24 accepted papers
Recently, studies exemplified by Hyper-Connections (HC) have extended the ubiquitous residual connection paradigm established over the past decade by expanding the residual stream width and diversifying connectivity patterns. While yielding substantial performance gains, this diversification fundame…
Long-context modeling is crucial for next-generation language models, yet the high computational cost of standard attention mechanisms poses significant computational challenges. Sparse attention offers a promising direction for improving efficiency while maintaining model capabilities. We present N…
Activation sparsity refers to the existence of considerable weakly-contributed elements among activation outputs, serving as a promising paradigm for accelerating model inference. Nevertheless, most large language models (LLMs) adopt activation functions without intrinsic activation sparsity (e.g.,…
In computer-assisted orthopedic surgery (CAOS), accurate point set registration is essential for enhancing surgical accuracy. However, the sparse and low-overlap nature of intraoperative point sets presents significant challenges for reliable registration. To deal with these challenges, we propose a
In this paper, we present a novel curve-to-surface registration method, termed Bi-directional Hybrid Mixture Model Registration based on Dual-constrained Tangent and Normal Vectors (BiHMM-DTN), where two different tangent vectors at the intraoperative point are simultaneously used with the normal ve
In this paper, we introduce a novel normal-assisted learning-based rigid registration approach, i.e., Deep Bi-directional Hybrid Mixture Registration (DeepBHMR). Our approach utilises helpful normal vectors explicitly in both correspondence and transformation stages and formulates the optimization o
Pre-trained Transformers inherently possess the characteristic of sparse activation, where only a small fraction of the neurons are activated for each token. While sparse activation has been explored through post-training methods, its potential in pre-training remains untapped. In this work, we firs…
Large language models (LLMs) have emerged as a cornerstone in real-world applications with lengthy streaming inputs (e.g., LLM-driven agents). However, existing LLMs, pre-trained on sequences with a restricted maximum length, cannot process longer sequences due to the out-of-domain and distraction i…
In this paper, we introduce a novel overlap-based bidirectional point set registration approach, i.e., Overlap-guided Bidirectional Hybrid Mixture Registration (OBHMR), which incorporates geometric information (i.e., normal vectors) in both the correspondence and transformation stages and formulates…
Large language models (LLMs) can make predictions using *parametric knowledge* – knowledge encoded in the model weights – or *contextual knowledge* – knowledge presented in the context. In many scenarios, a desirable behavior is that LLMs give precedence to contextual knowledge when it conflicts wit…
This work examines the presence of modularity in pre-trained Transformers, a feature commonly found in human brains and thought to be vital for general intelligence. In analogy to human brains, we consider two main characteristics of modularity: (1) functional specialization of neurons: we evaluate…
Large-scale pre-trained models (PTMs) have been widely used in document-oriented NLP tasks, such as question answering. However, the encoding-task coupling requirement results in the repeated encoding of the same documents for different tasks and queries, which is highly computationally inefficient.…
Injecting external knowledge can improve the performance of pre-trained language models (PLMs) on various downstream NLP tasks. However, massive retraining is required to deploy new knowledge injection methods or knowledge bases for downstream tasks. In this work, we are the first to study how to im…
For many real-world applications, the user-generated inputs usually contain various noises due to speech recognition errors caused by linguistic variations or typographical errors (typos). Thus, it is crucial to test model performance on data with realistic input noises to ensure robustness and fair…
Large language models (LLMs) have achieved remarkable results on NLP tasks but at the expense of huge parameter sizes and the consequent computational costs. In this paper, we propose Variator, a parameter-efficient acceleration method that enhances computational efficiency through plug-and-play com…
Prompting, which casts downstream applications as language modeling tasks, has shown to be sample efficient compared to standard fine-tuning with pre-trained models. However, one pitfall of prompting is the need of manually-designed patterns, whose outcome can be unintuitive and requires large valid…
Transformer-based pre-trained language models have demonstrated superior performance on various natural language processing tasks. However, it remains unclear how the skills required to handle these tasks distribute among model parameters. In this paper, we find that after prompt tuning for specific…
This paper presents a novel, robust, and accurate three-dimensional (3D) rigid point set registration (PSR) method, which is achieved by generalizing the state-of-the-art (SOTA) Bayesian coherent point drift (BCPD) theory to the scenario that high-dimensional point sets(PSs) are aligned and that the…
Recent explorations of large-scale pre-trained language models (PLMs) have revealed the power of PLMs with huge amounts of parameters, setting off a wave of training ever-larger PLMs. However, it requires tremendous computational resources to train a large-scale PLM, which may be practically unaffor…
This paper proposes a new network for reconstructing multi-object point cloud. Different from previous networks which reconstruct multi-object point cloud as a whole, our network iteratively reconstructs each individual object point cloud from a frame of multi-object point cloud. To achieve this goa…
Recent work has shown that feed-forward networks (FFNs) in pre-trained Transformers are a key component, storing various linguistic and factual knowledge. However, the computational patterns of FFNs are still unclear. In this work, we study the computational patterns of FFNs and observe that most in…
Recent works have shown promising results of prompt tuning in stimulating pre-trained language models (PLMs) for natural language processing (NLP) tasks. However, to the best of our knowledge, existing works focus on prompt-tuning generative PLMs that are pre-trained to generate target tokens, such…
We study the problem of adversarial language games, in which multiple agents with conflicting goals compete with each other via natural language interactions. While adversarial language games are ubiquitous in human activities, little attention has been devoted to this field in natural language proc…
Backdoor attacks are a kind of insidious security threat against machine learning models. After being injected with a backdoor in training, the victim model will produce adversary-specified outputs on the inputs embedded with predesigned triggers but behave properly on normal inputs during inference…