相关论文: Sparse Activation Editing for Reliable Instruction…

Advances in machine reading comprehension (MRC) rely heavily on the collection of large scale human-annotated examples in the form of (question, paragraph, answer) triples. In contrast, humans are typically able to generalize with only a…

The rapid evolution of Large Language Models (LLMs) has enabled the industry to develop various AI-based services. Instruction tuning is considered essential in adapting foundation models for target domains to provide high-quality services…

Reliable control of myoelectric prostheses is often hindered by high inter-subject variability and the clinical impracticality of high-density sensor arrays. This study proposes a deep learning framework for accurate gesture recognition…

Language-Guided object recognition in remote sensing imagery is crucial for large-scale mapping and automated data annotation. However, existing open-vocabulary and visual grounding methods rely on explicit category cues, limiting their…

Sparse autoencoders (SAEs) improve interpretability in multimodal models, but it remains unclear whether SAE features form modular, composable units for reasoning-an assumption underlying many intervention-based steering methods. We test…

We propose a learning approach for mapping context-dependent sequential instructions to actions. We address the problem of discourse and state dependencies with an attention-based model that considers both the history of the interaction and…

Transformer-based Language Models have become ubiquitous in Natural Language Processing (NLP) due to their impressive performance on various tasks. However, expensive training as well as inference remains a significant impediment to their…

Obtaining versions of deep neural networks that are both highly-accurate and highly-sparse is one of the main challenges in the area of model compression, and several high-performance pruning techniques have been investigated by the…

Recent LLMs have shown remarkable success in following user instructions, yet handling instructions with multiple constraints remains a significant challenge. In this work, we introduce WildIFEval - a large-scale dataset of 7K real user…

In modern speech synthesis, paralinguistic information--such as a speaker's vocal timbre, emotional state, and dynamic prosody--plays a critical role in conveying nuance beyond mere semantics. Traditional Text-to-Speech (TTS) systems rely…

Sparse autoencoders (SAEs) have emerged as a powerful tool for interpreting neural networks by extracting the concepts represented in their activations. However, choosing the size of the SAE dictionary (i.e. number of learned concepts)…

To teach robots complex manipulation tasks, a common approach is to fine-tune a pre-trained vision-language-action model (VLA) on task-specific data. However, since this recipe updates existing representations, it is unsuitable for…

Self-attention based Transformer has demonstrated the state-of-the-art performances in a number of natural language processing tasks. Self-attention is able to model long-term dependencies, but it may suffer from the extraction of…

Traditional language models, adept at next-token prediction in text sequences, often struggle with transduction tasks between distinct symbolic systems, particularly when parallel data is scarce. Addressing this issue, we introduce…

Sequential learning, also called lifelong learning, studies the problem of learning tasks in a sequence with access restricted to only the data of the current task. In this paper we look at a scenario with fixed model capacity, and…

Sparse Autoencoders (SAEs) are a promising approach for extracting neural network representations by learning a sparse and overcomplete decomposition of the network's internal activations. However, SAEs are traditionally trained considering…

Following multiple instructions is a crucial ability for large language models (LLMs). Evaluating this ability comes with significant challenges: (i) limited coherence between multiple instructions, (ii) positional bias where the order of…

Artificial intelligence in healthcare requires models that are accurate and interpretable. We advance mechanistic interpretability in medical vision by applying Medical Sparse Autoencoders (MedSAEs) to the latent space of MedCLIP, a…

Lifelong learning requires models that can continuously learn from sequential streams of data without suffering catastrophic forgetting due to shifts in data distributions. Deep learning models have thrived in the non-sequential learning…

Instruction-tuned large language models have shown remarkable performance in aligning generated text with user intentions across various tasks. However, maintaining human-like discourse structure in the generated text remains a challenging…