Negative / Null Result ReportOpen accessComputer Science
Tom Kouwenhoven, Max Peeperkorn, Bram van Dijk et al. · 2024 · arXiv
Natural language has the universal properties of being compositional and grounded in reality. The emergence of linguistic properties is often investigated through simulations of emergent communication in referential games. However, these experiments have yielded mixed results compared to similar experiments addressing linguistic properties of human language. Here we address representational alignment as a potential contributing factor to these results. Specifically, we assess the representational alignment between agent image representations and between agent representations and input images.
View details →Negative / Null Result ReportOpen accessComputer Science
Luigi Giannelli, Ralf Betzholz, Laura Kreiner et al. · 2016 · arXiv
We theoretically analyse the cooling dynamics of a high-Q mode of a mechanical resonator, when the structure is also an optical cavity and is coupled with a NV center. The NV center is driven by a laser and interacts with the cavity photon field and with the strain field of the mechanical oscillator, while radiation pressure couples mechanical resonator and cavity field. Starting from the full master equation we derive the rate equation for the mechanical resonator's motion, whose coefficients depend on the system parameters and on the noise sources. We then determine the cooling regime, the c
View details →Negative / Null Result ReportOpen accessComputer Science
Elias Hossain, Md Mehedi Hasan Nipu, Maleeha Sheikh et al. · 2025 · arXiv
Clinical language models often assign high confidence to incorrect predictions, particularly in high-severity and out-of-distribution cases. We present MedBayes-Lite, a retraining-free uncertainty governance layer for transformer-based clinical predictors. It combines Monte Carlo dropout, predictive calibration, and confidence-guided abstention to defer low-confidence predictions for human review, adding no trainable parameters. Evaluated on MedMCQA and MedQA-USMLE, MedBayes-Lite reduces expected calibration error by 0.23 to 0.33 and drives harmful overconfident errors (confident, incorrect, h
View details →Negative / Null Result ReportOpen accessComputer Science
Lei Wang · 2026 · arXiv
The endpoint region $ζ\to1$ of the NLO forward jet vertex has not been systematically separated from BFKL energy-scale terms in Mueller-Navelet phenomenology. Starting from the small-cone NLO vertex, we isolate the quark and gluon plus distributions and construct a BFKL-aware threshold matching scheme that preserves exact NLO accuracy. The conservative Scheme-II exponent resums only the ordinary endpoint logarithms and leaves the $χ(n,γ)\ln\bar N$ term in the fixed-order coefficient, avoiding an uncontrolled tower of mixed endpoint-BFKL logarithms. In fixed-baseline CMS tests, this matched ver
View details →Negative / Null Result ReportOpen accessComputer Science
Silas L. Fong, Vincent Y. F. Tan · 2017 · arXiv
This paper investigates the asymptotic expansion for the maximum rate of fixed-length codes over a parallel Gaussian channel with feedback under the following setting: A peak power constraint is imposed on every transmitted codeword, and the average error probability of decoding the transmitted message is non-vanishing as the blocklength increases. It is well known that the presence of feedback does not increase the first-order asymptotics of the channel, i.e., capacity, in the asymptotic expansion, and the closed-form expression of the capacity can be obtained by the well-known water-filling
View details →Negative / Null Result ReportOpen accessComputer Science
Ryosuke Kohita, Seiichiro Yoshioka · 2026 · arXiv
Memes are a popular element of modern web communication, used not only as static artifacts but also as interactive replies within conversations. While computational research has focused on analyzing the intrinsic properties of memes, the dynamic and contextual use of memes to create humor remains an understudied area of web science. To address this gap, we introduce the Meme Reply Selection task and present MaMe-Re (Manga Meme Reply Benchmark), a benchmark of 100,000 human-annotated pairs (500,000 total annotations from 2,325 unique annotators) consisting of openly licensed Japanese manga pane
View details →Negative / Null Result ReportOpen accessComputer Science
Evgeniia Razumovskaia, Ivan Vulić, Anna Korhonen · 2024 · arXiv
Supervised fine-tuning (SFT), supervised instruction tuning (SIT) and in-context learning (ICL) are three alternative, de facto standard approaches to few-shot learning. ICL has gained popularity recently with the advent of LLMs due to its simplicity and sample efficiency. Prior research has conducted only limited investigation into how these approaches work for multilingual few-shot learning, and the focus so far has been mostly on their performance. In this work, we present an extensive and systematic comparison of the three approaches, testing them on 6 high- and low-resource languages, thr
View details →Negative / Null Result ReportOpen accessComputer Science
Zijie Zhao, Roy E. Welsch · 2026 · arXiv
Financial retrieval-augmented generation (RAG) systems typically rank evidence by textual relevance, but in financial markets evidence utility depends on event type, forecast horizon, and market context. We study news-triggered event-impact prediction as a point-in-time financial RAG problem. For each company-news anchor, the system retrieves financial news and SEC filing passages, appends a pre-decision market-context card, and predicts multi-horizon residual-return signals. Our method keeps the LLM frozen and adapts retrieval through an external Bayesian source memory updated from matured re
View details →Negative / Null Result ReportOpen accessComputer Science
Baha Eddine Youcef Belmekki, Abdelkrim Hamza, Benoît Escrig · 2018 · arXiv
Vehicular safety communications (VSCs) are known to provide relevant contributions to avoid congestions and prevent road accidents, and more particularly at road intersections since these areas are more prone to accidents. In this context, one of the main impairments that affect the performance of VSCs are interference. In this paper, we develop a tractable framework to model cooperative transmissions in presence of interference for VSCs at intersections. We use tools from stochastic geometry, and model interferer vehicles locations as a Poisson point process. First, we calculate the outage pr
View details →Negative / Null Result ReportOpen accessComputer Science
Jennifer Haase, Jana Gonnermann-Müller, See Heng Yim et al. · 2026 · arXiv
Large language model (LLM)-based simulations of clinical patients are increasingly used for research and training, yet their validity requires persona stability: coherent maintenance of an assigned psychological profile across and within conversations. We evaluate this prerequisite using eating disorder personas grounded in five published case vignettes, a dual-assessment framework (self-report + independent observer ratings), and validated psychometric instruments (EDE-Q) with known ground-truth scores. Across six LLMs and two experiments (between-conversation stability (Exp. I) and within-co
View details →Negative / Null Result ReportOpen accessComputer Science
Vitaly Kurin, Maximilian Igl, Tim Rocktäschel et al. · 2020 · arXiv
Multitask Reinforcement Learning is a promising way to obtain models with better performance, generalisation, data efficiency, and robustness. Most existing work is limited to compatible settings, where the state and action space dimensions are the same across tasks. Graph Neural Networks (GNN) are one way to address incompatible environments, because they can process graphs of arbitrary size. They also allow practitioners to inject biases encoded in the structure of the input graph. Existing work in graph-based continuous control uses the physical morphology of the agent to construct the inpu
View details →Negative / Null Result ReportOpen accessComputer Science
Jin Zeng, Yang Liu, Gene Cheung et al. · 2022 · arXiv
A graph convolutional network (GCN) employs a graph filtering kernel tailored for data with irregular structures. However, simply stacking more GCN layers does not improve performance; instead, the output converges to an uninformative low-dimensional subspace, where the convergence rate is characterized by the graph spectrum -- this is the known over-smoothing problem in GCN. In this paper, we propose a sparse graph learning algorithm incorporating a new spectrum prior to compute a graph topology that circumvents over-smoothing while preserving pairwise correlations inherent in data. Specifica
View details →Negative / Null Result ReportOpen accessComputer Science
Wentao Zhao, Dalin Zhou, Xinguo Qiu et al. · 2020 · arXiv
Graph neural networks (GNNs) have been investigated for potential applicability in multiple fields that employ graph data. However, there are no standard training settings to ensure fair comparisons among new methods, including different model architectures and data augmentation techniques. We introduce a standard, reproducible benchmark to which the same training settings can be applied for node classification. For this benchmark, we constructed 9 datasets, including both small- and medium-scale datasets from different fields, and 7 different models. We design a k-fold model assessment strate
View details →Negative / Null Result ReportOpen accessComputer Science
Charles Jin, Melinda Sun, Martin Rinard · 2021 · arXiv
We propose a novel clustering mechanism based on an incompatibility property between subsets of data that emerges during model training. This mechanism partitions the dataset into subsets that generalize only to themselves, i.e., training on one subset does not improve performance on the other subsets. Leveraging the interaction between the dataset and the training process, our clustering mechanism partitions datasets into clusters that are defined by--and therefore meaningful to--the objective of the training process. We apply our clustering mechanism to defend against data poisoning attacks,
View details →Negative / Null Result ReportOpen accessComputer Science
Alexia Jolicoeur-Martineau · 2019 · arXiv
This paper provides a more rigorous look at Relativistic Generative Adversarial Networks (RGANs). We prove that the objective function of the discriminator is a statistical divergence for any concave function $f$ with minimal properties ($f(0)=0$, $f'(0) \neq 0$, $\sup_x f(x)>0$). We also devise a few variants of relativistic $f$-divergences. Wasserstein GAN was originally justified by the idea that the Wasserstein distance (WD) is most sensible because it is weak (i.e., it induces a weak topology). We show that the WD is weaker than $f$-divergences which are weaker than relativistic $f$-diver
View details →Negative / Null Result ReportOpen accessComputer Science
Zachary Baker, Yuxiao Li · 2025 · arXiv
Sparse Autoencoders (SAEs) have emerged as a promising approach for interpreting neural network representations by learning sparse, human-interpretable features from dense activations. We investigate whether incorporating variational methods into SAE architectures can improve feature organization and interpretability. We introduce the Variational Sparse Autoencoder (vSAE), which replaces deterministic ReLU gating with stochastic sampling from learned Gaussian posteriors and incorporates KL divergence regularization toward a standard normal prior. Our hypothesis is that this probabilistic sampl
View details →Negative / Null Result ReportOpen accessComputer Science
Ali Subhan, Ashir Raza · 2026 · arXiv
DragDiffusion is a diffusion-based method for interactive point-based image editing that enables users to manipulate images by directly dragging selected points. The method claims that accurate spatial control can be achieved by optimizing a single diffusion latent at an intermediate timestep, together with identity-preserving fine-tuning and spatial regularization. This work presents a reproducibility study of DragDiffusion using the authors' released implementation and the DragBench benchmark. We reproduce the main ablation studies on diffusion timestep selection, LoRA-based fine-tuning, mas
View details →Negative / Null Result ReportOpen accessComputer Science
Paul Röttger, Janet B. Pierrehumbert · 2021 · arXiv
Language use differs between domains and even within a domain, language use changes over time. For pre-trained language models like BERT, domain adaptation through continued pre-training has been shown to improve performance on in-domain downstream tasks. In this article, we investigate whether temporal adaptation can bring additional benefits. For this purpose, we introduce a corpus of social media comments sampled over three years. It contains unlabelled data for adaptation and evaluation on an upstream masked language modelling task as well as labelled data for fine-tuning and evaluation on
View details →Negative / Null Result ReportOpen accessComputer Science
Mireille El-Assal, Pierre Tirilly, Ioan Marius Bilasco · 2023 · arXiv
Video analysis is a computer vision task that is useful for many applications like surveillance, human-machine interaction, and autonomous vehicles. Deep Convolutional Neural Networks (CNNs) are currently the state-of-the-art methods for video analysis. However they have high computational costs, and need a large amount of labeled data for training. In this paper, we use Convolutional Spiking Neural Networks (CSNNs) trained with the unsupervised Spike Timing-Dependent Plasticity (STDP) learning rule for action classification. These networks represent the information using asynchronous low-ener
View details →Negative / Null Result ReportOpen accessComputer Science
Óscar García-Sierra, Ana Fernández-Pampillón Cesteros, Miguel Ortega-Martín · 2024 · arXiv
Subword tokenization algorithms used by Large Language Models are significantly more efficient and can independently build the necessary vocabulary of words and subwords without human intervention. However, those subwords do not always align with real morphemes, potentially impacting the models' performance, though it remains uncertain when this might occur. In previous research, we proposed a method to assess the morphological quality of vocabularies, focusing on the overlap between these vocabularies and the morphemes of a given language. Our evaluation method was built on three quality meas
View details →Negative / Null Result ReportOpen accessComputer Science
Bob de Ruiter · 2023 · arXiv
In many fields of experimental science, papers that failed to replicate continue to be cited as a result of the poor discoverability of replication studies. As a first step to creating a system that automatically finds replication studies for a given paper, 334 replication studies and 344 replicated studies were collected. Replication studies could be identified in the dataset based on text content at a higher rate than chance (AUROC = 0.886). Additionally, successful replication studies could be distinguished from failed replication studies at a higher rate than chance (AUROC = 0.664).
View details →Negative / Null Result ReportOpen accessComputer Science
James Kirby, Ioana Krehan, Michele Gubian · 2026 · arXiv
This study examines the extent to which the wav2vec2.0 architecture exhibits evidence of compensation for phonological context. We conducted a pseudo-replication of a perceptional compensation experiment on Mandarin Chinese tones, and compared the embedding similarities and probing classifier outputs between a purely self-supervised pre-trained model and a model fine-tuned for Mandarin ASR. No evidence of compensation was found in the embedding similarities of the purely pre-trained model. Probing classifiers showed some evidence of compensation in addition to the expected layer-wise improveme
View details →Negative / Null Result ReportOpen accessComputer Science
Jaron Maene, Mingxiao Li, Marie-Francine Moens · 2021 · arXiv
The lottery ticket hypothesis states that sparse subnetworks exist in randomly initialized dense networks that can be trained to the same accuracy as the dense network they reside in. However, the subsequent work has failed to replicate this on large-scale models and required rewinding to an early stable state instead of initialization. We show that by using a training method that is stable with respect to linear mode connectivity, large networks can also be entirely rewound to initialization. Our subsequent experiments on common vision tasks give strong credence to the hypothesis in Evci et a
View details →Negative / Null Result ReportOpen accessComputer Science
Robert McCarthy, Daniel C. H. Tan, Dominik Schmidt et al. · 2024 · arXiv
Scaling deep learning to massive and diverse internet data has driven remarkable breakthroughs in domains such as video generation and natural language processing. Robot learning, however, has thus far failed to replicate this success and remains constrained by a scarcity of available data. Learning from videos (LfV) methods aim to address this data bottleneck by augmenting traditional robot data with large-scale internet video. This video data provides foundational information regarding physical dynamics, behaviours, and tasks, and can be highly informative for general-purpose robots. This su
View details →Negative / Null Result ReportOpen accessComputer Science
Jaroslaw Kornowicz · 2024 · arXiv
This study empirically examines the "Evaluative AI" framework, which aims to enhance the decision-making process for AI users by transitioning from a recommendation-based approach to a hypothesis-driven one. Rather than offering direct recommendations, this framework presents users pro and con evidence for hypotheses to support more informed decisions. However, findings from the current behavioral experiment reveal no significant improvement in decision-making performance and limited user engagement with the evidence provided, resulting in cognitive processes similar to those observed in tradi
View details →Negative / Null Result ReportOpen accessComputer Science
Karam Ahmed, Sherif Abuelenin, Heba Soliman et al. · 2015 · arXiv
V-BLAST detection method suffers large computational complexity due to its successive detection of symbols. In this paper, we propose a modified V-BLAST algorithm to decrease the computational complexity by reducing the number of detection iterations required in MIMO communication systems. We begin by showing the existence of a maximum number of iterations, beyond which, no significant improvement is obtained. We establish a criterion for the number of maximum effective iterations. We propose a modified algorithm that uses the measured SNR to dynamically set the number of iterations to achieve
View details →Negative / Null Result ReportOpen accessComputer Science
Alp Atici · 2003 · arXiv
It is an established fact that for many of the interesting problems quantum algorithms based on queries of the standard oracle bring no significant improvement in comparison to known classical algorithms. It is conceivable that there are other oracles of algorithmic importance acting in a less intuitive fashion to which such limitations do not apply. Thus motivated this article suggests a broader understanding towards what a general quantum oracle is. We propose a general definition of a quantum oracle and give a classification of quantum oracles based on the behavior of the eigenvalues and ei
View details →Negative / Null Result ReportOpen accessComputer Science
James Large, Paul Southam, Anthony Bagnall · 2018 · arXiv
tl;dr: no, it cannot, at least not on average on the standard archive problems. We assess whether using six smoothing algorithms (moving average, exponential smoothing, Gaussian filter, Savitzky-Golay filter, Fourier approximation and a recursive median sieve) could be automatically applied to time series classification problems as a preprocessing step to improve the performance of three benchmark classifiers (1-Nearest Neighbour with Euclidean and Dynamic Time Warping distances, and Rotation Forest). We found no significant improvement over unsmoothed data even when we set the smoothing param
View details →Negative / Null Result ReportOpen accessComputer Science
J. Bouchez · 2000 · arXiv
We show that the unified method recently proposed by Feldman and Cousins to put confidence intervals on bounded parameters cannot avoid the possibility of getting null results. A modified bayesian approach is also proposed (although not advocated) which ensures no null results and proper coverage.
View details →Negative / Null Result ReportOpen accessComputer Science
Hoyeon Chang, Jinho Park, Seonghyeon Ye et al. · 2024 · arXiv
Despite the recent observation that large language models (LLMs) can store substantial factual knowledge, there is a limited understanding of the mechanisms of how they acquire factual knowledge through pretraining. This work addresses this gap by studying how LLMs acquire factual knowledge during pretraining. The findings reveal several important insights into the dynamics of factual knowledge acquisition during pretraining. First, counterintuitively, we observe that pretraining on more data shows no significant improvement in the model's capability to acquire and maintain factual knowledge.
View details →