Related papers: LLaDA2.1: Speeding Up Text Diffusion via Token Edi…

Autoregressive (AR) Large Language Models (LLMs) have demonstrated significant success across numerous tasks. However, the AR modeling paradigm presents certain limitations; for instance, contemporary autoregressive LLMs are trained to…

Modern Vision-Language Models (VLMs) can solve a wide range of tasks requiring visual reasoning. In real-world scenarios, desirable properties for VLMs include fast inference and controllable generation (e.g., constraining outputs to adhere…

Masked diffusion language models (MDLMs) offer the potential for parallel token generation, but most open-source MDLMs decode fewer than 5 tokens per model forward pass even with sophisticated sampling strategies, limiting their parallel…

We present a novel counterexample-guided, sketch-based method for the synthesis of symbolic distributed protocols in TLA+. Our method's chief novelty lies in a new search space reduction technique called interpretation reduction, which…

Striking an optimal balance between minimal drafting latency and high speculation accuracy to enhance the inference speed of Large Language Models remains a significant challenge in speculative decoding. In this paper, we introduce Falcon,…

Diffusion Large Language Models (dLLMs) have achieved rapid progress, viewed as a promising alternative to the autoregressive paradigm. However, most dLLM decoders still adopt a global confidence threshold, and do not explicitly model local…

Autoregressive next token prediction language models offer powerful capabilities but face significant challenges in practical deployment due to the high computational and memory costs of inference, particularly during the decoding stage. We…

Text-to-image (T2I) models are well known for their ability to produce highly realistic images, while multimodal large language models (MLLMs) are renowned for their proficiency in understanding and integrating multiple modalities. However,…

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-based large language models (dLLMs) are gaining attention for their inherent capacity for parallel decoding, offering a compelling alternative to autoregressive LLMs. Among various decoding strategies, block-wise…

Scaling text-to-speech (TTS) with autoregressive language model (LM) to large-scale datasets by quantizing waveform into discrete speech tokens is making great progress to capture the diversity and expressiveness in human speech, but the…

Latent diffusion models (LDMs) achieve state-of-the-art performance across various tasks, including image generation and video synthesis. However, they generally lack robustness, a limitation that remains not fully explored in current…

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…

Speculative decoding (SD) has proven effective for accelerating LLM inference by quickly generating draft tokens and verifying them in parallel. However, SD remains largely unexplored for Large Vision-Language Models (LVLMs), which extend…

Text-to-image diffusion models (SD) exhibit significant advancements while requiring extensive computational resources. Existing acceleration methods usually require extensive training and are not universally applicable. LCM-LoRA, trainable…

The architectural shift to prefill/decode (PD) disaggregation in LLM serving improves resource utilization but struggles with the bursty nature of modern workloads. Existing autoscaling policies, often retrofitted from monolithic systems…

While diffusion language models (DLMs) enable fine-grained refinement, their practical controllability remains fragile. We identify and formally characterize a central failure mode called update forgetting, in which uniform and context…

This research aims to accelerate the inference speed of large language models (LLMs) with billions of parameters. We propose \textbf{S}mart \textbf{P}arallel \textbf{A}uto-\textbf{C}orrect d\textbf{E}coding (SPACE), an innovative approach…

Efficient parallelization of Large Language Models (LLMs) with long sequences is essential but challenging due to their significant computational and memory demands, particularly stemming from communication bottlenecks in attention…

This work reframes the Text-to-SQL task as a pathway for teaching large language models (LLMs) to reason over and manipulate tabular data--moving beyond the traditional focus on query generation. We propose a two-stage framework that…