English
Related papers

Related papers: LLMs are Bayesian, In Expectation, Not in Realizat…

200 papers

Advances in neural architecture search, as well as explainability and interpretability of connectionist architectures, have been reported in the recent literature. However, our understanding of how to design Bayesian Deep Learning (BDL)…

Machine Learning · Computer Science 2021-06-24 Nidhin Harilal , Udit Bhatia , Auroop R. Ganguly

Recent advances in multimodal large language models (MLLMs) have yielded increasingly powerful models, yet their perceptual capacities remain poorly characterized. In practice, most model families scale language component while reusing…

Computer Vision and Pattern Recognition · Computer Science 2025-12-19 Tejas Anvekar , Fenil Bardoliya , Pavan K. Turaga , Chitta Baral , Vivek Gupta

To advance the transparency of learning machines such as Deep Neural Networks (DNNs), the field of Explainable AI (XAI) was established to provide interpretations of DNNs' predictions. While different explanation techniques exist, a popular…

Transformers predict over a representation of a sequence. The same data can be written as bytes, characters, or subword tokens, and these representations may be lossless. Yet, under a fixed context window, they need not expose the same…

Machine Learning · Computer Science 2026-05-14 Amirmehdi Jafari Fesharaki , Mohammadamin Rami , Aslan Tchamkerten

Standard evaluations of Bayesian deep learning methods assume that metric estimates are reliable, but we show this assumption fails under data scarcity. Method rankings are not only unreliable at small $n$, but also dataset-dependent in…

Machine Learning · Computer Science 2026-04-28 Qishi Zhan , Minxuan Hu , Guansu Wang , Jiaxin Liu , Liang He

Understanding emerging behaviors of reinforcement learning (RL) agents may be difficult since such agents are often trained in complex environments using highly complex decision making procedures. This has given rise to a variety of…

Artificial Intelligence · Computer Science 2022-12-02 Mira Finkelstein , Lucy Liu , Nitsan Levy Schlot , Yoav Kolumbus , David C. Parkes , Jeffrey S. Rosenshein , Sarah Keren

Scaling large language models (LLMs) leads to an emergent capacity to learn in-context from example demonstrations. Despite progress, theoretical understanding of this phenomenon remains limited. We argue that in-context learning relies on…

Computation and Language · Computer Science 2023-03-15 Michael Hahn , Navin Goyal

There is a growing interest in the so-called Bayesian Predictive Inference approach, which allows to perform Bayesian inference without specifying the likelihood and prior of the model, or the need of any MCMC. Instead, only a sequence of…

Statistics Theory · Mathematics 2025-09-30 Marco Battiston , Lorenzo Cappello

Principled Bayesian deep learning (BDL) does not live up to its potential when we only focus on marginal predictive distributions (marginal predictives). Recent works have highlighted the importance of joint predictives for (Bayesian)…

Machine Learning · Computer Science 2022-05-19 Andreas Kirsch , Jannik Kossen , Yarin Gal

Nonlinear causal discovery from observational data imposes strict identifiability assumptions on the formulation of structural equations utilized in the data generating process. The evaluation of structure learning methods under assumption…

Machine Learning · Statistics 2024-12-17 Georg Velev , Stefan Lessmann

We review recent advances in machine-learning (ML) force-field methods for large-scale Landau-Lifshitz-Gilbert (LLG) simulations of metallic spin systems. We generalize the Behler-Parrinello (BP) ML architecture -- originally developed for…

Strongly Correlated Electrons · Physics 2026-04-14 Gia-Wei Chern , Yunhao Fan , Sheng Zhang , Puhan Zhang

There has been considerable interest in using surprisal from Transformer-based language models (LMs) as predictors of human sentence processing difficulty. Recent work has observed an inverse scaling relationship between Transformers'…

Computation and Language · Computer Science 2026-02-04 Yi-Chien Lin , William Schuler

Large language models (LLMs) are known to exhibit brittle behavior under adversarial prompts and jailbreak attacks, even after extensive alignment and fine-tuning. This fragility reflects a broader challenge of modern neural language…

Computation and Language · Computer Science 2026-02-04 Patrick Cooper , Alireza Nadali , Ashutosh Trivedi , Alvaro Velasquez

Multilevel models (MLMs) are a central building block of the Bayesian workflow. They enable joint, interpretable modeling of data across hierarchical levels and provide a fully probabilistic quantification of uncertainty. Despite their…

The basic underlying assumption of machine learning (ML) models is that the training and test data are sampled from the same distribution. However, in daily practice, this assumption is often broken, i.e. the distribution of the test data…

Computation and Language · Computer Science 2026-01-16 Adriana Valentina Costache , Silviu Florin Gheorghe , Eduard Gabriel Poesina , Paul Irofti , Radu Tudor Ionescu

Detection of anomalous situations for complex mission-critical systems hold paramount importance when their service continuity needs to be ensured. A major challenge in detecting anomalies from the operational data arises due to the…

Machine Learning · Computer Science 2025-05-20 Shanay Mehta , Shlok Mehendale , Nicole Fernandes , Jyotirmoy Sarkar , Santonu Sarkar , Snehanshu Saha

Translation-based embedding models have gained significant attention in link prediction tasks for knowledge graphs. TransE is the primary model among translation-based embeddings and is well-known for its low complexity and high efficiency.…

Computation and Language · Computer Science 2019-07-12 Mojtaba Nayyeri , Xiaotian Zhou , Sahar Vahdati , Hamed Shariat Yazdi , Jens Lehmann

Large language models are increasingly deployed across diverse applications. This often includes tasks LLMs have not encountered during training. This implies that enumerating and obtaining the high-quality training data for all tasks is…

Computation and Language · Computer Science 2025-11-11 Shambhavi Krishna , Atharva Naik , Chaitali Agarwal , Sudharshan Govindan , Taesung Lee , Haw-Shiuan Chang

Estimating causal treatment effects in observational settings is frequently compromised by selection bias arising from unobserved confounders. While traditional econometric methods struggle when these confounders are orthogonal to…

Artificial Intelligence · Computer Science 2026-01-06 Ahmed Dawoud , Osama El-Shamy

We investigate the generalization boundaries of current Multimodal Large Language Models (MLLMs) via comprehensive evaluation under out-of-distribution scenarios and domain-specific tasks. We evaluate their zero-shot generalization across…

Computer Vision and Pattern Recognition · Computer Science 2024-02-12 Xingxuan Zhang , Jiansheng Li , Wenjing Chu , Junjia Hai , Renzhe Xu , Yuqing Yang , Shikai Guan , Jiazheng Xu , Peng Cui
‹ Prev 1 3 4 5 6 7 10 Next ›