16 accepted papers
As an essential component of fine-tuning, warm-up plays a crucial role in promoting stability and generalization. Many studies have examined its underlying mechanisms from different aspects. However, most of the studies focus on incorporating these insights into optimizers to reduce the reliance on
The key-value (KV) cache plays a vital role in accelerating autoregressive inference for large language models (LLMs). However, its linear memory growth with sequence length poses significant memory bottlenecks, especially in long-context scenarios. Quantization offers a promising solution for memor…
While low-rank decomposition offers potential for LLM size reduction, its application is limited by considerable performance degradation. In this work, we identify and formalize a key overlooked issue in LLM decomposition: \textit{representation drift}. We show that approximation errors introduced b…
Mixture-of-Experts (MoE) architectures have demonstrated remarkable capabilities and scalability for large language models, but incur a prohibitive memory footprint due to duplicated expert parameters. Existing compression approaches, particularly those based on low-rank decomposition, typically ope…
Optimizers are critical for training deep neural networks. Existing training processes rely on a single static optimizer (e.g., SGD) or a simple hybrid of two optimizers, which miss the opportunity to exploit evolving dynamics in different training states, degrading model quality and convergence. In…
Tuning inference hyperparameters, such as temperature and maximum output tokens, on downstream tasks can enhance inference performance. However, directly applying hyperparameter optimization to these hyperparameters is token-expensive. Multi-fidelity optimization improves HPO efficiency with low-fid
The increasing demand for efficient summarization tools in resource-constrained environments highlights the need for effective solutions. While large language models (LLMs) deliver superior summarization quality, their high computational resource requirements limit practical use applications. In con…
Conventional Multi-modal multi-label emotion recognition (MMER) assumes complete access to visual, textual, and acoustic modalities. However, real-world multi-party settings often violate this assumption, as non-speakers frequently lack acoustic and textual inputs, leading to a significant degradati
In long structured document retrieval, existing methods typically fine-tune pre-trained language models (PLMs) using contrastive learning on datasets lacking explicit structural information. This practice suffers from two critical issues: 1) current methods fail to leverage structural features and e
Large language models (LLMs) have demonstrated impressive capabilities across various tasks, but the billion-scale parameters pose deployment challenges. Although existing methods attempt to reduce the scale of LLMs, they require either special hardware support or expensive post-training to maintain…
As the size of language models notably grows, fine-tuning the models becomes more challenging: fine-tuning with first-order optimizers (e.g., SGD and Adam) requires high memory consumption, while fine-tuning with a memory-efficient zeroth-order optimizer (MeZO) has a significant accuracy drop and sl…
Hyperparameter Optimization and Neural Architecture Search are powerful in attaining state-of-the-art machine learning models with Bayesian Optimization (BO) standing out as a mainstream method. Extending BO into the multi-fidelity setting has been an emerging research topic in this field but faces…
Aspect-term sentiment analysis (ATSA) identifies fine-grained sentiments towards specific aspects of the text. While pre-trained language models (PLMs) have set the state-of-the-art (SOTA) for ATSA, they are resource-intensive due to their large model sizes, restricting their wide applications to re…
Path attribution methods are a popular tool to interpret a visual model's prediction on an input. They integrate model gradients for the input features over a path defined between the input and a reference, thereby satisfying certain desirable theoretical properties. However, their reliability hinge…
The ability to interpret machine learning models is critical for high-stakes applications. Due to its desirable theoretical properties, path integration is a widely used scheme for feature attribution to interpret model predictions. However, the methods implementing this scheme currently rely on abs…
In the last few years, Gradient Boosting Decision Trees (GBDTs) have been widely used in various applications such as online advertising and spam filtering. However, GBDT training is often a key performance bottleneck for such data science pipelines, especially for training a large number of deep tr…