Related papers: EDIT: Early Diffusion Inference Termination for dL…

Diffusion-based large language models (DLLMs) have shown promise for non-autoregressive text generation, but their deployment is constrained by large model sizes and heavy computational costs. Post-training quantization (PTQ), a widely used…

Diffusion Large Language Models (dLLMs) represent a new paradigm beyond autoregressive modeling, offering competitive performance while naturally enabling a flexible decoding process. Specifically, dLLMs can generate tokens at arbitrary…

Auto-regressive Large Language Models (LLMs) achieve strong performance on coding tasks, but incur high memory and inference costs. Diffusion-based language models (d-LLMs) offer bounded inference cost via iterative denoising, but their…

Large Language Models (LLMs) based on autoregressive, decoder-only Transformers generate text one token at a time, where a token represents a discrete unit of text. As each newly produced token is appended to the partial output sequence,…

Diffusion large language models (dLLMs) generate text through iterative denoising, yet current decoding strategies discard rich intermediate predictions in favor of the final output. Our work here reveals a critical phenomenon, temporal…

Masked diffusion language models (MDLMs) have recently emerged as a promising alternative to autoregressive (AR) language models, offering properties such as parallel decoding, flexible generation orders, and the potential for fewer…

Reinforcement learning with verifiable rewards (RLVR) is a powerful paradigm for enhancing the reasoning capabilities of large language models (LLMs), yet its success hinges on effective exploration. An ideal exploration strategy must…

Dataset distillation aims to synthesize a compact dataset from the original large-scale one, enabling highly efficient learning while preserving competitive model performance. However, traditional techniques primarily capture low-level…

Existing sequential recommendation models, even advanced diffusion-based approaches, often struggle to capture the rich semantic intent underlying user behavior, especially for new users or long-tail items. This limitation stems from their…

Prompt compression reduces inference cost and context length in large language models, but prior evaluations focus primarily on autoregressive architectures. This study investigates whether prompt compression transfers effectively to…

Diffusion models currently dominate the field of data-driven image synthesis with their unparalleled scaling to large datasets. In this paper, we identify and rectify several causes for uneven and ineffective training in the popular ADM…

Diffusion models have emerged as powerful generative priors for high-dimensional inverse problems, yet learning them when only corrupted or noisy observations are available remains challenging. In this work, we propose a new method for…

Entropy-based confidence signals are increasingly leveraged to improve reasoning in large language models (LLMs), yet existing approaches treat confidence as a static quantity -- typically aggregated over tokens. We show that the…

Diffusion models have demonstrated remarkable performance in the domain of text-to-image generation. However, most widely used models still employ CLIP as their text encoder, which constrains their ability to comprehend dense prompts,…

Diffusion language models (DLMs) promise parallel, order-agnostic generation, but on standard benchmarks they have historically lagged behind autoregressive models in sample quality and diversity. Recent continuous flow and diffusion…

We present CadLLM, a training-free method to accelerate the inference throughput of diffusion-based LLMs (dLLMs). We first investigate the dynamic nature of token unmasking confidence across blocks and steps. Based on this observation, we…

Steering language model generation toward desired textual properties is essential for practical deployment, and inference-time methods are particularly appealing because they enable controllable generation without retraining. Recent work…

Recent advances in large reasoning language models (LRLMs) rely on test-time scaling, which extends long chain-of-thought (CoT) generation to solve complex tasks. However, overthinking in long CoT not only slows down the efficiency of…

Text-conditioned image generation models have recently shown immense qualitative success using denoising diffusion processes. However, unlike discriminative vision-and-language models, it is a non-trivial task to subject these…

This paper investigates using knowledge editing techniques to detoxify Large Language Models (LLMs). We construct a benchmark, SafeEdit, which covers nine unsafe categories with various powerful attack prompts and equips comprehensive…