Related papers: DOS: Dependency-Oriented Sampler for Masked Diffus…

Transformer has been widely used for self-supervised pre-training in Natural Language Processing (NLP) and achieved great success. However, it has not been fully explored in visual self-supervised learning. Meanwhile, previous methods only…

In arbitrary-order language models, it is an open question how to sample tokens in parallel from the correct joint distribution. With discrete diffusion models, the more tokens they generate in parallel, the less their predicted…

Optimizing discrete diffusion model (DDM) with rewards remains a challenge: the non-autoregressive paradigm makes importance sampling intractable and rollout complex, puzzling reinforcement learning methods such as Group Relative Policy…

Molecular optimization (MO) is a crucial stage in drug discovery in which task-oriented generated molecules are optimized to meet practical industrial requirements. Existing mainstream MO approaches primarily utilize external property…

Speech generation models based on large language models (LLMs) typically operate on discrete acoustic codes, which differ fundamentally from text tokens due to their multicodebook structure. At each timestep, models must predict N codebook…

Building scalable and reusable multi-agent decision policies from offline datasets remains a challenge in offline multi-agent reinforcement learning (MARL), as existing methods often rely on fixed observation formats and action spaces that…

Recent large language models (LLMs) have demonstrated strong reasoning capabilities that benefits from online reinforcement learning (RL). These capabilities have primarily been demonstrated within the left-to-right autoregressive (AR)…

While diffusion Multimodal Large Language Models (dMLLMs) have recently achieved remarkable strides in multimodal generation, the development of interpretability mechanisms has lagged behind their architectural evolution. Unlike traditional…

Imitation Learning offers a promising approach to learn directly from data without requiring explicit models, simulations, or detailed task definitions. During inference, actions are sampled from the learned distribution and executed on the…

Any order generation of discrete data using masked diffusion models (MDMs) offers a compelling alternative to traditional autoregressive models, especially in domains that lack a natural causal ordering of data. However, current popular…

Adapting language models (LMs) to novel domains is often achieved through fine-tuning a pre-trained LM (PLM) on domain-specific data. Fine-tuning introduces new knowledge into an LM, enabling it to comprehend and efficiently perform a…

Masked diffusion models (MDMs), which leverage bidirectional attention and a denoising process, are narrowing the performance gap with autoregressive models (ARMs). However, their internal attention mechanisms remain under-explored. This…

Diffusion-based Large Language Models (dLLMs) have emerged as a competitive alternative to autoregressive models, offering unique advantages through bidirectional attention and parallel generation paradigms. However, the generation results…

Masked diffusion models (MDMs) have recently emerged as a promising alternative to autoregressive models over discrete domains. MDMs generate sequences in an any-order, parallel fashion, enabling fast inference and strong performance on…

To ensure that text generated by large language models (LLMs) is in an expected format, constrained decoding proposes to enforce strict formal language constraints during generation. However, as we show in this work, not only do such…

Task-oriented dialogue systems based on Large Language Models (LLMs) have gained increasing attention across various industries and achieved significant results. Current approaches condense complex procedural workflows into a single agent…

We study the problem of learning a neural sampler to generate samples from discrete state spaces where the target probability mass function $\pi\propto\mathrm{e}^{-U}$ is known up to a normalizing constant, which is an important task in…

This paper describes several improvements to a new method for signal decomposition that we recently formulated under the name of Differentiable Dictionary Search (DDS). The fundamental idea of DDS is to exploit a class of powerful deep…

This thesis provides methods and analysis of models which make progress on this goal. The techniques outlined are task agnostic, and should provide benefit when used with nearly any transformer LM. We introduce two new finetuning methods…

In this paper, we present Morse, a simple dual-sampling framework for accelerating diffusion models losslessly. The key insight of Morse is to reformulate the iterative generation (from noise to data) process via taking advantage of fast…