Negative / Null Result ReportOpen accessComputer Science
Chen Cai, Yusu Wang · 2020 · arXiv
Graph Neural Networks (GNNs) have achieved a lot of success on graph-structured data. However, it is observed that the performance of graph neural networks does not improve as the number of layers increases. This effect, known as over-smoothing, has been analyzed mostly in linear cases. In this paper, we build upon previous results \cite{oono2019graph} to further analyze the over-smoothing effect in the general graph neural network architecture. We show when the weight matrix satisfies the conditions determined by the spectrum of augmented normalized Laplacian, the Dirichlet energy of embeddin
View details →Negative / Null Result ReportOpen accessComputer Science
Ngoc Minh Lai · 2022 · arXiv
Processing complex and ambiguous named entities is a challenging research problem, but it has not received sufficient attention from the natural language processing community. In this short paper, we present our participation in the English track of SemEval-2022 Task 11: Multilingual Complex Named Entity Recognition. Inspired by the recent advances in pretrained Transformer language models, we propose a simple yet effective Transformer-based baseline for the task. Despite its simplicity, our proposed approach shows competitive results in the leaderboard as we ranked 12 over 30 teams. Our syste
View details →Negative / Null Result ReportOpen accessComputer Science
Christian Mollière, Iker Cumplido, Marco Zeulner et al. · 2025 · arXiv
The rapid growth of data from satellite-based Earth observation (EO) systems poses significant challenges in data transmission and storage. We evaluate the potential of task-specific learned compression algorithms in this context to reduce data volumes while retaining crucial information. In detail, we compare traditional compression (JPEG 2000) versus a learned compression approach (Discretized Mixed Gaussian Likelihood) on three EO segmentation tasks: Fire, cloud, and building detection. Learned compression notably outperforms JPEG 2000 for large-scale, multi-channel optical imagery in both
View details →Negative / Null Result ReportOpen accessMathematics
Gilles Chardon · 2014 · arXiv
The scattering of waves by obstacles in a 2D setting is considered, in particular the computation of the scattered field via the collocation or the least-squares methods. In the case of multiple scattering by smooth obstacles, we prove that the scattered field can be uniformly approximated by sums of multipoles. For a unique obstacle, the choice of the number of points and their positions for the estimation of the error on the border of the scatterer is studied, showing the benefit of using a non-uniform distribution of points dependent on the scatterer and the approximation scheme. In general
View details →Negative / Null Result ReportMedicine
Schauer JM · 2023 · Multivariate behavioral research
A prominent approach to studying the replication crisis has been to conduct replications of several different scientific findings as part of the same research effort. The reported proportion of findings that these programs determined…
View details →Negative / Null Result ReportOpen accessComputer Science
Charles Welch, Rada Mihalcea, Jonathan K. Kummerfeld · 2020 · arXiv
Many NLP applications, such as biomedical data and technical support, have 10-100 million tokens of in-domain data and limited computational resources for learning from it. How should we train a language model in this scenario? Most language modeling research considers either a small dataset with a closed vocabulary (like the standard 1 million token Penn Treebank), or the whole web with byte-pair encoding. We show that for our target setting in English, initialising and freezing input embeddings using in-domain data can improve language model performance by providing a useful representation o
View details →Negative / Null Result ReportOpen accessComputer Science
Dhananjay Srivastava · 2023 · arXiv
Clinical conversation summarization has become an important application of Natural language Processing. In this work, we intend to analyze summarization model ensembling approaches, that can be utilized to improve the overall accuracy of the generated medical report called chart note. The work starts with a single summarization model creating the baseline. Then leads to an ensemble of summarization models trained on a separate section of the chart note. This leads to the final approach of passing the generated results to another summarization model in a multi-layer/stage fashion for better coh
View details →Negative / Null Result ReportOpen accessComputer Science
Roy Abel, Idan Benami, Yoram Louzoun · 2019 · arXiv
In colored graphs, node classes are often associated with either their neighbors class or with information not incorporated in the graph associated with each node. We here propose that node classes are also associated with topological features of the nodes. We use this association to improve Graph machine learning in general and specifically, Graph Convolutional Networks (GCN). First, we show that even in the absence of any external information on nodes, a good accuracy can be obtained on the prediction of the node class using either topological features, or using the neighbors class as an inp
View details →Negative / Null Result ReportOpen accessComputer Science
Guanxu Chen, Dongrui Liu, Jing Shao · 2026 · arXiv
Large Language Models (LLMs) often exhibit a gap between their internal knowledge and their explicit linguistic outputs. In this report, we empirically investigate whether Looped Transformers (LTs)--architectures that increase computational depth by iterating shared layers--can bridge this gap by utilizing their iterative nature as a form of introspection. Our experiments reveal that while increasing loop iterations narrows the gap, it is partly driven by a degradation of their internal knowledge carried by representations. Moreover, another empirical analysis suggests that current LTs' abilit
View details →Negative / Null Result ReportOpen accessMathematics
Nicolas Dupin · 2019 · arXiv
The discrete unit commitment problem with min-stop ramping constraints optimizes the daily production of thermal power plants (coal, gas, fuel units). For this problem, compact Integer Linear Programming (ILP) formulations have been designed to solve exactly small instances and heuristically real-size instances. This paper investigates whether Dantzig-Wolfe reformulation allows to improve the previous exact method and matheuristics. The extended ILP formulation is presented with the column generation algorithm to solve its linear relaxation. The experimental results show that the Dantzig-Wolfe
View details →Negative / Null Result ReportOpen accessComputer Science
Richard A. Formato · 2010 · arXiv
Central Force Optimization is a global search and optimization algorithm that searches a decision space by flying "probes" whose trajectories are deterministically computed using two equations of motion. Because it is possible for a probe to fly outside the domain of feasible solutions, a simple errant probe retrieval method has been used previously that does not include the directional information contained in a probe's acceleration vector. This note investigates the effect of adding directionality to the "repositioning factor" approach. As a general proposition, it appears that doing so does
View details →Negative / Null Result ReportOpen accessComputer Science
Adrian Sauter, Willem Zuidema, Marianne de Heer Kloots · 2025 · arXiv
How does visual information included in training affect language processing in audio- and text-based deep learning models? We explore how such visual grounding affects model-internal representations of words, and find substantially different effects in speech- vs. text-based language encoders. Firstly, global representational comparisons reveal that visual grounding increases alignment between representations of spoken and written language, but this effect seems mainly driven by enhanced encoding of word identity rather than meaning. We then apply targeted clustering analyses to probe for phon
View details →Negative / Null Result ReportOpen accessComputer Science
Ehsan Asadi Kangarshahi, Albert Guillén i Fàbregas · 2020 · arXiv
We derive a single-letter upper bound to the mismatched-decoding capacity for discrete memoryless channels. The bound is expressed as the mutual information of a transformation of the channel, such that a maximum-likelihood decoding error on the translated channel implies a mismatched-decoding error in the original channel. In particular, a strong converse is shown to hold for this upper-bound: if the rate exceeds the upper-bound, the probability of error tends to 1 exponentially when the block-length tends to infinity. We also show that the underlying optimization problem is a convex-concave
View details →Negative / Null Result ReportOpen accessComputer Science
Yongsheng Lian · 2025 · arXiv
This study presents a systematic comparison of three Reinforcement Learning (RL) algorithms (PPO, GRPO, and DAPO) for improving complex reasoning in large language models (LLMs). Our main contribution is a controlled transfer-learning evaluation: models are first fine-tuned on the specialized Countdown Game and then assessed on a suite of general-purpose reasoning benchmarks. Across all tasks, RL-trained models outperform their corresponding base models, although the degree of improvement differs by benchmark. Our parametric analysis offers practical guidance for RL-based LLM training. Increas
View details →Negative / Null Result ReportOpen accessComputer Science
Niladri S. Chatterji, Philip M. Long · 2022 · arXiv
We bound the excess risk of interpolating deep linear networks trained using gradient flow. In a setting previously used to establish risk bounds for the minimum $\ell_2$-norm interpolant, we show that randomly initialized deep linear networks can closely approximate or even match known bounds for the minimum $\ell_2$-norm interpolant. Our analysis also reveals that interpolating deep linear models have exactly the same conditional variance as the minimum $\ell_2$-norm solution. Since the noise affects the excess risk only through the conditional variance, this implies that depth does not impr
View details →Negative / Null Result ReportOpen accessMathematics
Martina Zizza · 2024 · arXiv
In this paper we examine the discrete Shnirelman's inequality [Shnirelman A., 1985], which relates the $L^2$-distance of two discrete configurations of a fluid to the $L^1_tL^2_x$-norm of the vector field connecting them. Our proof is inspired by [Shnirelman A., 1985], where it was obtained $α=\frac{1}{64}$ in dimension $ν=2$, while here we get $α\geq\frac{2}{7}$. Moreover we prove that $α\geq\frac{1}{ν+1}$ for any dimension $ν\geq 3$. We point out that, even if this does not improve the bound in the continuous version, where it was proved that $α\geq\frac{2}{4+ν}$, with $ν\geq 3$, our bound i
View details →Negative / Null Result ReportOpen accessComputer Science
Felix Krejca, Tobias Kietreiber, Alexander Buchelt et al. · 2025 · arXiv
The increasing volume of online discussions requires advanced automatic content moderation to maintain responsible discourse. While hate speech detection on social media is well-studied, research on German-language newspaper forums remains limited. Existing studies often neglect platform-specific context, such as user history and article themes. This paper addresses this gap by developing and evaluating binary classification models for automatic content moderation in German newspaper forums, incorporating contextual information. Using LSTM, CNN, and ChatGPT-3.5 Turbo, and leveraging the One Mi
View details →Negative / Null Result ReportOpen accessComputer Science
Syed Assad, Mark Bradshaw, Ping Koy Lam · 2016 · arXiv
Amplification of quantum states is inevitably accompanied with the introduction of noise at the output. For protocols that are probabilistic with heralded success, noiseless linear amplification in theory may still possible. When the protocol is successful, it can lead to an output that is a noiselessly amplified copy of the input. When the protocol is unsuccessful, the output state is degraded and is usually discarded. Probabilistic protocols may improve the performance of some quantum information protocols, but not for metrology if the whole statistics is taken into consideration. We calcula
View details →Failed Experiment ReportOpen accessComputer Science
Roman Aperdannier, Sigurd Schacht, Alexander Piazza · 2024 · arXiv
Speaker diarization answers the question "who spoke when" for an audio file. In some diarization scenarios, low latency is required for transcription. Speaker diarization with low latency is referred to as online speaker diarization. The DIART pipeline is an online speaker diarization system. It consists of a segmentation and an embedding model. The embedding model has the largest share of the overall latency. The aim of this paper is to optimize the inference latency of the DIART pipeline. Different inference optimization methods such as knowledge distilation, pruning, quantization and layer
View details →Negative / Null Result ReportOpen accessMathematics
Aihua Xia, Fuxi Zhang · 2011 · arXiv
Random events in space and time often exhibit a locally dependent structure. When the events are very rare and dependent structure is not too complicated, various studies in the literature have shown that Poisson and compound Poisson processes can provide adequate approximations. However, the accuracy of approximations does not improve or may even deteriorate when the mean number of events increases. In this paper, we investigate an alternative family of approximating point processes and establish Stein's method for their approximations. We prove two theorems to accommodate respectively the po
View details →Negative / Null Result ReportOpen accessComputer Science
Peratham Wiriyathammabhum · 2023 · arXiv
In this report, we describe our Transformers for euphemism detection baseline (TEDB) submissions to a shared task on euphemism detection 2022. We cast the task of predicting euphemism as text classification. We considered Transformer-based models which are the current state-of-the-art methods for text classification. We explored different training schemes, pretrained models, and model architectures. Our best result of 0.816 F1-score (0.818 precision and 0.814 recall) consists of a euphemism-detection-finetuned TweetEval/TimeLMs-pretrained RoBERTa model as a feature extractor frontend with a Ki
View details →Negative / Null Result ReportOpen accessEngineering
Jingqi Li, Anand Siththaranjan, Somayeh Sojoudi et al. · 2024 · arXiv
Autonomous agents should coordinate effectively without prior knowledge of others' intents. While prior work has focused on intent inference, we address the inverse problem: how agents can strategically demonstrate their intents within general-sum dynamic games. We model this problem and propose an algorithm that balances intent demonstration with task performance. To handle nonlinear dynamic games with continuous state-action spaces, our method leverages iterative linear-quadratic game approximations and provides efficient intent-teaching guarantees: the uncertain agent's belief can be driven
View details →Failed Experiment ReportOpen accessPhysics
Daixi Xia, Hassan Allami, Jacob J. Krich · 2025 · arXiv
We present a Poisson/drift-diffusion model that includes valley scattering effects for simulating valley photovoltaic devices. The valley photovoltaic concept is a novel implementation of a hot-carrier solar cell and leverages the valley scattering effect under large electric field to potentially achieve high voltage and high efficiency. Fabricated devices have shown S-shaped current-voltage curves, low fill factor, and thus low efficiency. We hence develop the first device model for valley photovoltaics. Our model includes electric-field-dependent valley scattering rates extracted from previo
View details →Negative / Null Result ReportOpen accessEngineering
Karl Strecker, Sabit Ekin, John OHara · 2021 · arXiv
A theoretical framework and numerical simulations quantifying the impact of atmospheric group velocity dispersion on wireless terahertz communication link error rate were developed based upon experimental work. We present, for the first time, predictions of symbol error rate as a function of link distance, signal bandwidth, signal-to-noise ratio, and atmospheric conditions, revealing that long-distance, broadband terahertz communication systems may be limited by inter-symbol interference stemming from group velocity dispersion, rather than attenuation. In such dispersion limited links, increas
View details →Negative / Null Result ReportOpen accessComputer Science
Dawar Jyoti Deka, Amit Sethi, Syed Mohammad Ali · 2026 · arXiv
Vision-language models enable open-vocabulary object grounding through natural language queries, under the implicit assumption that semantically equivalent descriptions yield consistent outputs. We examine this assumption using a controlled pipeline combining DETR for object proposals with CLIP for language-conditioned selection on 263 COCO val2017 images. We find that overlapping prompts such as "a person," "a human," and "a pedestrian" frequently select different instances, with mean instability of 2.11 distinct selections across six prompts. PCA analysis shows this variability is structured
View details →Negative / Null Result ReportOpen accessComputer Science
Andrea Gallo Rosso, Francesco Vissani, Maria Cristina Volpe · 2017 · arXiv
We investigate the precision with which a neutron star gravitational binding energy can be measured through the supernova neutrino signal, without assuming any prior such as the energy equipartition hypothesis, mean energies hierarchy or constraints on the pinching parameters that characterize the neutrino spectra. We consider water Cherenkov detectors and prove that combining inverse beta decay with elastic scattering on electrons is sufficient to reach $11\%$ precision on the neutron star gravitational binding energy already with Super-Kamiokande. The inclusion of neutral current events on o
View details →Negative / Null Result ReportOpen accessComputer Science
Matthew Aldridge · 2012 · arXiv
Group testing is the combinatorial problem of identifying the defective items in a population by grouping items into test pools. Recently, nonadaptive group testing - where all the test pools must be decided on at the start - has been studied from an information theory point of view. Using techniques from channel coding, upper and lower bounds have been given on the number of tests required to accurately recover the defective set, even when the test outcomes can be noisy. In this paper, we give the first information theoretic result on adaptive group testing - where the outcome of previous tes
View details →Negative / Null Result ReportOpen accessComputer Science
Yunah Jang, Megha Sundriyal, Kyomin Jung et al. · 2026 · arXiv
Adaptive Retrieval-Augmented Generation (RAG) promises accuracy and efficiency by dynamically triggering retrieval only when needed and is widely used in practice. However, real-world queries vary in surface form even with the same intent, and their impact on Adaptive RAG remains under-explored. We introduce the first large-scale benchmark of diverse yet semantically identical query variations, combining human-written and model-generated rewrites. Our benchmark facilitates a systematic evaluation of Adaptive RAG robustness by examining its key components across three dimensions: answer quality
View details →Negative / Null Result ReportOpen accessComputer Science
Seungwon Baek · 2006 · arXiv
We perform a combined analysis of $B \to ππ$ and $B \to πK$ decays with the current experimental data. Assuming SU(3) flavor symmetry and no new physics contributions to the topological amplitudes, we demonstrate that the conventional parametrization in the Standard Model (SM) does not describe the data very well, in contrast with a similar analysis based on the earlier data. It is also shown that the introduction of smaller amplitudes and reasonable SU(3) breaking parameters does not improve the fits much. Interpreting these puzzling behaviors in the SM as a new physics (NP) signal, we study
View details →Negative / Null Result ReportOpen accessMathematics
Peter Bürgisser · 2022 · arXiv
Consider a system $f_1(x)=0,\ldots,f_n(x)=0$ of $n$ random real polynomials in $n$ variables, where each $f_i$ has a prescribed set of exponent vectors described by a set $A_i \subseteq \mathbb{Z}^n$ of cardinality $t_i$, whose convex hull is denoted $P_i$. Assuming that the coefficients of the $f_i$ are independent standard Gaussian, we prove that the expected number of zeros of the random system in the positive orthant is at most $(2π)^{-\frac{n}{2}} V_0 (t_1-1)\ldots (t_n-1)$. Here $V_0$ denotes the number of vertices of the Minkowski sum $P_1+\ldots + P_n$. However, this bound does not imp
View details →