相关论文: Masked Language Modeling Becomes Conditional Densi…

Developing Machine Learning (ML) algorithms for heterogeneous/mixed data is a longstanding problem. Many ML algorithms are not applicable to mixed data, which include numeric and non-numeric data, text, graphs and so on to generate…

The goal of optimization-based meta-learning is to find a single initialization shared across a distribution of tasks to speed up the process of learning new tasks. Conditional meta-learning seeks task-specific initialization to better…

Large language models (LLMs) effectively generate fluent text when the target output follows natural language patterns. However, structured prediction tasks confine the output format to a limited ontology, causing even very large models to…

Masked diffusion language models (MDLMs) have emerged as a promising alternative to dominant autoregressive approaches. Although they achieve competitive performance on several tasks, a substantial gap remains in open-ended text generation.…

Masked diffusion models (MDMs) have shown promise in language modeling, yet their scalability and effectiveness in core language tasks, such as text generation and language understanding, remain underexplored. This paper establishes the…

Multimodal Large Language Models (MLLMs) rely on strong linguistic reasoning inherited from their base language models. However, multimodal instruction fine-tuning paradoxically degrades this text's reasoning capability, undermining…

While large language models (LLMs) bring not only performance but also complexity, recent work has started to turn LLMs into data generators rather than task inferencers, where another affordable task model is trained for efficient…

Recently, program synthesis driven by large language models (LLMs) has become increasingly popular. However, program synthesis for machine learning (ML) tasks still poses significant challenges. This paper explores a novel form of program…

The current era of natural language processing (NLP) has been defined by the prominence of pre-trained language models since the advent of BERT. A feature of BERT and models with similar architecture is the objective of masked language…

Automating the decision of whether a code change requires manual review is vital for maintaining software quality in modern development workflows. However, the emergence of new programming languages and frameworks creates a critical…

Masked Language Modeling (MLM) has been one of the most prominent approaches for pretraining bidirectional text encoders due to its simplicity and effectiveness. One notable concern about MLM is that the special $\texttt{[MASK]}$ symbol…

We study how masking and predicting tokens in an unsupervised fashion can give rise to linguistic structures and downstream performance gains. Recent theories have suggested that pretrained language models acquire useful inductive biases…

The Multimodal Large Language Models (MLLMs) are continually pre-trained on a mixture of image-text caption data and interleaved document data, while the high-quality data filtering towards image-text interleaved document data is…

Large Language Models (LLMs) have demonstrated remarkable multilingual capabilities, making them promising tools in both high- and low-resource languages. One particularly valuable use case is generating synthetic samples that can be used…

Masked Diffusion Models (MDMs) provide an efficient non-causal alternative to autoregressive generation but often struggle with token dependencies and semantic incoherence due to their reliance on discrete marginal distributions. We address…

Masked diffusion models (MDM) are powerful generative models for discrete data that generate samples by progressively unmasking tokens in a sequence. Each token can take one of two states: masked or unmasked. We observe that token sequences…

Multimodal Large Language Models (MLLMs) have demonstrated exceptional capabilities in high-level visual understanding. However, extending these models to fine-grained dense prediction tasks, such as semantic segmentation and depth…

In this work, we address the task of table image to LaTeX code generation, with the goal of automating the reconstruction of high-quality, publication-ready tables from visual inputs. A central challenge of this task lies in accurately…

The success of Large Language Models (LLMs) is inherently linked to the availability of vast, diverse, and high-quality data for training and evaluation. However, the growth rate of high-quality data is significantly outpaced by the…

Large language models (LLMs) rely on pretraining on massive and heterogeneous corpora, where training data composition has a decisive impact on training efficiency and downstream generalization under realistic compute and data budget…