Zachary Izzo NEC Labs America

Zachary Izzo

Researcher

Machine Learning

Posts

To Err Is Human: Systematic Quantification of Errors in Published AI Papers via LLM Analysis

/in /by

How many mistakes do published AI papers contain? Peer-reviewed publications form the foundation upon which new research and knowledge are built. Errors that persist in the literature can propagate unnoticed, creating confusion in follow-up studies and complicating reproducibility. The accelerating pace of research and the increasing demands on the peer-review system make such mistakes harder to detect and avoid. To address this, we developed a Paper Correctness Checker based on GPT-5 to systematically identify mistakes in papers previously published at top AI conferences and journals. Our analysis focuses on objective mistakes-e.g., errors in formulas, derivations, calculations, figures, and tables-that have a clearly verifiable ground truth. We intentionally exclude subjective considerations such as novelty, importance, or writing quality. We find that published papers contain a non-negligible number of objective mistakes and that the average number of mistakes per paper has increased over time-from 3.8 in NeurIPS 2021 to 5.9 in NeurIPS 2025 (55.3% increase); from 4.1 in ICLR 2018 to 5.2 in ICLR 2025; and from 5.0 in TMLR 2022/23 to 5.5 in TMLR 2025. Human experts reviewed 316 potential mistakes identified by the AI Checker and confirmed that 263 were actual mistakes, corresponding to a precision of 83.2%. While most identified issues are relatively minor, correcting them would reduce confusion in the literature and strengthen reproducibility. The AI Checker also surfaced potentially more substantive mistakes that could affect the interpretation of results. Moreover, we show that the AI Checker can propose correct fixes for 75.8% of the identified mistakes. Overall, this study highlights the potential of frontier LLMs to detect and correct objective mistakes in published papers, helping to establish a firmer foundation of knowledge.

Read more

Quantitative Bounds for Length Generalization in Transformers

/in /by

We study the problem of length generalization (LG) in transformers: the ability of a model trained on shorter sequences to maintain performance when evaluated on much longer, previously unseen inputs. Prior work by Huang et al. (2025) established that transformers eventually achieve length generalization once the training sequence length exceeds some finite threshold, but left open the question of how large it must be. In this work, we provide the first quantitative bounds on the required training length for length generalization to occur. Motivated by previous empirical and theoretical work, we analyze LG in several distinct problem settings: error control vs. average error control over an input distribution, infinite-precision softmax attention vs. finite-precision attention (which reduces to an argmax) in the transformer, and one- vs. two-layer transformers. In all scenarios, we prove that LG occurs when the internal behavior of the transformer on longer sequences can be “simulated” by its behavior on shorter sequences seen during training. Our bounds give qualitative estimates for the length of training data required for a transformer to generalize, and we verify these insights empirically. These results sharpen our theoretical understanding of the mechanisms underlying extrapolation in transformers, and formalize the intuition that richer training data is required for generalization on more complex tasks.

Read more

Group Relative Augmentation for Data Efficient Action Detection

/in /by

Adapting large Video-Language Models (VLMs) for action detection using only a few examples poses challenges like overfitting and the granularity mismatch between scene-level pre-training and required person-centric understanding. We propose an efficient adaptation strategy combining parameter-efficient tuning (LoRA) with a novel learnable internal feature augmentation. Applied within the frozen VLM backbone using FiLM, these augmentations generate diverse feature variations directly relevant to the task. Additionally, we introduce a group-weighted loss function that dynamically modulates the training contribution of each augmented sample based on its prediction divergence relative to the group average. This promotes robust learning by prioritizing informative yet reasonable augmentations. We demonstrate our method’s effectiveness on complex multi-label, multi-person action detection datasets (AVA, MOMA), achieving strong mAP performance and showcasing significant data efficiency for adapting VLMs from limited examples.

Read more

Quantitative Bounds for Length Generalization in Transformers

/in /by

We provide quantitative bounds on the length of sequences required to be observed during training for a transformer to length generalize, e.g., to continue to perform well on sequences unseen during training. Our results improve on Huang et al. [8], who show that there is a finite training length beyond which length generalization is guaranteed, but for which they do not provide quantitative bounds.

Read more

Solving Inverse Problems via a Score-Based Prior: An Approximation-Free Posterior Sampling Approach

/in /by

Diffusion models (DMs) have proven to be effective in modeling high-dimensional distributions, leading to their widespread adoption for representing complex priors in Bayesian inverse problems (BIPs). However, current DM-based posterior sampling methods proposed for solving common BIPs rely on heuristic approximations to the generative process. To exploit the generative capability of DMs and avoid the usage of such approximations, we propose an ensemble-based algorithm that performs posterior sampling without the use of heuristic approximations. Our algorithm is motivated by existing works that combine DM-based methods with the sequential Monte Carlo (SMC) method. By examining how the prior evolves through the diffusion process encoded by the pre-trained score function, we derive a modified partial differential equation (PDE) governing the evolution of the corresponding posterior distribution. This PDE includes a modified diffusion term and a reweighting term, which can be simulated via stochastic weighted particle methods. Theoretically, we prove that the error between the true posterior distribution canbe bounded in terms of the training error of the pre-trained score function and the ]number of particles in the ensemble. Empirically, we validate our algorithm on several inverse problems in imaging to show that our method gives more accurate reconstructions compared to existing DM-based methods.

Read more

Domain-Guided Weight Modulation for Semi-Supervised Domain Generalization

/in /by

Unarguably deep learning models capable of generalizing to unseen domain data while leveraging a few labels are of great practical significance due to low developmental costs. In search of this endeavor we study the challenging problem of semi-supervised domain generalization (SSDG) where the goal is to learn a domain-generalizable model while using only a small fraction of labeled data and a relatively large fraction of unlabeled data. Domain generalization (DG) methods show subpar performance under the SSDG setting whereas semi-supervised learning (SSL) methods demonstrate relatively better performance however they are considerably poor compared to the fully-supervised DG methods. Towards handling this new but challenging problem of SSDG we propose a novel method that can facilitate the generation of accurate pseudo-labels under various domain shifts. This is accomplished by retaining the domain-level specialism in the classifier during training corresponding to each source domain. Specifically we first create domain-level information vectors on the fly which are then utilized to learn a domain-aware mask for modulating the classifier’s weights. We provide a mathematical interpretation for the effect of this modulation procedure on both pseudo-labeling and model training. Our method is plug-and-play and can be readily applied to different SSL baselines for SSDG. Extensive experiments on six challenging datasets in two different SSDG settings show that our method provides visible gains over the various strong SSL-based SSDG baselines. Our code is available at github.com/DGWM.

Read more

Subgroup Discovery with the Cox Model

/in /by

We study the problem of subgroup discovery with Cox regression models and introduce a method for finding an interpretable subset of the data on which a Cox model is highly accurate. Our method relies on two technical innovations: the emph (Unknown sysvar: (expected prediction entropy)), a novel metric for evaluating survival models which predict a hazard function; and the emph (Unknown sysvar: (conditional rank distribution)), a statistical object which quantifies the deviation of an individual point to the distribution of survival times in an existing subgroup. Because of the interpretability of the discovered subgroups, in addition to improving the predictive accuracy of the model, they can also form meaningful, data-driven patient cohorts for further study in a clinical setting.

Read more

NEC Labs America Team Attending NeurIPS24 in Vancouver

/in /by

NEC Labs America is proud to attend NeurIPS 2024 in Vancouver, Canada from December 10-15. Zachary Izzo will present Subgroup Discovery with the Cox Model, Shaobo Han will present VB-LoRA: Extreme Parameter Efficient Fine-Tuning with Vector Banks and Jonathan Warrell will present Discrete-Continuous Variational Optimization with Local Gradients.

Read more

Matching Confidences and Softened Target Occurrences for Calibration

/in /by

The problem of calibrating deep neural networks (DNNs) is gaining attention, as these networks are becoming central to many real-world applications. Different attempts have been made to counter the poor calibration of DNNs. Amongst others, train-time calibration methods have unfolded as an effective class for improving model calibration. Motivated by this, we propose a novel train-time calibration method that is built on a new auxiliary loss formulation, namely multiclass alignment of confidences with the gradually softened ground truth occurrences (MACSO). It is developed on the intuition that, for a class, the gradually softened ground truth occurrences distribution is a suitable non-zero entropy signal whose better alignment withthe predicted confidences distribution is positively correlated with reducing the model calibration error. In our train-time approach, besides simply aligning the two distributions, e.g., via their means or KL divergence, we propose to quantify the linear correlation between the two distributions, which preserves the relations among them, thereby further improving the calibration performance. Finally, we also reveal that MACSO posses desirable theoretical properties. Extensive results on several challenging datasets, featuring in and out-of-domain scenarios, class imbalanced problem, and a medical image classification task, validate the efficacy of our method against state-of-the-art train-time calibration methods.

Read more

Introducing the Trustworthy Generative AI Project: Pioneering the Future of Compositional Generation and Reasoning

/in /by

We are thrilled to announce the launch of our latest research initiative, the Trustworthy Generative AI Project. This ambitious project is set to revolutionize how we interact with multimodal content by developing cutting-edge generative models capable of compositional generation and reasoning across text, images, reports, and even 3D videos.

Read more