Related papers: The Path Matters: Learning a Token-Commitment Poli…
Diffusion language models (DLMs) have recently emerged as a strong alternative to autoregressive models by enabling parallel text generation. To improve inference efficiency and KV-cache compatibility, prior work commonly adopts block-based…
Masked Diffusion Language Models generate sequences via iterative sampling that progressively unmasks tokens. However, they still recompute the attention and feed-forward blocks for every token position at every step -- even when many…
Discrete diffusion language models (dLLMs) enable parallel token updates with bidirectional attention, yet practical generation typically adopts blockwise semi-autoregressive decoding. This switch creates a training-inference mismatch:…
Diffusion large language models (dLLMs) have shown advantages in text generation, particularly due to their inherent ability for parallel decoding. However, constrained by the quality--speed trade-off, existing inference solutions adopt…
Discrete diffusion models have recently become competitive with autoregressive models for language modeling, even outperforming them on reasoning tasks requiring planning and global coherence, but they require more computation at inference…
Diffusion-based language models (dLLMs) have emerged as a promising alternative to autoregressive language models, offering the potential for parallel token generation and bidirectional context modeling. However, harnessing this flexibility…
Masked diffusion language models (MDLMs) enable parallel decoding by predicting all masked positions at each denoising step, yet existing training-free samplers usually decide which positions to commit at token-level granularity. We revisit…
Diffusion transformers have gained substantial interest in diffusion generative modeling due to their outstanding performance. However, their computational demands, particularly the quadratic complexity of attention mechanisms and…
Diffusion large language models (dLLMs) generate text through iterative denoising. In commonly adopted parallel decoding schemes, each step confirms only high-confidence positions while remasking the others. By analyzing dLLM denoising…
Discrete diffusion language models have emerged as a competitive alternative to auto-regressive language models, but training them efficiently under limited parameter and memory budgets remains challenging. Modern architectures are…
Diffusion Language Models (DLMs) decode multiple tokens in parallel, but aggressive multi-token decoding amplifies cross-token dependency errors and can sharply degrade generation quality. We propose BackPlay, a frozen-backbone…
Most large language models are autoregressive: they generate tokens one at a time. Discrete diffusion language models can generate multiple tokens in parallel, but sampling from them requires a denoising order: a strategy for deciding which…
Diffusion language models decode text by iteratively denoising masked token sequences, making the choice of which positions to decode a central inference-time decision. Most training-free decoding strategies use model confidence for…
Offline reinforcement learning (RL) leverages pre-collected datasets to train optimal policies. Diffusion Q-Learning (DQL), introducing diffusion models as a powerful and expressive policy class, significantly boosts the performance of…
Diffusion language models (DLMs) generate text through iterative denoising, but inference requires full-sequence attention at every iteration, resulting in substantial redundant computation on masked tokens. Block-wise diffusion can reduce…
This paper presents Diffusion Forcing, a new training paradigm where a diffusion model is trained to denoise a set of tokens with independent per-token noise levels. We apply Diffusion Forcing to sequence generative modeling by training a…
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.…
Predicting the binding structure of a small molecule ligand to a protein -- a task known as molecular docking -- is critical to drug design. Recent deep learning methods that treat docking as a regression problem have decreased runtime…
Diffusion language models are a promising alternative to autoregressive models, yet post-training methods for them largely adapt reward-maximizing objectives. We identify a central failure mode in this setting we call trajectory locking:…
As large language models (LLMs) scale up, accuracy improves, but the autoregressive (AR) nature of decoding increases latency since each token requires a serial forward pass. Speculative decoding addresses this by employing a fast drafter…