Related papers: Cascade-Aware Training of Language Models

Prompting and in-context learning (ICL) have become efficient learning paradigms for large language models (LLMs). However, LLMs suffer from prompt brittleness and various bias factors in the prompt, including but not limited to the…

Large language models (LLMs) have enhanced our ability to rapidly analyze and classify unstructured natural language data. However, concerns regarding cost, network limitations, and security constraints have posed challenges for their…

Currently, large language models (LLMs) predominantly focus on the text modality. To enable more natural human-AI interaction, speech LLMs are emerging, but building effective end-to-end speech LLMs remains challenging due to limited data…

Despite the significant improvements achieved by large language models (LLMs) in English reasoning tasks, these models continue to struggle with multilingual reasoning. Recent studies leverage a full-parameter and two-stage training…

Effective content moderation is essential for video platforms to safeguard user experience and uphold community standards. While traditional video classification models effectively handle well-defined moderation tasks, they struggle with…

Several previous works concluded that the largest part of generation capabilities of large language models (LLM) are learned (early) during pre-training. However, LLMs still require further alignment to adhere to downstream task…

A cascaded speech translation model relies on discrete and non-differentiable transcription, which provides a supervision signal from the source side and helps the transformation between source speech and target text. Such modeling suffers…

Recent progress in Language Models (LMs) has dramatically advanced the field of natural language processing (NLP), excelling at tasks like text generation, summarization, and question answering. However, their inference remains…

The modeling of cascade processes in multi-agent systems in the form of complex networks has in recent years become an important topic of study due to its many applications: the adoption of commercial products, spread of disease, the…

Machine-learning classifiers provide high quality of service in classification tasks. Research now targets cost reduction measured in terms of average processing time or energy per solution. Revisiting the concept of cascaded classifiers,…

Sparsity-aware training is an effective approach for transforming large language models (LLMs) into hardware-friendly sparse patterns, thereby reducing latency and memory consumption during inference. In this paper, we propose Continuous…

In-context learning (ICL) with dynamically selected demonstrations combines the flexibility of prompting large language models (LLMs) with the ability to leverage training data to improve performance. While ICL has been highly successful…

Self-supervised learning (SSL) is able to build latent representations that generalize well to unseen data. However, only a few SSL techniques exist for the online CL setting, where data arrives in small minibatches, the model must comply…

Effective communication protocols in multi-agent reinforcement learning (MARL) are critical to fostering cooperation and enhancing team performance. To leverage communication, many previous works have proposed to compress local information…

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) and other large foundation models have achieved noteworthy success, but their size exacerbates existing resource consumption and latency challenges. In particular, the large-scale deployment of these models is…

Large Language Models (LLMs) are revolutionizing industries by enhancing efficiency, scalability, and innovation. This paper investigates the potential of LLMs in automating Computer-Aided Design (CAD) workflows, by integrating FreeCAD with…

Cascades and speculative decoding are two common approaches to improving language models' inference efficiency. Both approaches involve interleaving models of different sizes, but via fundamentally distinct mechanisms: cascades employ a…

Time series anomaly detection is critical for supply chain management to take proactive operations, but faces challenges: classical unsupervised anomaly detection based on exploiting data patterns often yields results misaligned with…

Large Language Models (LLMs) need to be aligned with human expectations to ensure their safety and utility in most applications. Alignment is challenging, costly, and needs to be repeated for every LLM and alignment criterion. We propose to…