Related papers: Scaling Embeddings Outperforms Scaling Experts in …

The generation quality of large language models (LLMs) is often improved by utilizing inference-time sequence-level scaling methods (e.g., Chain-of-Thought). We introduce hyper-parallel scaling, a complementary framework that improves…

Mixture-of-Experts (MoE) models promise efficient scaling of large language models (LLMs) by activating only a small subset of experts per token, but their parallelized inference pipelines make elastic serving challenging. Existing…

We present MoE-MLA-RoPE, a novel architecture combination that combines Mixture of Experts (MoE) with Multi-head Latent Attention (MLA) and Rotary Position Embeddings (RoPE) for efficient language modeling. Our approach addresses the…

Large language models (LLMs) have demonstrated exceptional proficiency in understanding and generating human language, but efficient inference on resource-constrained embedded devices remains challenging due to large model sizes and…

Aligning large language models (LLMs) to simultaneously satisfy multiple objectives remains a significant challenge, especially given the diverse and often conflicting nature of human preferences. Existing alignment methods struggle to…

We introduce the Byte Latent Transformer (BLT), a new byte-level LLM architecture that, for the first time, matches tokenization-based LLM performance at scale with significant improvements in inference efficiency and robustness. BLT…

Despite their remarkable achievement, gigantic transformers encounter significant drawbacks, including exorbitant computational and memory footprints during training, as well as severe collapse evidenced by a high degree of parameter…

Deep model training on extensive datasets is increasingly becoming cost-prohibitive, prompting the widespread adoption of deep model fusion techniques to leverage knowledge from pre-existing models. From simple weight averaging to more…

Most recent state-of-the-art (SOTA) large language models (LLMs) use Mixture-of-Experts (MoE) architectures to scale model capacity without proportional per-token compute, enabling higher-quality outputs at manageable serving costs.…

Mixture-of-Experts (MoE) shines brightly in large language models (LLMs) and demonstrates outstanding performance in plentiful natural language processing tasks. However, existing methods transforming LLMs from dense to MoE face significant…

The Mixture of Experts (MoE) architecture is an important method for scaling Large Language Models (LLMs). It increases model capacity while keeping computation cost low. However, the ultra-large MoE models still have hundreds of billions…

Mixture-of-Experts (MoE) is now the dominant architecture for frontier language models, yet it requires all expert parameters to be loaded in memory, making it less preferable for memory-constrained deployment. Existing compression methods…

Large language models (LLMs) deliver impressive performance but incur prohibitive memory and compute costs at deployment. Model pruning is an effective way to reduce these overheads, yet existing approaches face challenges: unstructured…

Mixture-of-Experts (MoE) has gained increasing popularity as a promising framework for scaling up large language models (LLMs). However, the reliability assessment of MoE lags behind its surging applications. Moreover, when transferred to…

Large language models (LLMs) have achieved great success in medical question answering and clinical decision-making, promoting the efficiency and popularization of the personalized virtual doctor in society. However, the traditional…

Sparse attention offers a promising strategy to extend long-context capabilities in Transformer LLMs, yet its efficiency-accuracy trade-offs remain unclear due to the lack of comprehensive evaluation. We address this gap with the…

The Mixture of Experts (MoE) paradigm provides a powerful way to decompose dense layers into smaller, modular computations often more amenable to human interpretation, debugging, and editability. However, a major challenge lies in the…

Embedding models play a pivot role in modern NLP applications such as IR and RAG. While the context limit of LLMs has been pushed beyond 1 million tokens, embedding models are still confined to a narrow context window not exceeding 8k…

We propose $SCONE$ ($S$calable, $C$ontextualized, $O$ffloaded, $N$-gram $E$mbedding), a new method for extending input embedding layers to enhance language model performance. To avoid increased decoding costs, $SCONE$ retains the original…

Parameter Efficient Finetuning (PEFT) has emerged as a viable solution for improving the performance of Large Language Models (LLMs) without requiring massive resources and compute. Prior work on multilingual evaluation has shown that there…