Category
19,710 papers
Deep neural networks often fail at small-sample regression, collapsing to low-variance predictions that miss individual differences. Here, we introduce a pairwise comparison framework that reframes regression as aggregated relative rankings. This method improves data efficiency across model architectures and dataset si...
Watermarking has emerged as a key tool for identifying text generated by large language models (LLMs), with current schemes embedding statistical signals into the generation process to enable later detection. In this work, we identify a shared weakness across a broad class of popular LLM watermarking methods, including...
This work ablate a production pipeline that turns conference speech into question-answer pairs, and finds that more than a third of its pairs carry knowledge that neither of two frontier models produces on its own.
Temperature scaling is typically applied as a post-hoc transformation of model probabilities. In posterior-induced flow language models, this creates two mismatches. First, posterior tempering implicitly changes both the endpoint distribution and the distribution of intermediate noisy states, while the denoiser remains...
Reach audiences
Advertise in front of researchers, engineers, and readers.
It is shown that a single egocentric camera worn on the collector's head replaces the wrist camera, the pose tracker and their separate streams with one, and the full co-trained head-camera policy succeeds in 20/25 against 15/25 for the wrist-camera recipe, and 12/25 for a fixed camera.
The central result is an impossibility: relational purpose violations form a 2-safety hyperproperty with no per-trace locus of blame, so a per-action monitor that never raises a false alarm detects none of them, independent of the underlying model or decision procedure.
By learning heterogeneous inter-graph interactions, the proposed method achieved state-of-the-art accuracy in predicting band gaps of 1,682 hybrid solar cell materials.
ABench is a fine-grained, handcrafted benchmark specifically tailored to taxonomized values in Chinese, grounded in a rigorous hierarchical taxonomy comprising 158 derived value subcategories and utilizing question-specific scoring criteria for nuanced assessment.
Together, the findings support a claim-indexed reporting standard that connects each claim to the evaluation design needed to test it, and evidence for repeatability and improved procedures remains less developed than product evaluation.
The WORTH Benchmark is proposed: models read original mystery narratives without clue annotations, autonomously select key clue sentences, identify case participants, and explain their reasoning process, and it is suggested that not-fully-cooperative informational relationships may influence evidence selection and judg...
When unique pretraining data is scarce, models see the same tokens many times and are thought to memorize. Random-token replacement, an input-corruption augmentation, is one remedy reported to lower validation loss, but a lower loss alone does not reveal which source of error it reduces. On a controlled source whose en...
Factual recall is a lookup: some representation inside the network serves as the key, and what that key is made of decides which queries can retrieve the fact, what an edit must cover, and what a retriever can read. We call it the factual access state. In autoregressive (AR) models the subject position enriches attribu...
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
