Category
3,445 papers
AutoSynth, which represents MIDI performance events, fixed synthesizer parameters, and variable-length modulation routes as a unified sequence for a synthesizer, and learns their dependencies with an audio-conditioned autoregressive model, is presented.
Artificial intelligence applied to mass spectrometry-based metabolomics and lipidomics has advanced through three technological generations: chemometric and classical machine learning, deep learning, and self-supervised foundation models, with large language models so far entering mainly at the edges. The metabolome an...
Jev is a"System One"model that returns a choice among given options instead of generating text. We study how such a specialized decision model compares with general-purpose large language models (LLMs). We evaluate Jev on 13 multiple-choice benchmarks covering knowledge, reasoning, and multilingual understanding, and c...
Byte-level language models such as the Byte Latent Transformer (BLT) group bytes into patches and run their large global model once per patch. BLT starts a patch where a small model's next-byte entropy is high, so global compute goes where the next byte is hard to predict. We show that this rule has a systematic blind...
Reach audiences
Advertise in front of researchers, engineers, and readers.
Speech-to-LLM systems often connect a frozen speech encoder to a frozen large language model (LLM) through a small trainable bridge. The bridge is usually treated as plumbing, but it in fact defines the geometry of the speech-to-LLM interface, and the pretraining objective decides whether that interface provides a reus...
It is argued that sparse attention should be formulated as matrix approximation, not as blindly choosing the largest values from a bag of entries, and proposed Matrix Approximation Sparse Attention (MASA), which replaces raw attention-mass ranking with a closed-form score that measures how much each sparse unit reduces...
This work quantifies whether a public detector would be an additional liability in a deployment setting at varying levels of access, and introduces a split-key public-private watermarking method that exposes one key through a public detector while keeping the other for full verification and forensics.
A local recovery guarantee for teachers sufficiently close to the initial student in a shared parameterization under regularity conditions is proved, offering a conditional explanation for the success of self-RL teachers in the authors' experiments.
The Muon optimizer orthogonalizes each update matrix, setting all of its singular values to one, and has proven highly effective for training large language models. It remains unclear, however, whether this success comes from amplifying small singular directions that gradient descent neglects or from suppressing large,...
Knowledge distillation is an established technique for improving the capabilities of small, efficient student models by training them with the representations of larger, more capable teacher models. Much of the recent work in the distillation of large language models (LLMs) has focused on distilling abilities learned d...
Recent multimodal large language models (MLLMs) increasingly incorporate explainable reasoning for emotion understanding. However, reasoning based mainly on observable affective cues can reduce emotion understanding to superficial cue-label associations, giving rise to the Clever Hans effect. Such shortcuts become unre...
Reinforcement learning (RL) methods such as GRPO substantially improve large language model reasoning but often suffer from policy entropy collapse: the loss of sampling diversity weakens exploration and limits further improvement. Existing methods address this issue either through algorithm-level interventions, such a...
A Blog post by Liquid AI on Hugging Face
Genie 4: our new world model unlocking unprecedented realism in real-time simulation.
Generative AI
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
