Related papers: Semantic Density Effect (SDE): Maximizing Informat…

Speculative decoding emerges as a pivotal technique for enhancing the inference speed of Large Language Models (LLMs). Despite recent research aiming to improve prediction efficiency, multi-sample speculative decoding has been overlooked…

Information extraction(IE) is a crucial subfield within natural language processing. However, for the traditionally segmented approach to sentence classification and Named Entity Recognition, the intricate interactions between these…

Long-context inference for Large Language Models (LLMs) is heavily limited by high computational demands. While several existing methods optimize attention computation, they still process the full set of hidden states at each layer,…

Large language models (LLMs) are increasingly integrated into users' daily lives, leading to a growing demand for personalized outputs. Previous work focuses on leveraging a user's own history, overlooking inter-user differences that are…

Effective training of today's large language models (LLMs) depends on large batches and long sequences for throughput and accuracy. To handle variable-length sequences on hardware accelerators, it is common practice to introduce padding…

Large language models (LLMs) have shown impressive capabilities in real-world applications. The capability of in-context learning (ICL) allows us to adapt an LLM to downstream tasks by including input-label exemplars in the prompt without…

While large language models (LLMs) have rapidly improved their performance on a broad number of tasks, they still often fall short on reasoning tasks. As LLMs become more integrated in diverse real-world tasks, advancing their reasoning…

Reinforcement learning (RL) has become an effective way to improve prompt alignment and perceptual quality in diffusion and flow-matching generators. A critical step for applying online RL to flow matching is turning the deterministic…

The shift from cloud-hosted Large Language Models (LLMs) to locally deployed open-source Small Language Models (SLMs) has democratized AI-assisted coding; however, it has also decentralized the environmental footprint of AI. While prompting…

The field of prompt engineering is becoming an essential phenomenon in artificial intelligence. It is altering how data scientists interact with large language models (LLMs) for analytics applications. This research paper shares empirical…

The SPLADE (SParse Lexical AnD Expansion) model is a highly effective approach to learned sparse retrieval, where documents are represented by term impact scores derived from large language models. During training, SPLADE applies…

In recent years, the rise of Large Language Models (LLMs) has spurred a growing demand for plug-and-play AI systems. Among the various AI techniques, prompt engineering stands out as particularly significant. However, users often face…

Explicit chain-of-thought (CoT) reasoning substantially improves the reasoning ability of large language models (LLMs), but incurs high inference cost due to lengthy autoregressive traces. Existing latent reasoning methods offer a promising…

The quadratic complexity of attention imposes severe memory and computational bottlenecks on Large Language Model (LLM) inference. This challenge is particularly acute for emerging agentic applications that require processing multi-million…

AI-Integrated programming is emerging as a foundational paradigm for building intelligent systems with large language models (LLMs). Recent approaches such as Meaning Typed Programming (MTP) automate prompt generation by leveraging the…

Multi-agent techniques such as role playing or multi-turn debates have been shown to be effective in improving the performance of large language models (LLMs) in downstream tasks. Despite their differences in workflows, existing multi-agent…

Large language models (LLMs) can be seen as atomic units of computation mapping sequences to a distribution over sequences. Thus, they can be seen as stochastic language layers in a language network, where the learnable parameters are the…

As Large Language Models (LLMs) can now process extremely long contexts, efficient inference over these extended inputs has become increasingly important, especially for emerging applications like LLM agents that highly depend on this…

Well-designed prompts are crucial for enhancing Large language models' (LLMs) reasoning capabilities while aligning their outputs with task requirements across diverse domains. However, manually designed prompts require expertise and…

Large Language Models are transforming software engineering, yet prompt management in practice remains ad hoc, hindering reliability, reuse, and integration into industrial workflows. We present Prompt-with-Me, a practical solution for…