Related papers: SR-KI: Scalable and Real-Time Knowledge Integratio…

Recent large language models (LLMs) with enormous model sizes use many GPUs to meet memory capacity requirements incurring substantial costs for token generation. To provide cost-effective LLM inference with relaxed latency constraints,…

Continual learning (CL) is crucial for language models to dynamically adapt to the evolving real-world demands. To mitigate the catastrophic forgetting problem in CL, data replay has been proven a simple and effective strategy, and the…

Recent studies have demonstrated the effectiveness of LLM test-time scaling. However, existing approaches to incentivize LLMs' deep thinking abilities generally require large-scale data or significant training efforts. Meanwhile, it remains…

Relational knowledge bases (KBs) are commonly used to represent world knowledge in machines. However, while advantageous for their high degree of precision and interpretability, KBs are usually organized according to manually-defined…

Despite the impressive performance of large language models (LLMs) pretrained on vast knowledge corpora, advancing their knowledge manipulation-the ability to effectively recall, reason, and transfer relevant knowledge-remains challenging.…

Inference for Large Language Models (LLMs) is computationally demanding. To reduce the cost of auto-regressive decoding, Key-Value (KV) cache is used to store intermediate activations, which significantly lowers the computational overhead…

Large language models (LLMs) are omnipresent, however their practical deployment is challenging due to their ever increasing computational and memory demands. Quantization is one of the most effective ways to make them more compute and…

Large language models (LLMs) have shown remarkable promise but remain challenging to continually improve through traditional finetuning, particularly when integrating capabilities from other specialized LLMs. Popular methods like ensemble…

Language models (LMs) have shown great potential as implicit knowledge bases (KBs). And for their practical use, knowledge in LMs need to be updated periodically. However, existing tasks to assess LMs' efficacy as KBs do not adequately…

We propose knowledge internalization (KI), which aims to complement the lexical knowledge into neural dialog models. Instead of further conditioning the knowledge-grounded dialog (KGD) models on externally retrieved knowledge, we seek to…

We introduce SIRI, Scaling Iterative Reinforcement Learning with Interleaved Compression, a simple yet effective RL approach for Large Reasoning Models (LRMs) that enables more efficient and accurate reasoning. Existing studies have…

This paper focuses on how to take advantage of external knowledge bases (KBs) to improve recurrent neural networks for machine reading. Traditional methods that exploit knowledge from KBs encode knowledge as discrete indicator features. Not…

The linear growth of key-value (KV) cache memory and quadratic computational in attention mechanisms complexity pose significant bottlenecks for large language models (LLMs) in long-context processing. While existing KV cache optimization…

Knowledge retrieval with multi-modal queries plays a crucial role in supporting knowledge-intensive multi-modal applications. However, existing methods face challenges in terms of their effectiveness and training efficiency, especially when…

Huge memory consumption has been a major bottleneck for deploying high-throughput large language models in real-world applications. In addition to the large number of parameters, the key-value (KV) cache for the attention mechanism in the…

Large language models face significant computational and memory challenges when processing long contexts. During inference, efficient management of the key-value (KV) cache, which stores intermediate activations for autoregressive…

Optimizing the Key-Value (KV) cache of the Large Language Model (LLM) has been considered critical to saving the cost of inference. Most of the existing KV-cache compression algorithms attempted to sparsify the sequence of tokens by taking…

Reducing the key-value (KV) cache size is a crucial step toward enabling efficient inference in large language models (LLMs), especially under latency and memory constraints. While Multi-Head Attention (MHA) offers strong representational…

Long-context Large Language Models (LLMs) enable powerful applications but incur high memory costs due to the key-value states (KV-Cache). Recent studies attempt to share KV-Cache across layers, but these approaches either require expensive…

Although large language models (LLMs) have made significant progress in understanding Structured Knowledge (SK) like KG and Table, existing evaluations for SK understanding are non-rigorous (i.e., lacking evaluations of specific…