Related papers: Generation Meets Verification: Accelerating Large …

Transformer language models generate text autoregressively, making inference latency proportional to the number of tokens generated. Speculative decoding reduces this latency without sacrificing output quality, by leveraging a small draft…

Speech language models (Speech LMs) enable end-to-end speech-text modeling within a single model, offering a promising direction for spoken dialogue systems. The choice of speech-text jointly decoding paradigm plays a critical role in…

In edge-cloud speculative decoding (SD), edge devices equipped with small language models (SLMs) generate draft tokens that are verified by large language models (LLMs) in the cloud. A key bottleneck in such systems is the limited…

While large language models (LLMs) have demonstrated remarkable performance across diverse tasks, they fundamentally lack self-awareness and frequently exhibit overconfidence, assigning high confidence scores to incorrect predictions.…

Diffusion large language models (dLLMs) have recently gained significant attention due to their inherent support for parallel decoding. Building on this paradigm, Mixture-of-Experts (MoE) dLLMs with autoregressive (AR) initialization have…

Large Language Models (LLMs) have achieved remarkable performance across a wide variety of natural language tasks; however, their large size makes their inference slow and computationally expensive. Focusing on this problem, we propose to…

Large language models (LLMs) have achieved remarkable performance across a wide range of tasks, but their increasing parameter sizes significantly slow down inference. Speculative decoding mitigates this issue by leveraging a smaller draft…

Some text generation tasks, such as Attribute Value Extraction (AVE), require decoding multiple independent sequences from the same document context. While standard autoregressive decoding is slow due to its sequential nature, the…

Autoregressive (AR) generation is the standard decoding paradigm for Large Language Models (LLMs), but its token-by-token nature limits parallelism at inference time. Diffusion Language Models (DLLMs) offer parallel decoding by recovering…

Large language models (LLMs) are increasingly used to generate software artifacts across many software engineering (SE) tasks, yet ensuring the semantic validity of these artifacts remains a fundamental challenge. Existing constrained…

Large language models (LLMs) often struggle with context fidelity, producing inconsistent answers when responding to questions based on provided information. Existing approaches either rely on expensive supervised fine-tuning to generate…

Retrieval-augmented generation (RAG) frameworks enable large language models (LLMs) to retrieve relevant information from a knowledge base and incorporate it into the context for generating responses. This mitigates hallucinations and…

Large Language Models (LLMs) demonstrate remarkable emergent abilities across various tasks, yet fall short of complex reasoning and planning tasks. The tree-search-based reasoning methods address this by surpassing the capabilities of…

Large language models (LLMs) deliver impressive generation quality, but incur very high inference cost because each output token is generated auto-regressively through all model layers. Early-exit based self-speculative decoding (EESD) has…

Speculative decoding is an effective technique for accelerating large language model inference by drafting multiple tokens in parallel. In practice, its speedup is often bottlenecked by a rigid verification step that strictly enforces the…

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…

Recent advancements in Large Language Models (LLMs) have shown remarkable performance across a wide range of tasks. Despite this, the auto-regressive nature of LLM decoding, which generates only a single token per forward propagation, fails…

Large language models (LLMs) have shown strong reasoning capabilities when fine-tuned with reinforcement learning (RL). However, such methods require extensive data and compute, making them impractical under many realistic training budgets.…

Large reasoning models (LRMs) excel on complex problems but face a critical barrier to efficiency: reinforcement learning (RL) training requires long rollouts for outcome-based rewards, where autoregressive decoding dominates time and…

In this work, we propose FastCoT, a model-agnostic framework based on parallel decoding without any further training of an auxiliary model or modification to the LLM itself. FastCoT uses a size-varying context window whose size changes with…