16 accepted papers
Activation steering has emerged as a cost-effective paradigm for modifying large language model (LLM) behaviors. Existing methods typically intervene at the block level, steering the bundled activations of selected attention heads, feedforward networks, or residual streams. However, we reveal that b…
Depth completion, the task of reconstructing dense depth maps from sparse depth and RGB images, plays a critical role in 3D scene understanding. However, existing methods often struggle to recover high-frequency details, such as regions with fine structures or weak signals, since depth sensors may f…
Effective organization of in-context learning (ICL) demonstrations is key to improving the quality of large language model (LLM) responses. To create better sample-label pairs that instruct LLM understanding, we introduce logit separability, a criterion to assess the clarity of both samples and clas…
Pruning is a widely used technique to reduce the size and inference cost of large language models (LLMs), but it often causes performance degradation. To mitigate this, existing restoration methods typically employ parameter-efficient fine-tuning (PEFT), such as LoRA, to recover the pruned model's p…
Few-shot text classification has seen significant advancements, particularly with entailment-based methods, which typically use either class labels or intensional definitions of class labels in hypotheses for label semantics expression. In this paper, we propose EDEntail, a method that employs exten…
Controllable text generation (CTG) seeks to craft texts adhering to specific attributes, traditionally employing learning-based techniques such as training, fine-tuning, or prefix-tuning with attribute-specific datasets. These approaches, while effective, demand extensive computational and data reso…
Self-supervised depth estimation has evolved into an image reconstruction task that minimizes a photometric loss. While recent methods have made strides in indoor depth estimation, they often produce inconsistent depth estimation in textureless areas and unsatisfactory depth discrepancies at object…
In this study, we explore in-context learning (ICL) in document-level event argument extraction (EAE) to alleviate the dependency on large-scale labeled data for this task. We introduce the Heuristic-Driven Link-of-Analogy (HD-LoA) prompting tailored for the EAE task. Specifically, we hypothesize an…
Unsupervised domain adaptation methods have demonstrated superior capabilities in handling the domain shift issue which widely exists in various time series tasks. However, their prominent adaptation performances heavily rely on complex model architectures, posing an unprecedented challenge in deplo…
Large language models (LLMs) have demonstrated impressive capabilities in various tasks using the in-context learning (ICL) paradigm. However, their effectiveness is often compromised by inherent bias, leading to prompt brittleness—sensitivity to design settings such as example selection, order, and…
Prompts play a crucial role in guiding the responses of Large Language Models (LLMs). However, the intricate role of individual tokens in prompts, known as input saliency, in shaping the responses remains largely underexplored. Existing saliency methods either misalign with LLM generation objectives…
The Universum class, often known as the *other* class or the*miscellaneous* class, is defined as a collection of samples that do not belong to any class of interest. It is a typical class that exists in many classification-based tasks in NLP, such as relation extraction, named entity recognition, se…
For many real-world time series tasks, the computational complexity of prevalent deep leaning models often hinders the deployment on resource limited environments (e.g., smartphones). Moreover, due to the inevitable domain shift between model training (source) and deploying (target) stages, compress…
In document-level event argument extraction, an argument is likely to appear multiple times in different expressions in the document. The redundancy of arguments underlying multiple sentences is beneficial but is often overlooked. In addition, in event argument extraction, most entities are regarded…
Recently, Transformer has been demonstrating promising performance in many NLP tasks and showing a trend of replacing Recurrent Neural Network (RNN). Meanwhile, less attention is drawn to Convolutional Neural Network (CNN) due to its weak ability in capturing sequential and long-distance dependencie…
Partial Domain Adaptation (PDA) is a practical and general domain adaptation scenario, which relaxes the fully shared label space assumption such that the source label space subsumes the target one. The key challenge of PDA is the issue of negative transfer caused by source-only classes. For videos,…