Stay updated with the latest developments in Artificial Intelligence
In sectors such as energy, aquaculture and chemical processing, the effectiveness of both mechanistic and data-driven models is frequently limited by poor-quality training data, which obscures underlying physical laws and degrades predictive accuracy.
Layer-ablation studies often perturb early or late layers of a language model, compare the damage to prediction on two corpora, and read a larger early-layer effect on one corpus as early-layer specialization for its task.
Meta-evaluation of text generation metrics and LLM-judges is primarily conducted using metric-human correlations. However, prior work has shown that correlation is not an appropriate estimate of a metric's evaluation capability and can be unstable across evaluation settings, such as different…
Recent advancements in topic modeling have split into two main paths: efficient embedding-based methods that offer scalability but are often outperformed on standard clustering metrics, and Large Language Model (LLM) approaches that achieve state-of-the-art clustering performance but at the cost of…
Estimating (heterogeneous) treatment effects is still challenging when the outcome is semicontinuous (i.e., exhibiting both a discrete point mass at zero and a skewed continuous distribution for positive values), despite the strong presence of this data type in real world settings.
Full waveform inversion (FWI) is a powerful tool for high-resolution subsurface model reconstruction, but it remains highly nonlinear and ill-posed, especially when the initial model is inaccurate or the acquired data are noisy and incomplete.
Efficient global optimization aims to identify a global optimum of an expensive black-box function within a limited evaluation budget $N$. We investigate the convergence rates of Gaussian process Thompson sampling (GP-TS) under noiseless observations, assuming a fixed objective function in a…
Because its binary optimization landscape contains exponentially many local optima, MAX-CUT is highly sensitive to initialization. We study Particle Polynomial Relaxation (PPR), a moment-based nonconvex continuous reformulation possessing an advantageous optimization landscape.
Transformers are efficient to pre-train at scale because attention permits parallel computation across sequence positions, but long-context inference requires increasingly large KV caches.
In-context learning (ICL) allows language models to adapt their behavior from instructions and demonstrations in a prompt, but accuracy alone does not reveal how contextual information controls their predictions.
Ukrainian president calls Trump-Putin relationship a ‘mistake’
Discrete diffusion models have emerged as a leading alternative to autoregressive models for generating text and other categorical data, yet their theoretical foundations remain less developed than those of their continuous counterparts.
This paper presents LLM-jp-4, a family of Japanese sovereign large language models (LLMs) developed with an emphasis on transparency, reproducibility, and practical usability.
Many sentiment datasets use one annotator for each item, so the test labels show the conventions of that person. We build a Nepali benchmark from two annotators who labelled the same sentences blind. They labelled 5,614 sentences from tweets of Nepali public figures on a five-point scale.
Low-rank adaptation (LoRA) applies every rank-one component of its update to every token, and mixture-of-experts variants replace this with a learned router that activates a fixed number of components.
Abstractive summarization remains challenging across languages, where linguistic quality and factual consistency may diverge, particularly in low-resource settings.
Feature distillation is usually expected to add to logit distillation. We find that this expectation does not hold for two common feature losses in compact multilingual automatic speech recognition (ASR), and analyze why through their gradients.
Large language model (LLM) evaluators are increasingly used to assess personalized assistants, yet whether they can reliably judge personalization has rarely been tested.
Showing 72 of 31,395 stories
Load more storiesGet the top AI news and tools straight to your inbox every week.
Weekly · AI news
Join 15,000+ AI enthusiasts
