相关论文: Achieving Sparse Activation in Small Language Mode…

Small language models (SLMs), despite their widespread adoption in modern smart devices, have received significantly less academic attention compared to their large language model (LLM) counterparts, which are predominantly deployed in data…

Fine-tuning LLMs is both computationally and memory-intensive. While parameter-efficient fine-tuning methods, such as QLoRA and DoRA, reduce the number of trainable parameters and lower memory usage, they do not decrease computational cost.…

A central goal for mechanistic interpretability has been to identify the right units of analysis in large language models (LLMs) that causally explain their outputs. While early work focused on individual neurons, evidence that neurons…

Being prompted to engage in reasoning has emerged as a core technique for using large language models (LLMs), deploying additional inference-time compute to improve task performance. However, as LLMs increase in both size and adoption,…

Recent studies show that LLM hidden states encode reward-related information, such as answer correctness and model confidence. However, existing approaches typically fit black-box probes on the full hidden states, offering little insight…

Model pruning technique is vital for accelerating large language models by reducing their size and computational requirements. However, the generalizability of existing pruning methods across diverse datasets and tasks remains unclear.…

Large Language Models (LLMs) have achieved remarkable performance by capturing complex interactions between input features. To identify these interactions, most existing approaches require enumerating all possible combinations of features…

Large Language Models (LLMs) demonstrate exceptional reasoning abilities, enabling strong generalization across diverse tasks such as commonsense reasoning and instruction following. However, as LLMs scale, inference costs become…

Large language models (LLMs) excel at diverse tasks, but their deployment on resource-constrained devices remains challenging. Existing methods like quantization, pruning, and distillation can reduce memory footprint but often demand…

As large language models (LLMs) are increasingly deployed across various applications, privacy and copyright concerns have heightened the need for more effective LLM unlearning techniques. Many existing unlearning methods aim to suppress…

While diffusion language models (DLMs) offer a promising alternative to autoregressive models (ARs), existing open-source DLMs suffer from high inference latency. This bottleneck is mainly due to the attention's quadratic complexity with…

Evaluating the importance of different layers in large language models (LLMs) is crucial for optimizing model performance and interpretability. This paper first explores layer importance using the Activation Variance-Sparsity Score (AVSS),…

Sparsity has long been a central theme in LLM efficiency, but its role in context processing remains unresolved. As LLM workloads shift toward longer contexts and agentic interactions, the compute and memory bottlenecks of attention become…

Large language models possess strong chemical reasoning capabilities, making them effective molecular editors. However, property-relevant information is implicitly entangled across their dense hidden states, providing no explicit handle for…

Large Language Models (LLMs) have become pivotal in advancing the field of artificial intelligence, yet their immense sizes pose significant challenges for both fine-tuning and deployment. Current post-training pruning methods, while…

As large language models (LLMs) continue to advance, their capacity to function effectively across a diverse range of languages has shown marked improvement. Preliminary studies observe that the hidden activations of LLMs often resemble…

Training neural network models with discrete (categorical or structured) latent variables can be computationally challenging, due to the need for marginalization over large or combinatorial sets. To circumvent this issue, one typically…

Communication between multiple language model (LM) agents has been shown to scale up the reasoning ability of LMs. While natural language has been the dominant medium for inter-LM communication, it is not obvious this should be the…

Recent advances show that large language models (LLMs) generalize strong performance across different natural language benchmarks. However, the large size of LLMs makes training and inference expensive and impractical to run in…

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…