相关论文: The Single-Multi Evolution Loop for Self-Improving…

Knowledge distillation from large language models (LLMs) assumes that the teacher's output distribution is a high-quality training signal. On reasoning tasks, this assumption is frequently violated. A model's intermediate representations…

Learning based on multimodal data has attracted increasing interest recently. While a variety of sensory modalities can be collected for training, not all of them are always available in development scenarios, which raises the challenge to…

Integrating Large Language Models (LLMs) and Evolutionary Computation (EC) represents a promising avenue for advancing artificial intelligence by combining powerful natural language understanding with optimization and search capabilities.…

Today's pursuit of a single Large Language Model (LMM) for all software engineering tasks is resource-intensive and overlooks the potential benefits of complementarity, where different models contribute unique strengths. However, the degree…

Large language models (LLMs) have shown promising self-correction abilities, where iterative refinement improves the quality of generated responses. However, most existing approaches operate at the level of output critique, patching surface…

We present DistillFlow, a knowledge distillation approach to learning optical flow. DistillFlow trains multiple teacher models and a student model, where challenging transformations are applied to the input of the student model to generate…

Diffusion Models~(DMs) have emerged as the dominant approach in Generative Artificial Intelligence (GenAI), owing to their remarkable performance in tasks such as text-to-image synthesis. However, practical DMs, such as stable diffusion,…

As autonomous agents powered by LLM are increasingly deployed in society, understanding their collective behaviour in social dilemmas becomes critical. We introduce an evaluation framework where LLMs generate strategies encoded as…

Despite substantial progress in multilingual extractive Question Answering (QA), models with high and uniformly distributed performance across languages remain challenging, especially for languages with limited resources. We study…

Low-resource languages (LRLs) lack sufficient linguistic resources and are underrepresented in benchmark datasets, resulting in persistently lower translation quality than high-resource languages, especially in privacy-sensitive and…

As Natural Language Processing (NLP) systems are increasingly employed in intricate social environments, a pressing query emerges: Can these NLP systems mirror human-esque collaborative intelligence, in a multi-agent society consisting of…

Model merging combines multiple fine-tuned checkpoints into a single model without additional training, offering an attractive approach to reusing models and efficiently improving performance. However, it remains unclear whether the…

With the rapid development of storage and computing power on mobile devices, it becomes critical and popular to deploy models on devices to save onerous communication latencies and to capture real-time features. While quite a lot of works…

Alignment has greatly improved large language models (LLMs)' output quality at the cost of diversity, yielding highly similar outputs across generations. We propose Base-Aligned Model Collaboration (BACo), an inference-time token-level…

Large Language Models (LLMs) have demonstrated remarkable performance across a wide range of natural language processing tasks. However, their enormous parameter size and extremely high requirements for compute power pose challenges for…

We present a framework for robot skill acquisition, which 1) efficiently scale up data generation of language-labelled robot data and 2) effectively distills this data down into a robust multi-task language-conditioned visuo-motor policy.…

Large language models (LLMs), despite their ability to perform few-shot machine translation (MT), often lag behind dedicated MT systems trained on parallel corpora, which are crucial for high quality machine translation (MT). However,…

Machine learning (ML) is increasingly vital for smart-grid research, yet restricted access to realistic, diverse data - often due to privacy concerns - slows progress and fuels doubts within the energy sector about adopting ML-based…

Optimizing large-scale machine learning systems, such as recommendation models for global video platforms, requires navigating a massive hyperparameter search space and, more critically, designing sophisticated optimizers, architectures,…

Model distillation is an effective and widely used technique to transfer knowledge from a teacher to a student network. The typical application is to transfer from a powerful large network or ensemble to a small network, that is better…