they apply the homogeneous transformation setting, i.e., using the same transformation types across all layers, ignoring the heterogeneous distribution characteristics within LLMs. In this paper, we propose an adaptive transformation selection framework that systematically determines optimal transformations on a per-layer basis. To this end, we first formulate transformation selection as a differentiable optimization problem to achieve the accurate transformation type for each layer. However, searching for optimal layer-wise transformations for every model is computationally expensive. To this end, we establish the connection between weight distribution kurtosis and accurate transformation type. Specifically, we propose an outlier-guided layer selection method using robust $z$-score normalization that achieves comparable performance to differentiable search with significantly reduced overhead. Comprehensive experiments on LLaMA family models demonstrate that our adaptive approach consistently outperforms the widely-used fixed transformation settings. For example, our method achieves an improvement of up to 4.58 perplexity points and a 2.11% gain in average six-task zero-shot accuracy under aggressive W3A3K2V2 quantization settings for the LLaMA-3-8B model compared to the current best existing method, FlatQuant, demonstrating the necessity of heterogeneous transformation selection for optimal LLM quantization.

Radiology plays an integral role in modern medicine, yet rising imaging volumes have far outpaced workforce growth. Foundation models offer a path toward assisting with the full spectrum of radiology tasks, but existing medical models remain limited: they process volumetric CT and MRI as low-fidelity 2D slices, discard critical grayscale contrast information, and lack evaluation frameworks that reflect real clinical practice. We introduce Pillar-0, a radiology foundation model pretrained on 42,990 abdomen-pelvis CTs, 86,411 chest CTs, 14,348 head CTs, and 11,543 breast MRIs from a large academic center, together with RATE, a scalable framework that extracts structured labels for 366 radiologic findings with near-perfect accuracy using LLMs. Across internal test sets of 14,230 abdomen-pelvis CTs, 10,646 chest CTs, 4,906 head CTs, and 1,585 breast MRIs, Pillar-0 establishes a new performance frontier, achieving mean AUROCs of 86.4, 88.0, 90.1, and 82.9, outperforming MedGemma (Google), MedImageInsight (Microsoft), Lingshu (Alibaba), and Merlin (Stanford) by 7.8-15.8 AUROC points and ranking best in 87.2\% (319/366) tasks. Pillar-0 similarly outperforms all baselines in an external validation on the Stanford Abdominal CT dataset, including Merlin (82.2 vs 80.6 AUROC). Pillar-0 extends to tasks beyond its pretraining, such as long-horizon lung cancer risk prediction, where it improves upon the state-of-the-art Sybil by 3.0 C-index points on NLST, and generalizes with gains of 5.9 (MGH) and 1.9 (CGMH). In brain hemorrhage detection, Pillar-0 obtained a >95 AUROC when using only 1/20th of the data of the next most sample efficient baseline. Pillar-0 and RATE together provide an open, clinically rigorous foundation for building high-performance radiology systems, enabling applications that were previously infeasible due to computational, data, and evaluation constraints.

Large language models (LLMs) have significantly advanced natural language processing, but their massive parameter counts create substantial computational and memory challenges during deployment. Post-training quantization (PTQ) has emerged as a promising approach to mitigate these challenges with minimal overhead. While existing PTQ methods can effectively quantize LLMs, they experience substantial accuracy loss at extremely low bit-widths, primarily due to high-impact parameters that significantly influence quantization performance. Several approaches address these issues by identifying and retaining the high-impact parameters in FP16 format. However, they apply fixed ratios of high-impact parameters across all layers, overlooking layer-wise sensitivity variations. In this paper, we propose a quadratic optimization framework that determines layer-specific ratios of high-impact parameters while considering inter-layer dependencies. We quantize high-impact parameters to moderate bit-widths, which often result in negligible performance degradation in quantized LLMs, while the remaining parameters can be quantized to extremely low bit-widths. Under the same resource-constrained budget, this allows for preserving more high-impact parameters than methods that keep selecting a few in FP16 format. Additionally, the proposed framework allows us to leverage an advanced quantization method that often requires extensive learnable parameters solely for high-impact parameters, while applying a computationally efficient method to the rest. Our approach achieves an effective balance between computational efficiency and model accuracy while maintaining high performance compared to state-of-the-art methods.

While recent world models generate highly realistic videos, their ability to perform robot path planning remains unclear and unquantified. We introduce Target-Bench, the first benchmark specifically designed to evaluate world models on mapless path planning toward semantic targets in real-world environments. Target-Bench provides 450 robot-collected video sequences spanning 45 semantic categories with SLAM-based ground truth trajectories. Our evaluation pipeline recovers camera motion from generated videos and measures planning performance using five complementary metrics that quantify target-reaching capability, trajectory accuracy, and directional consistency. We evaluate state-of-the-art models including Sora 2, Veo 3.1, and the Wan series. The best off-the-shelf model (Wan2.2-Flash) achieves only 0.299 overall score, revealing significant limitations in current world models for robotic planning tasks. We show that fine-tuning an open-source 5B-parameter model on only 325 scenarios from our dataset achieves 0.345 overall score -- an improvement of more than 400% over its base version (0.066) and 15% higher than the best off-the-shelf model. We will open-source the code and dataset.

We present PrismSSL, a Python library that unifies state-of-the-art self-supervised learning (SSL) methods across audio, vision, graphs, and cross-modal settings in a single, modular codebase. The goal of the demo is to show how researchers and practitioners can: (i) install, configure, and run pretext training with a few lines of code; (ii) reproduce compact benchmarks; and (iii) extend the framework with new modalities or methods through clean trainer and dataset abstractions. PrismSSL is packaged on PyPI, released under the MIT license, integrates tightly with HuggingFace Transformers, and provides quality-of-life features such as distributed training in PyTorch, Optuna-based hyperparameter search, LoRA fine-tuning for Transformer backbones, animated embedding visualizations for sanity checks, Weights & Biases logging, and colorful, structured terminal logs for improved usability and clarity. In addition, PrismSSL offers a graphical dashboard - built with Flask and standard web technologies - that enables users to configure and launch training pipelines with minimal coding. The artifact (code and data recipes) will be publicly available and reproducible.

Efficiently and meaningfully estimating prediction uncertainty is important for exploration in active learning campaigns in materials discovery, where samples with high uncertainty are interpreted as containing information missing from the model. In this work, the effect of different uncertainty estimation and calibration methods are evaluated for active learning when using ensembles of ALIGNN, eXtreme Gradient Boost, Random Forest, and Neural Network model architectures. We compare uncertainty estimates from ALIGNN deep ensembles to loss landscape uncertainty estimates obtained for solubility, bandgap, and formation energy prediction tasks. We then evaluate how the quality of the uncertainty estimate impacts an active learning campaign that seeks model generalization to out-of-distribution data. Uncertainty calibration methods were found to variably generalize from in-domain data to out-of-domain data. Furthermore, calibrated uncertainties were generally unsuccessful in reducing the amount of data required by a model to improve during an active learning campaign on out-of-distribution data when compared to random sampling and uncalibrated uncertainties. The impact of poor-quality uncertainty persists for random forest and eXtreme Gradient Boosting models trained on the same data for the same tasks, indicating that this is at least partially intrinsic to the data and not due to model capacity alone. Analysis of the target, in-distribution uncertainty, out-of-distribution uncertainty, and training residual distributions suggest that future work focus on understanding empirical uncertainties in the feature input space for cases where ensemble prediction variances do not accurately capture the missing information required for the model to generalize.

Computational approaches have previously shown various promises and pitfalls when it comes to the reliable identification of media frames. Generative LLMs like GPT and Claude are increasingly being used as content analytical tools, but how effective are they for frame analysis? We address this question by systematically evaluating them against their computational predecessors: bag-of-words models and encoder-only transformers; and traditional manual coding procedures. Our analysis rests on a novel gold standard dataset that we inductively and iteratively developed through the study, investigating six months of news coverage of the US Mpox epidemic of 2022. While we discover some potential applications for generative LLMs, we demonstrate that they were consistently outperformed by manual coders, and in some instances, by smaller language models. Some form of human validation was always necessary to determine appropriate model choice. Additionally, by examining how the suitability of various approaches depended on the nature of different tasks that were part of our frame analytical workflow, we provide insights as to how researchers may leverage the complementarity of these approaches to use them in tandem. We conclude by endorsing a methodologically pluralistic approach and put forth a roadmap for computational frame analysis for researchers going forward.

Chain-of-Thought (CoT) prompting has proven remarkably effective for eliciting complex reasoning in large language models (LLMs). Yet, its potential in multimodal large language models (MLLMs) remains largely untapped, hindered by the absence of large-scale datasets that capture the rich, spatially grounded reasoning intrinsic to visual understanding. Existing visual-CoT resources are typically small, domain-specific, or lack the human-like stepwise structure necessary for compositional visual reasoning. In this paper, we introduce VisReason, a large-scale dataset designed to advance visual Chain-of-Thought reasoning. VisReason comprises 489K annotated examples spanning four diverse domains, each featuring multi-round, human-like rationales that guide MLLMs through interpretable visual reasoning steps. Building upon this, we curate VisReason-Pro, a 165K subset produced with a stronger expert-level GPT annotator, enriched with detailed reasoning traces and 3D spatial grounding via depth-informed annotations. Fine-tuning the state-of-the-art Qwen2.5-VL model on VisReason and VisReason-Pro yields substantial improvements in step-by-step visual reasoning accuracy, interpretability, and cross-benchmark generalization. These results demonstrate that VisReason equips MLLMs with more systematic and generalizable reasoning capabilities. We envision VisReason as a cornerstone for cultivating human-like visual reasoning, paving the way toward the next generation of multimodal intelligence.

Abstract--Transformer-based models have dramatically increased their size and parameter count to tackle increasingly complex tasks. At the same time, there is a growing demand for low-latency inference on resource-constrained devices that achieves high performance. In particular, stream data inference is typically performed over a sliding temporal window, leading to highly redundant computations. The recent Continual Transformers have addressed this issue, but they can only be effectively used in shallow models, which limits their scope and generalization power . In this paper, we propose the Deep Continual Transformer (DeepCoT), a redundancy-free encoder-only model that can be applied over existing deep encoder architectures with minimal changes. In our experiments over audio, video, and text streams, we show that DeepCoTs retain comparative performance to their non-continual baselines while offering a linear computational cost for all Transformer layers, which reduces up to two orders of magnitude in the running time compared to previous efficient models. RANSFORMER models [1] have shown impressive performance for a wide range of classification and regression tasks [2], [3]. However, their size has grown significantly as new complex tasks have been targeted, resulting in slower inference speeds. This problem is especially critical in applications where low-latency models are required, making the use of deep Transformer models unfeasible. Some applications such as robot perception impose limitations in the available hardware to perform predictions, further increasing the latency. Cloud solutions are not always possible due to privacy or practical constraints such as network delay or reliability. Moreover, there is an increasing sense of awareness regarding the high energy consumption required to run large Transformer-based models. One problem following with such characteristics is stream processing. Stream processing can be defined as the set of tasks in which new predictions are made by a model at specific intervals or on-demand, given new data inputs. These models normally benefit from leveraging past information together with the present data and rely on a sliding temporal window formed by the n most recent data points. Zhou, and Q. Zhang are with the Department of Electrical and Computer Engineering, Aarhus University, Denmark. A. Iosifidis is with the Data Science Research Centre, Tampere University, Finland.