Negative / Null Result ReportOpen accessComputer Science
Can Cui, Imran Ahamad Sheikh, Mostafa Sadeghi et al. · 2024 · arXiv
Distant-microphone meeting transcription is a challenging task. State-of-the-art end-to-end speaker-attributed automatic speech recognition (SA-ASR) architectures lack a multichannel noise and reverberation reduction front-end, which limits their performance. In this paper, we introduce a joint beamforming and SA-ASR approach for real meeting transcription. We first describe a data alignment and augmentation method to pretrain a neural beamformer on real meeting data. We then compare fixed, hybrid, and fully neural beamformers as front-ends to the SA-ASR model. Finally, we jointly optimize the
Negative / Null Result ReportOpen accessComputer Science
Zelu Deng, Yujie Zhong, Sheng Guo et al. · 2021 · arXiv
This work aims at improving instance retrieval with self-supervision. We find that fine-tuning using the recently developed self-supervised (SSL) learning methods, such as SimCLR and MoCo, fails to improve the performance of instance retrieval. In this work, we identify that the learnt representations for instance retrieval should be invariant to large variations in viewpoint and background etc., whereas self-augmented positives applied by the current SSL methods can not provide strong enough signals for learning robust instance-level representations. To overcome this problem, we propose InsCL
Negative / Null Result ReportOpen accessComputer Science
Shayne Longpre, Yi Lu, Christopher DuBois · 2020 · arXiv
Recent work (Feng et al., 2018) establishes the presence of short, uninterpretable input fragments that yield high confidence and accuracy in neural models. We refer to these as Minimal Prediction Preserving Inputs (MPPIs). In the context of question answering, we investigate competing hypotheses for the existence of MPPIs, including poor posterior calibration of neural models, lack of pretraining, and "dataset bias" (where a model learns to attend to spurious, non-generalizable cues in the training data). We discover a perplexing invariance of MPPIs to random training seed, model architecture
Negative / Null Result ReportOpen accessMathematics
Oliver J. Hines, Christian L. Hines · 2026 · arXiv
Gradient boosted decision trees require a stopping rule to avoid overfitting. The standard rule monitors a validation loss and stops if the loss fails to improve for a fixed patience period. However, the patience parameter has no interpretable scale and validation losses can be noisy or implicitly defined by a user-specified gradient. We propose ScoreStop, a gradient-based early-stopping rule that casts the stopping decision at each iteration as a test of the null hypothesis that the current predictor is the population risk minimizer. We use a functional score test, computed on validation data
Negative / Null Result ReportOpen accessComputer Science
Hanbing Liu, Haoyang Li, Xiaokang Zhang et al. · 2025 · arXiv
Direct Preference Optimization (DPO) has proven effective in complex reasoning tasks like math word problems and code generation. However, when applied to Text-to-SQL datasets, it often fails to improve performance and can even degrade it. Our investigation reveals the root cause: unlike math and code tasks, which naturally integrate Chain-of-Thought (CoT) reasoning with DPO, Text-to-SQL datasets typically include only final answers (gold SQL queries) without detailed CoT solutions. By augmenting Text-to-SQL datasets with synthetic CoT solutions, we achieve, for the first time, consistent and
Negative / Null Result ReportOpen accessComputer Science
Àlex Miranda-Pascual, Javier Parra-Arnau, Thorsten Strufe · 2026 · arXiv
Sampling is renowned for its privacy amplification in differential privacy (DP), and is often assumed to improve the utility of a DP mechanism by allowing a noise reduction. In this paper, we further show that this last assumption is flawed: When measuring utility at equal privacy levels, sampling as preprocessing consistently yields penalties due to utility loss from omitting records over all canonical DP mechanisms -- Laplace, Gaussian, exponential, and report noisy max -- , as well as recent applications of sampling, such as clustering. Extending this analysis, we investigate suppression as
Negative / Null Result ReportOpen accessEngineering
Haoyang Li, Yuchen Hu, Chen Chen et al. · 2024 · arXiv
Deep neural network (DNN)-based speech enhancement (SE) usually uses conventional activation functions, which lack the expressiveness to capture complex multiscale structures needed for high-fidelity SE. Group-Rational KAN (GR-KAN), a variant of Kolmogorov-Arnold Networks (KAN), retains KAN's expressiveness while improving scalability on complex tasks. We adapt GR-KAN to existing DNN-based SE by replacing dense layers with GR-KAN layers in the time-frequency (T-F) domain MP-SENet and adapting GR-KAN's activations into the 1D CNN layers in the time-domain Demucs. Results on Voicebank-DEMAND sho
Negative / Null Result ReportMedicine
Duman Aydin, Küçükosman, Mohamed et al. · 2026 · BMC medical education
Although oxygen therapy (OT) is a fundamental and life-saving intervention in the management of hypoxemia, it may lead to serious complications when applied incorrectly or in an uncontrolled manner. The aim of this study is to evaluate the…
View details →DOI: 10.1186/s12909-026-09766-8 Negative / Null Result ReportOpen accessComputer Science
Guowei Liu, Hongming Li, Yaning Guo et al. · 2026 · arXiv
Deploying large-scale MoE models presents challenges in memory capacity and bandwidth for expert activation. While Attention-FFN Disaggregation (AFD) has emerged as a potential architecture to decouple compute and memory resources, its performance boundaries compared to standard large-scale Expert Parallelism (EP) remain underexplored. In this paper, we conduct a systematic analysis of AFD by extending the roofline model to the communication level, correlating interconnect bandwidth, arithmetic intensity, and Hardware FLOPS Utilization (HFU). Our analysis reveals a dead zone on standard cluste
Negative / Null Result ReportOpen accessComputer Science
Julian Coda-Forno, Zhuokai Zhao, Qiang Zhang et al. · 2025 · arXiv
Should LLM reasoning live in a separate module, or within a single model's forward pass and representational space? We study dual-architecture latent reasoning, where a fluent Base exchanges latent messages with a Coprocessor, and test two hypotheses aimed at improving latent communication over Liu et al. (2024): (H1) increase channel capacity; (H2) learn communication via joint finetuning. Under matched latent-token budgets on GPT-2 and Qwen-3, H2 is consistently strongest while H1 yields modest gains. A unified soft-embedding baseline, a single model with the same forward pass and shared rep
Negative / Null Result ReportOpen accessComputer Science
Sepanta Zeighami, Cyrus Shahabi · 2024 · arXiv
While extremely useful (e.g., for COVID-19 forecasting and policy-making, urban mobility analysis and marketing, and obtaining business insights), location data collected from mobile devices often contain data from a biased population subset, with some communities over or underrepresented in the collected datasets. As a result, aggregate statistics calculated from such datasets (as is done by various companies including Safegraph, Google, and Facebook), while ignoring the bias, leads to an inaccurate representation of population statistics. Such statistics will not only be generally inaccurate
Negative / Null Result ReportOpen accessComputer Science
Dong Xu, Jiantao Wu, Qihua Pan et al. · 2026 · arXiv
Drug-drug interaction (DDI) prediction is central to drug discovery and clinical development, particularly in the context of increasingly prevalent polypharmacy. Although existing computational methods achieve strong performance on standard benchmarks, they often fail to generalize to realistic deployment scenarios, where most candidate drug pairs involve previously unseen drugs and validated interactions are scarce. We demonstrate that proximity in the embedding spaces of prevailing molecule-centric DDI models does not reliably correspond to interaction labels, and that simply scaling up mode
Negative / Null Result ReportOpen accessComputer Science
Romain Cosentino, Sarath Shekkizhar, Adam Earle et al. · 2026 · arXiv
Negotiation requires more than inferring what the other side wants: it requires using that information to make advantageous offers and counteroffers over multiple turns. We study whether large language model (LLM) agents do this in a controlled multi-attribute bargaining environment. We find that current LLM agents can model a counterparty's preferences, but do not reliably turn that knowledge into strategic bargaining. When given negotiating partner preference information, agents model it accurately and early in their reasoning traces, yet this does not reliably improve outcomes for the infor
Negative / Null Result ReportOpen accessComputer Science
Mike Zhang, Ali Basirat, Desmond Elliott · 2026 · arXiv
Prior work establishes that controlled contrastiveness between self-generated responses from large language models, set via reward scores, improves downstream preference tuning in English. We extend this method to multiple languages and evaluate two models across a total of 14 high and low-resource languages on a diverse set of tasks. Our central finding is that cross-lingual contrastive preference tuning on self-generations (CroCo) transfers without language-specific preference annotation. A reward model trained on English preferences (atop a multilingual base) produces useful within-language
Negative / Null Result ReportOpen accessComputer Science
Aaron Baier-Reinio, Hans De Sterck · 2020 · arXiv
We use neural ordinary differential equations to formulate a variant of the Transformer that is depth-adaptive in the sense that an input-dependent number of time steps is taken by the ordinary differential equation solver. Our goal in proposing the N-ODE Transformer is to investigate whether its depth-adaptivity may aid in overcoming some specific known theoretical limitations of the Transformer in handling nonlocal effects. Specifically, we consider the simple problem of determining the parity of a binary sequence, for which the standard Transformer has known limitations that can only be ove
Negative / Null Result ReportMedicine
Escoffier, Hedhli, Campos-Juanatey et al. · 2026 · The French journal of urology
Artificial intelligence (AI) is increasingly used in surgery, but its role in reconstructive urology remains insufficiently studied. The aim of this work was to evaluate the theoretical knowledge of several AI platforms and compare their…
View details →DOI: 10.1016/j.fjurol.2026.103150 Negative / Null Result ReportOpen accessEngineering
Jiaqi Wu, Jingyi Yuan, Yang Weng et al. · 2025 · arXiv
Power system voltage regulation is crucial to maintain power quality while integrating intermittent renewable resources in distribution grids. However, the system model on the grid edge is often unknown, making it difficult to model physical equations for optimal control. Therefore, previous work proposes structured data-driven methods like input convex neural networks (ICNN) for "optimal" control without relying on a physical model. While ICNNs offer theoretical guarantees based on restrictive assumptions of non-negative neural network parameters, can one improve the approximation power with
Negative / Null Result ReportOpen accessComputer Science
Xiao Mao · 2023 · arXiv
The All-Pairs Shortest Paths (APSP) problem is one of the fundamental problems in theoretical computer science. It asks to compute the distance matrix of a given $n$-vertex graph. We revisit the classical problem of maintaining the distance matrix under a fully dynamic setting undergoing vertex insertions and deletions with a fast worst-case running time and efficient space usage. Although an algorithm with amortized update-time $\tilde O(n ^ 2)$ has been known for nearly two decades [Demetrescu and Italiano, STOC 2003], the current best algorithm for worst-case running time with efficient spa
Negative / Null Result ReportOpen accessComputer Science
Vageesh Saxena, Sharid Loáiciga, Nils Rethmeier · 2024 · arXiv
Neural networks have demonstrated significant advancements in Neural Machine Translation (NMT) compared to conventional phrase-based approaches. However, Multilingual Neural Machine Translation (MNMT) in extremely low-resource settings remains underexplored. This research investigates how knowledge transfer across languages can enhance MNMT in such scenarios. Using the Tatoeba translation challenge dataset from Helsinki NLP, we perform English-German, English-French, and English-Spanish translations, leveraging minimal parallel data to establish cross-lingual mappings. Unlike conventional meth
Negative / Null Result ReportOpen accessEngineering
Kwon Byung-Ki, Oh Hyun-Bin, Kim Jun-Seong et al. · 2023 · arXiv
Video motion magnification amplifies invisible small motions to be perceptible, which provides humans with a spatially dense and holistic understanding of small motions in the scene of interest. This is based on the premise that magnifying small motions enhances the legibility of motions. In the real world, however, vibrating objects often possess convoluted systems that have complex natural frequencies, modes, and directions. Existing motion magnification often fails to improve legibility since the intricate motions still retain complex characteristics even after being magnified, which may di
Negative / Null Result Report
L. P. Zakharenko, D. V. Petrovskii, R. A. Bykov · 2023 · Молекулярная биология
Cases of horizontal transfer of transposable elements (TEs) between species are known for the Drosophilidae family. In the middle of the last century, the case of horizontal transfer of the P-element from the Drosophila willistoni to the…
View details →DOI: 10.31857/s0026898423020258 Negative / Null Result Report
T. A. Pankratov, R. E. Shcherbatov, A. A. Del’tsov · 2023 · Микробиология
Abstract—Activity of the ethanol extracts from lichens (LE), of the cultures of lichenophilic (endobiotic) fungi (LFE), and of ethanol extracts from these cultures was tested using the following test organisms: Escherichia coli, Salmonella…
View details →DOI: 10.31857/s002636562360027x Negative / Null Result ReportMedicine
Peng, Wang, Xiao et al. · 2026 · Journal of minimally invasive gynecology
To compare the effectiveness and safety of transvaginal natural orifice transluminal endoscopic surgery (vNOTES) pelvic reconstruction (PRC), vNOTES presacral-uterosacral ligament suspension (PULS), and sacrospinous ligament fixation…
View details →DOI: 10.1016/j.jmig.2026.06.024 Negative / Null Result ReportMedicine
Rocha, Dos Anjos, Pinho et al. · 2026 · Journal of dentistry
This 12-month, double-blind, parallel, randomized controlled trial compared the material fracture/retention rates of occluso-proximal direct composite resin restorations associated with polyethylene fiber (CR+PF; Ribbond®) with…
View details →DOI: 10.1016/j.jdent.2026.106863 Negative / Null Result ReportMedicine
Kim, Yang, Kuang et al. · 2026 · Journal of oral and maxillofacial surgery : official journal of the American Association of Oral and Maxillofacial Surgeons
Conventional cephalometry relies on measurements derived from a limited set of landmarks and population-based norms, which may not fully capture individual skeletal form. Although evaluated independently, many cephalometric variables…
View details →DOI: 10.1016/j.joms.2026.06.005 Negative / Null Result ReportMedicine
Olson, Perera, Kamal et al. · 2026 · Journal of clinical neuroscience : official journal of the Neurosurgical Society of Australasia
Quantitative pupillometry (QP) provides a reliable measure of the pupillary light reflex. The pupil accommodation reflex (P-AR) occurs when there is a change in visual focus from near to far or from far to near. The ability to measure the…
View details →DOI: 10.1016/j.jocn.2026.112161 Negative / Null Result ReportMedicine
Jiang, Zhu, Gan et al. · 2026 · European journal of radiology
This study aimed to investigate the effectiveness and safety of endovascular treatment (EVT) in patients with large ischemic strokes assessed by non-contrast CT (NCCT) within the extended time window. This study was a sub-analysis of a…
View details →DOI: 10.1016/j.ejrad.2026.113034 Negative / Null Result ReportMedicine
Zhao, Wang · 2026 · Acta psychologica
Handwashing, as a common physical cleansing behavior, not only serves a physiological cleaning function but is also believed to symbolically "wash away" emotional experiences or mental residues. Previous research has primarily focused on…
View details →DOI: 10.1016/j.actpsy.2026.107323 Negative / Null Result ReportMedicine
Karnati, Wu, Kaghazchi et al. · 2026 · Journal of neurosurgery. Spine
The aim of this study was to evaluate the impact of initial postoperative gabapentinoid prescription on chronic postoperative opioid use in patients who underwent short-segment lumbar instrumentation by using a large multicenter electronic…
View details →DOI: 10.3171/2026.2.spine25802 Negative / Null Result ReportMedicine
Chen, Maddali, Langlotz et al. · 2026 · Journal of medical Internet research
Most clinically relevant data are in unstructured clinical notes, which are verbose and imprecise, making structured data extraction a costly bottleneck for screening patients for studies or maintaining health care registries. This…
View details →DOI: 10.2196/90547 