Related papers: Stop-Think-AutoRegress: Language Modeling with Lat…
Continuous latent-space reasoning offers a compact alternative to textual chain-of-thought for multimodal models, enabling high-dimensional visual evidence to be integrated without explicit reasoning tokens. However, we identify a…
The current era of Natural Language Processing (NLP) is dominated by Transformer models. However, novel architectures relying on recurrent mechanisms, such as xLSTM and Mamba, have been proposed as alternatives to attention-based models.…
Diffusion Large Language Models (dLLMs) offer a compelling paradigm for natural language generation, leveraging parallel decoding and bidirectional attention to achieve superior global coherence compared to autoregressive models. While…
Diffusion models achieve state-of-the-art image generation but remain computationally costly due to iterative denoising. Latent-space models like Stable Diffusion reduce overhead yet lose fine detail, while retrieval-augmented methods…
We present significant extensions to diffusion-based sequence generation models, blurring the line with autoregressive language models. We introduce hyperschedules, which assign distinct noise schedules to individual token positions,…
Auto-regressive models (ARMs) have established a dominant paradigm in language modeling. However, their strictly sequential decoding paradigm imposes fundamental constraints on both inference efficiency and modeling flexibility. To address…
Reinforcement Learning (RL) is crucial for unlocking the complex reasoning capabilities of Diffusion-based Large Language Models (dLLMs). However, applying RL to dLLMs faces unique challenges in efficiency and stability. To address these…
Diffusion-based language models are emerging as a promising alternative to autoregressive LMs: they approach the competence of autoregressive LMs while offering nuanced controllability at inference time. While autoregressive LMs have…
Diffusion Large Language Models (dLLMs) enable breakthroughs in reasoning and parallel decoding but suffer from prohibitive quadratic computational complexity and memory overhead during inference. Current caching techniques accelerate…
Large Language Models (LLMs) have achieved state-of-the-art performance on a broad range of Natural Language Processing (NLP) tasks, including document processing and code generation. Autoregressive Language Models (ARMs), which generate…
Large Language Models (LLMs) continue to set new standards in knowledge-intensive and complex reasoning tasks, yet their high computational demands limit widespread adoption. While distilling large models into smaller ones offers a…
Large language models (LLMs) offer significant promise as a knowledge source for task learning. Prompt engineering has been shown to be effective for eliciting knowledge from an LLM, but alone it is insufficient for acquiring relevant,…
Large Language Models (LLMs) tend to generate a long reasoning chain when solving complex tasks. However, as the reasoning chain extends, critical intermediate steps and the original prompt will be buried in the context, receiving…
The paradigm of Large Language Models (LLMs) is currently defined by auto-regressive (AR) architectures, which generate text through a sequential ``brick-by-brick'' process. Despite their success, AR models are inherently constrained by a…
Diffusion models have recently shown the ability to generate high-quality images. However, controlling its generation process still poses challenges. The image style transfer task is one of those challenges that transfers the visual…
Small language models (SLMs) offer computational efficiency for scalable deployment, yet they often fall short of the reasoning power exhibited by their larger counterparts (LLMs). To mitigate this gap, current approaches invoke an LLM to…
We introduce ASTRO, the "Autoregressive Search-Taught Reasoner", a framework for training language models to reason like search algorithms, explicitly leveraging self-reflection, backtracking, and exploration in their outputs. Recently,…
We extend the recent latent recurrent modeling to sequential input streams. By interleaving fast, recurrent latent updates with self-organizational ability between slow observation updates, our method facilitates the learning of stable…
We study why continuous diffusion language models (DLMs) have lagged behind discrete diffusion approaches despite their appealing continuous generative dynamics. Under a controlled token--recovery study, we identify token rounding, the…
Large reasoning models (LRMs) are proficient at generating explicit, step-by-step reasoning sequences before producing final answers. However, such detailed reasoning can introduce substantial computational overhead and latency,…