Related papers: Test-Time Tuned Language Models Enable End-to-end …

Product distribution matching (PDM) is proposed to generate target distributions over large alphabets by combining the output of several parallel distribution matchers (DMs) with smaller output alphabets. The parallel architecture of PDM…

Model generation is a problem complementary to theorem proving and is important for fault analysis and debugging of formal specifications of security protocols, programs and terminological definitions. This paper discusses several ways of…

Sequence-to-sequence learning with neural networks has become the de facto standard for sequence prediction tasks. This approach typically models the local distribution over the next word with a powerful neural network that can condition on…

The autoregressive nature of conventional large language models (LLMs) inherently limits inference speed, as tokens are generated sequentially. While speculative and parallel decoding techniques attempt to mitigate this, they face…

De novo molecular generation from tandem mass spectra is a challenging inverse problem whose core difficulty lies in the circular dependency between atom-level and bond-level reasoning: determining a bond's type requires knowing its…

Language models for molecular design have scaled to hundreds of millions of parameters, yet how they learn chemical grammar is poorly understood. We train SMolLM, a 53K-parameter weight-shared transformer, to generate novel SMILES with 95%…

Motivation: Mass spectrometry-based proteomics is among the most commonly used methods for scrutinizing proteomic profiles in different organs for biological or medical researches. All the proteomic analyses including peptide/protein…

Mining large-scale high-throughput tandem mass spectrometry data sets is a very important problem in mass spectrometry based protein identification. One of the fundamental problems in large scale mining of spectra is to design appropriate…

Statistical shape modeling (SSM) has recently taken advantage of advances in deep learning to alleviate the need for a time-consuming and expert-driven workflow of anatomy segmentation, shape registration, and the optimization of…

Understanding molecular structure, dynamics, and reactivity requires bridging processes that occur across widely separated time scales. Conventional molecular dynamics simulations provide atomistic resolution, but their femtosecond time…

Although n-gram language models (LMs) have been outperformed by the state-of-the-art neural LMs, they are still widely used in speech recognition due to its high efficiency in inference. In this paper, we demonstrate that n-gram LM can be…

Test-time training (TTT) methods explicitly update the weights of a model to adapt to the specific test instance, and they have found success in a variety of settings, including most recently language modeling and reasoning. To demystify…

Structure-based protein design has attracted increasing interest, with numerous methods being introduced in recent years. However, a universally accepted method for evaluation has not been established, since the wet-lab validation can be…

Medical image analysis using deep learning is often challenged by limited labeled data and high annotation costs. Fine-tuning the entire network in label-limited scenarios can lead to overfitting and suboptimal performance. Recently, prompt…

We propose a unified mixture sampler (UMS) that provides a universal estimation framework for nonlinear state-space models with "exp-exp" likelihood kernels. Unlike existing methods that require deriving new mixture approximations for each…

Molecular dynamics (MD) is a powerful approach for modelling molecular systems, but it remains computationally intensive on spatial and time scales of many macromolecular systems of biological interest. To explore the opportunities offered…

Effectively modeling non-stationary dynamics in probabilistic multivariate time series(MTS) forecasting requires balancing expressiveness with robustness. Existing parametric approaches benefit from strong inductive biases but lack…

We consider the task of building compact deep learning pipelines suitable for deployment on storage and power constrained mobile devices. We propose a unified framework to learn a broad family of structured parameter matrices that are…

Accurate modeling of eye gaze dynamics is essential for advancement in human-computer interaction, neurological diagnostics, and cognitive research. Traditional generative models like Markov models often fail to capture the complex temporal…

Large-scale transformers achieve impressive results on program synthesis benchmarks, yet their true generalization capabilities remain obscured by data contamination and opaque training corpora. To rigorously assess whether models are truly…