AccidentSim is a framework that generates physically realistic vehicle collision videos by extracting physical clues from real-world accident reports. It uses a reliable physical simulator to replicate post-collision trajectories, builds a trajectory dataset, fine‑tunes a language model to predict consistent trajectories from user prompts, and finally renders high‑quality videos with Neural Radiance Fields. The resulting videos show strong visual and physical authenticity compared to existing methods.
By Xiangwen Zhang, Qian Zhang, Longfei Han, Qiang Qu, Xiaoming Chen, Weidong Cai
The paper introduces SPD (Single Forward Pass), a decoding strategy that efficiently produces ranked lists from large language models by emitting only the ordinal positions of items. SPD extracts an item‑position score matrix from the model’s hidden states, then solves a bipartite assignment problem via the Hungarian algorithm to generate a valid permutation in a single forward pass. Experiments show that LoRA‑based fine‑tuning combined with autoregressive ranking distillation achieves 28 ms end‑to‑end inference, a 64× speed‑up while preserving ranking quality.
By Emil Laftchiev, Prachi Agrawal, Moe Kayali, Bixing Yan, Qi Xu, Zijie Lei, Chen Qiu, Zhi Hua, Ke Li, Luke Simon
The paper reports a comprehensive study of transformer-based NLP models for detecting check-worthy social media posts, covering data collection, preprocessing, architecture selection, fine‑tuning, testing, and implementation. It focuses on multilingual models that can process English and low‑resource languages such as Arabic, Bulgarian, Dutch, Polish, Czech, and Slovak, and compares their performance to state‑of‑the‑art baselines. The work introduces multi‑label multilingual classifiers that simultaneously identify harmful content and posts containing verifiable factual claims efficiently.
By Sebastian Kula
The paper explores how to adapt tabular foundation models (TabFMs) for censored time‑to‑event prediction by linking them with CoxPH and DeepHit and revising training procedures. It evaluates zero‑shot, classification‑based fine‑tuning, and survival‑head adaptations across 74 single‑risk and 4 competing‑risk datasets, finding that zero‑shot works best on small datasets while supervised adaptation excels as data grows. The study shows that the choice of adaptation interface and data regime critically influences TabFM transfer performance.
By Minh-Khoi Pham, Luca Cotugno, Dan Cernei, Alina Sirbu, Stefano Masi, Giuseppe Prencipe, Alessandro Pingitore, Patrizia Landi, Working Group on Uric Acid, Cardiovascular Risk of the Italian Society of Hypertension, Tai Tan Mai, Martin Crane, Marija Bezbradica
The paper explores using a language model’s low‑level symbolic skill—specifically SQL—to detect hallucinations without fine‑tuning. By having the model construct an SQL database from reference documents, it can reason over both the source and the model’s output, creating a neurosymbolic check. Experiments on RAGTruth and DiaHalu show this method outperforms direct prediction and rivals state‑of‑the‑art detectors, highlighting the value of leveraging inherent symbolic competences in LLMs.
By Renato Vukovic, Hsien-chin Lin, Carel van Niekerk, Benjamin Ruppik, Michael Heck, Shutong Feng, Nurul Lubis, Milica Gasic
Measured Sliders introduces a framework that defines continuous image controls via closed‑form differentiable measurements, enabling a unified measurement space for training and calibration. An observability test pre‑identifies usable supervision, while a measurement‑guided objective learns target movements and suppresses unwanted changes. The resulting controls, tested on SDXL and FLUX.1‑dev, are ordered, selective, and composable, achieving high monotonicity and selectivity across multiple attributes.
By Yijia Chen, Boyu Wei, Xuanhua Yin
The paper introduces FlexPension-LLM, a domain‑specialized large language model designed to predict pension enrollment among China’s flexible workers. By injecting policy‑grounded cues and using LoRA/SFT for rationale‑augmented supervision, the model achieves a Composite F1 score of 0.9316 on a blind split, outperforming several baselines and matching top commercial models. External survey tests confirm its robustness, with the narrowest performance range among strong systems.
By Yumiao Li, Peixin Liu, Donglin Di, Chen Li, Runhuan Feng
AngelFingerprint introduces a watermarking framework for text-guided image editing that embeds the editing prompt’s CLIP text embedding directly into the diffusion model’s weights via a LoRA module. The watermark is recoverable from image pixels alone, providing an explainable trace of the edit while remaining stealthy even under full white-box access. Experiments on the MagicBrush dataset show the extractor achieves 86% top‑1 accuracy in 200‑way prompt retrieval, outperforming prompt inversion methods.
By Bo-Han Kung, Futa Waseda, Ching-Chun Chang, Isao Echizen, Shang-Tse Chen
The paper investigates how pause tokens affect fine‑tuning dynamics rather than just inference performance. Experiments on synthetic continual‑learning and math‑reasoning tasks show that masked pause tokens (MBP) reduce overwriting of learned modes and compress downstream‑step information. Across 1B‑8B Qwen and Llama models, MBP consistently improves reasoning scores while preserving language understanding, and the approach also benefits GRPO.
By Jaehyeon Kim, Suhwan Kim, Nakyung Lee, Yeongoon Kim, Jimin Seo, Giho Lee, Jungwoo Lee
EuroAlpaca presents a task‑preserving localisation pipeline that translates English instruction‑tuning data into 50 European languages while maintaining task‑critical constraints. The method uses field‑wise machine translation or reconstructs task‑equivalent target‑language instances, followed by validation of coherence and consistency. Experiments show that EuroAlpaca improves instruction‑following accuracy by 12.9% over a baseline and outperforms direct translation on ROUGE‑L and F‑BERT metrics.
By Aleix Sant, Jordi Luque, Carlos Escolano
SimFuse3D tackles cross‑platform LiDAR unsupervised domain adaptation by addressing box‑point inconsistency through source‑guided target simulation and confidence‑guided multi‑stage localization reweighting. It preserves target placement, repairs pseudo‑objects using labeled source geometry, and reweights predictions based on confidence, all during adaptation without altering the detector architecture. The method outperforms existing adaptation techniques across six cross‑platform transfers and ranks first on nuScenes‑to‑KITTI for both evaluated detectors.
By Yongchun Lin, Xinliang Zhang, Yun Zou, Zhixuan Xiao, Liang Lei, Jianya Guo, Yuqiang Zhai, Xiaofeng Wang, HaiKuo Xu, Haoang Li
The article "Dynamical System Transfer Learning with Reduced Order Models" discusses how to enhance reinforcement learning for complex physics problems by employing reduced order models. It explores the application of transfer learning techniques to dynamical systems, aiming to improve the efficiency and effectiveness of reinforcement learning algorithms in physics-based simulations.
By Robert Etter
Measured Sliders introduces a framework that defines continuous image controls via closed‑form differentiable image measurements, enabling predictable and comparable slider behavior. An observability test pre‑filters usable supervision, while a measurement‑guided objective learns target movements and suppresses unwanted changes during training. After training, decoded calibration expresses controls in consistent units, and multiple LoRA branches can be composed without joint training, achieving high selectivity and composability across SDXL and FLUX.1‑dev models.
SVG-Score introduces a human‑aligned evaluation framework for text‑to‑SVG generation, addressing the shortcomings of existing image‑based metrics like CLIPScore that poorly capture SVG‑specific errors such as color, count, and spatial inaccuracies. The authors first demonstrate that CLIP‑based scores are largely insensitive to these errors and that generic Vision‑Language Models respond inconsistently across error types and styles. They then present a human‑annotated Semantic Alignment dataset and develop two complementary evaluators: a CLIP‑based scorer adapted to vector graphics and a VLM judge refined through supervised fine‑tuning and reward‑shaped reinforcement learning, enabling both fast large‑scale and expressive, interpretable assessment of SVG generators.
By Marco Cipriano, Leonardo Zini, Alexandra Schild, Valentin Teutschbein, Afsana Mimi, Marcella Cornia, Lorenzo Baraldi, Gerard de Melo
The paper introduces PromptGFM, a Graph Foundation Model designed for text‑attributed graphs (TAGs). It integrates Large Language Models (LLMs) and Graph Neural Networks (GNNs) through a Graph Understanding Module that prompts LLMs to emulate GNN workflows, and a Graph Inference Module that creates a language‑based graph vocabulary for better alignment and scalability. Experiments show PromptGFM outperforms existing methods and transfers effectively across various graphs and tasks.
By Xi Zhu, Haochen Xue, Ziwei Zhao, Wujiang Xu, Jingyuan Huang, Minghao Guo, Qifan Wang, Kaixiong Zhou, Imran Razzak, Yongfeng Zhang
The paper introduces Distilled Rapid Embedding Transfer (DRET), a parameter‑efficient method that injects biomedical domain knowledge from large specialized models into a smaller general‑purpose model without retraining on the original specialized corpora. DRET evolves through iterative strategies—tokenizer‑merge (DRET 1.x), hybrid embedding averaging (DRET 2.0), priority‑based embedding transfer (DRET 3.x), and further refinements (DRET 4.x)—and demonstrates that a 66‑million‑parameter DistilBERT can achieve competitive or superior performance on token‑level PICO classification compared to much larger models, while remaining lightweight. The authors validate the embedding‑level transfer with cosine similarity, semantic‑shift, and t‑SNE analyses, highlighting DRET’s potential for scalable, resource‑efficient biomedical text mining.
By Girish Sundaram, Daniel Berleant
The 2026 PNPL Competition builds on the 2025 PNPL effort by expanding the LibriBrain dataset to 32 new subjects and more within‑subject data, creating LibriBrain100. It introduces two tracks: a Deep track for high‑performance within‑subject word classification and a Broad track that tests cross‑subject generalisation with progressively less subject‑specific fine‑tuning data, down to 10 minutes. The competition aims to advance non‑invasive brain‑computer interfaces toward practical, clinically feasible communication restoration for people with profound paralysis.
By Francesco Mantegna, Gereon Elvers, Dulhan Jayalath, Gilad Landau, Tasha Kim, Miran \"Ozdogan, Luisa Kurth, Teyun Kwon, SungJun Cho, Benjamin Ballyk, Alex Fung, Anna Greer, Pratik Somaiya, Christian Herff, Yorguin Mantilla Ramos, Hamza Abdelhedi, Karim Jerbi, Greg Farquhar, Brendan Shillingford, Mark Woolrich, Oiwi Parker Jones
The paper presents a graph-transformer AI weather model that is fine‑tuned with high‑resolution IMERG precipitation observations, moving beyond the traditional reliance on the ERA5 reanalysis dataset. This approach yields up to a 19% improvement in medium‑range continuous ranked probability scores and a 57% better Brier skill score for extreme rainfall compared to leading operational models, while also excelling in tropical storm and drizzle prediction. The study demonstrates that directly incorporating observation‑based precipitation data into AI training can markedly enhance forecast accuracy, though physics‑based models still outperform for the heaviest events.
By Julian F. Schmitt, Bertrand Delorme, Robert C. King, Yashica Patodia, Tapio Schneider, Aditi Sheshadri, Ravi Jain
The paper presents a two‑pipeline framework for retinal fundus analysis that combines four‑class disease classification with vessel segmentation. It fine‑tunes eight ImageNet‑pretrained CNNs on the FIVES dataset, applies five gradient‑based explanation methods to assess model interpretability, and benchmarks ten U‑Net variants—including transformer‑based and attention‑enhanced architectures—on the FIVES and DRIVE datasets. The best classification results come from ResNet101 (94.17% accuracy), while the strongest segmentation performance is achieved by Attention U‑Net with a ResNet101V2 backbone, improving DRIVE IoU from 60.80% to 64.83%.
By Fatema Tuj Johora Faria, Mukaffi Bin Moin, Pronay Debnath, Asif Iftekher Fahim, Faisal Muhammad Shah
Para-Pipe is a hierarchical mapping framework that integrates intra- and inter-stage operator parallelism within a pipelined architecture for machine‑learning computational graphs on heterogeneous System‑on‑Chip (SoC) platforms. By selectively fine‑tuning parallelism levels across pipeline stages, it navigates the trade‑off between throughput and latency, reducing inter‑processor communication overhead and improving energy efficiency. Evaluation on Amlogic and Black Sesame SoCs shows multiple Pareto‑optimal configurations, with throughput‑optimized setups achieving up to 11.0% better energy efficiency than purely pipelined strategies and 23.3% better than non‑pipelined parallel execution.
By Yujie Zhang, Huiying Lan, Ehsan Aghapour, Zhiyuan Ning, Peng Zan, Weidong Shao, Anuj Pathania, Tulika Mitra