Leaderboards, eval harnesses and ablations — the contested business of deciding which model is actually better.
Hierarchical data is ubiquitous in the empirical sciences and is most commonly analyzed with generalized linear mixed-effects models (GLMMs). Bayesian inference for GLMMs yields calibrated uncertainty...
Cross-domain Named Entity Recognition (CD-NER) aims to transfer the rich knowledge in the source domain to the target domain. Recent studies adopting decomposition or generation paradigms have achieve...
Robotic foundation models achieve impressive performance on standard manipulation benchmarks, yet these evaluations typically assume clean, timely, and consistent visual observations throughout execut...
Evaluating world models requires assessing both the quality of the worlds they generate and their consistency and responsiveness under exploration, interaction, and modification. We introduce HappyWor...
Deep Imbalanced Regression (DIR) addresses a common failure mode of regression models: target distributions are highly non-uniform, causing models to perform best in densely populated target regions e...
As Large Language Model (LLM) agents are applied in continuously interactive environments, driving the evolution of their own capabilities becomes a core problem for achieving long-term autonomy. Curr...
Instance segmentation is a fundamental computer vision task with diverse real-world applications. Recently, prompt-driven foundation models have shown promising generalization. However, automated prom...
Visual segmentation systems encounter objects outside their training distribution during real-world deployment, hindering reliable autonomous systems that depend on scene parsing in the perception sta...
Visual search on large e-commerce catalogs must serve both "similarity" queries that ask for items resembling an uploaded image and "modifier" queries that comprise an image and text describing a desi...
Generative models have recently demonstrated considerable promise in speech super-resolution (SSR). Nevertheless, the majority of existing work has concentrated on standard or versatile SSR configurat...
Traditional data systems face profound limitations in the AI era, relying on human-crafted pipelines, lacking semantic understanding of heterogeneous data, and operating through rigid, reactive proces...
Simulation success is not equivalent to structural correctness for LLM-generated circuits. We define and measure four evaluation levels -- schema validity, topological validity, backend executability,...
Questions scraped from the web are used across academia and industry as a proxy for what people want to know. Across QA training data, retrieval benchmarks, and content strategy, questions on a page a...
While deep learning has enabled language decoding from intracranial brain recordings, extending this capability to non-invasive recordings remains an unresolved challenge. Decoding individual words fr...
The paper introduces an uncertainty‑driven training framework for 3D CT lung nodule classification that uses validation‑based uncertainty estimates to reweight the loss, aiming to improve predictive performance and probability calibration. Two uncertainty quantification methods—Monte Carlo Dropout and Evidential Deep Learning—are evaluated across multiple backbone architectures (ResNet, DenseNet, EfficientNet, ViT, Swin) on the LIDC‑IDRI and NoduleMNIST3D datasets. The approach yields comparable classification accuracy to conventional training while substantially reducing expected calibration error, especially on convolutional backbones, and shows that simple temperature scaling can also achieve strong calibration.
CaLR: Causal Latent Revision for Robust Diffusion Reasoning proposes a framework that combines autoregressive and diffusion language models by reformulating reasoning as constrained latent optimization. The method uses a causal topology matrix from an expert model and implicit differentiation to perform gradient-guided thought revision, enforcing logical consistency and allowing dynamic self-correction of intermediate steps during parallel generation. Empirical results show CaLR achieves state‑of‑the‑art performance on complex benchmarks, surpassing strong autoregressive baselines and demonstrating superior robustness in constrained tasks such as Sudoku.
The paper introduces a 12,000-instance dataset of two-option moral dilemmas covering three pairwise value conflicts—Honesty vs. Justice, Justice vs. Autonomy, and Autonomy vs. Honesty—translated into Hindi, Arabic, Spanish, and Chinese to test cross‑lingual behavior. Benchmarking on GPT‑5‑mini shows a consistent preference for Honesty over Autonomy across all languages when no policy is provided, while Llama‑3.2‑1/3B models exhibit a strong first‑option bias that is largely eliminated by plain fine‑tuning or Direct Preference Optimization, raising accuracy above 98%. The authors propose a task vector transfer method that orthogonalizes value preference vectors with respect to general instruction‑following vectors, effectively isolating specific value directions and enabling task arithmetic to flip a model’s stance.
The study investigates ECG biometrics by training a Siamese ResNet with late multi-lead fusion on a large dataset from cardiopulmonary exercise tests. It evaluates the model under realistic conditions, including exercise-induced stress and cross-session variability, achieving an intra-session rest-to-peak EER of 1.7% and a state‑of‑the‑art 3.9% on the CYBHi dataset. The results demonstrate that an intrinsic cardiac signature remains robust to physiological and temporal drift.
Neural Cellular Automata (NCAs) are shown to learn general, scale‑invariant topological primitives in their hidden channels, which can be transferred from a teacher to a student model for few‑shot learning. The study introduces a transfer‑learning mechanism that injects pretrained hidden states into a student, improving early optimization and outperforming recurrent and feed‑forward baselines on MNIST benchmarks with only ~9,800 parameters. Mechanistic analysis reveals that hidden channels decouple feature extraction from classification, converging to mutually orthogonal states that absorb morphological complexity.
The paper introduces a lightweight pre‑encoder gate for Transformer‑based time‑series forecasters, which assigns sigmoid scores to covariate representations before they enter the encoder. The gate is evaluated as a plug‑in for models such as TimeXer, iTransformer, and PatchTST on datasets including ETTm1, ETTm2, Traffic, Energy, and ILI, showing competitive performance and the ability to regulate covariate admission via a usage penalty. Experiments also explore gate placement, initialization, and feature importance using VIF‑informed permutation diagnostics.