Related papers: Pair-In, Pair-Out: Latent Multi-Token Prediction f…

Speculative decoding accelerates large language model (LLM) inference by using a small draft model to generate candidate tokens for a larger target model to verify. The efficacy of this technique hinges on the trade-off between the time…

Chain-of-thought (CoT) reasoning improves large language models (LLMs) on difficult tasks, but it also makes inference expensive because every intermediate step must be generated as a discrete token. Latent reasoning reduces visible token…

Model fusion combines multiple Large Language Models (LLMs) with different strengths into a more powerful, integrated model through lightweight training methods. Existing works on model fusion focus primarily on supervised fine-tuning…

Speculative decoding is a pivotal technique to accelerate the inference of large language models (LLMs) by employing a smaller draft model to predict the target model's outputs. However, its efficacy can be limited due to the low predictive…

Speculative decoding has demonstrated its effectiveness in accelerating the inference of large language models while maintaining a consistent sampling distribution. However, the conventional approach of training a separate draft model to…

Diffusion Large Language Models (DLLMs) promise fast parallel generation, yet open-source DLLMs still face a severe quality-speed trade-off: accelerating decoding by revealing multiple tokens often causes substantial quality degradation. We…

Direct Preference Optimization (DPO) has been widely adopted for preference alignment of Large Language Models (LLMs) due to its simplicity and effectiveness. However, DPO is derived as a bandit problem in which the whole response is…

As large language models (LLMs) are increasingly used as evaluators for natural language generation tasks, ensuring unbiased assessments is essential. However, LLM evaluators often display biased preferences, such as favoring verbosity and…

Large language model (LLM) inference at the network edge is a promising serving paradigm that leverages distributed edge resources to run inference near users and enhance privacy. Existing edge-based LLM inference systems typically adopt…

When the quality of naive prompts is carefully optimized by human experts, the task performance of large language models (LLMs) can be significantly improved. However, expert-based prompt optimizations are expensive. Herein, some works have…

Recent advancements in Large Language Models (LLMs) have shifted from explicit Chain-of-Thought (CoT) reasoning to more efficient latent reasoning, where intermediate thoughts are represented as vectors rather than text. However, latent…

Multi-token prediction (MTP) is a recently proposed pre-training objective for language models. Rather than predicting only the next token (NTP), MTP predicts the next $k$ tokens at each prediction step, using multiple prediction heads. MTP…

The growing gap between the increasing complexity of large language models (LLMs) and the limited computational budgets of edge devices poses a key challenge for efficient on-device inference, despite gradual improvements in hardware…

To mitigate the high inference latency stemming from autoregressive decoding in Large Language Models (LLMs), Speculative Decoding has emerged as a novel decoding paradigm for LLM inference. In each decoding step, this method first drafts…

Many open-ended instructions have multiple valid answers that users can benefit from seeing, but post-training often narrows an LLM's output space toward a small set of canonical responses. We introduce REDIPO, an offline DPO…

Large language models (LLMs) achieve strong performance across a wide range of tasks but are highly sensitive to prompt design, motivating the need for automatic prompt optimization. Existing methods predominantly focus on performance…

Optimizing large language models (LLMs) for multi-turn conversational outcomes remains a significant challenge, especially in goal-oriented settings like AI marketing or sales agents who facilitate transactions via messaging platforms. The…

Large language models have achieved remarkable capabilities, but their practical deployment is hindered by significant computational costs. While adaptive computation methods like early-exiting promise to reduce these costs, they introduce…

Large language models have transformed many applications but remain expensive to train. Sparse Mixture of Experts (MoE) addresses this through conditional computation, with Expert Parallel (EP) as the standard distributed training method.…

Speculative decoding accelerates inference in large language models (LLMs) by generating multiple draft tokens simultaneously. However, existing methods often struggle with token misalignment between the training and decoding phases,…