Sponsor of the Day:
Jerkmate
https://openreview.net/forum?id=yzkSU5zdwD
Emergent Abilities of Large Language Models | OpenReview
Scaling up language models has been shown to predictably improve performance and sample efficiency on a wide range of downstream tasks. This paper instead...
large language modelsemergentabilitiesopenreview
https://openreview.net/forum?id=WCRQFlji2q
Do I Know This Entity? Knowledge Awareness and Hallucinations in Language Models | OpenReview
Hallucinations in large language models are a widespread problem, yet the mechanisms behind whether models will hallucinate are poorly understood, limiting our...
language models openreviewknowledge awarenessentityhallucinations
https://openreview.net/forum?id=m6xyTie61H
Eliciting Language Model Behaviors using Reverse Language Models | OpenReview
Despite advances in fine-tuning methods, language models (LMs) continue to output toxic and harmful responses on worst-case inputs, including adversarial...
language modelusing reversemodels openreviewelicitingbehaviors
https://openreview.net/forum?id=SylkYeHtwr
SUMO: Unbiased Estimation of Log Marginal Probability for Latent Variable Models | OpenReview
We create an unbiased estimator for the log probability of latent variable models, extending such models to a larger scope of applications.
latent variable modelssumounbiasedestimationlog
https://openreview.net/forum?id=yaqPf0KAlN
Omni-MATH: A Universal Olympiad Level Mathematic Benchmark for Large Language Models | OpenReview
Recent advancements in large language models (LLMs) have led to significant breakthroughs in mathematical reasoning capabilities. However, existing benchmarks...
large language modelsolympiad levelomnimathuniversal
https://openreview.net/forum?id=EfQv02muYG
Causal Data Augmentation for Robust Fine-Tuning of Tabular Foundation Models | OpenReview
Fine-tuning tabular foundation models (TFMs) in the face of scarce data is challenging, as early stopping on even scarcer validation data often fails to...
tabular foundation modelsdata augmentationfine tuningcausalrobust
https://openreview.net/forum?id=r1lZgyBYwS
HiLLoC: lossless image compression with hierarchical latent variable models | OpenReview
We scale up lossless compression with latent variables, achieving state of the art on full-size ImageNet images.
latent variable modelslossless imagecompressionhierarchicalopenreview
https://openreview.net/forum?id=j4-a3SNyaY
Journey to the BAOAB-limit: finding effective MCMC samplers for score-based models | OpenReview
Sometimes bugs are effective MCMC samplers for score-based models.
based modelsjourneylimitfindingeffective
https://openreview.net/forum?id=1i4wNFgHDd
Generalizable, real-time neural decoding with hybrid state-space models | OpenReview
Real-time decoding of neural activity is central to neuroscience and neurotechnology applications, from closed-loop experiments to brain-computer interfaces,...
state space modelsreal timegeneralizableneuraldecoding
https://openreview.net/forum?id=YBOQ5HnzI6
Mamba4Cast: Efficient Zero-Shot Time Series Forecasting with State Space Models | OpenReview
This paper introduces Mamba4Cast, a zero-shot foundation model for time series forecasting. Based on the Mamba architecture and inspired by Prior-data Fitted...
time series forecastingstate space modelszero shotefficientopenreview
https://openreview.net/forum?id=h8hy1lABh3
Towards Synthetic Data for Fine-tuning Tabular Foundation Models | OpenReview
Tabular foundation models pre-trained on synthetically generated datasets have exhibited strong in-context learning capabilities. While fine-tuning can further...
tabular foundation modelssynthetic datafine tuningtowardsopenreview
https://openreview.net/forum?id=Lm8T39vLDTE
Autoregressive Diffusion Models | OpenReview
We introduce Autoregressive Diffusion Models (ARDMs), a model class encompassing and generalizing order-agnostic autoregressive models (Uria et al., 2014) and...
diffusion modelsautoregressiveopenreview