相关论文: Fusion Matters: Length-Aware Analysis of Positiona…

Retrieval-Augmented Generation systems depend on retrieving semantically relevant document chunks to support accurate, grounded outputs from large language models. In structured and repetitive corpora such as regulatory filings, chunk…

Accurate prediction of others' trajectories is essential for autonomous driving. Trajectory prediction is challenging because it requires reasoning about agents' past movements, social interactions among varying numbers and kinds of agents,…

In this work, we investigate the positional encoding methods used in language pre-training (e.g., BERT) and identify several problems in the existing formulations. First, we show that in the absolute positional encoding, the addition…

We use a mean-field-based transformer model to theoretically investigate how auxiliary variables, such as positional encoding, prevent mode collapse of self-attention mechanisms. The use of mean-field transformers to analyze the properties…

We propose a training-free approach to improve sentence embeddings leveraging test-time compute by applying generative text models for data augmentation at inference time. Unlike conventional data augmentation that utilises synthetic…

While large language models (LLMs) fine-tuned with lightweight adapters achieve strong performance across diverse tasks, their performance on individual tasks depends on the fine-tuning strategy. Fusing independently trained models with…

Growing amounts of online user data motivate the need for automated processing techniques. In case of user ratings, one interesting option is to use neural networks for learning to predict ratings given an item and a user. While training…

Transformer based language models exhibit intelligent behaviors such as understanding natural language, recognizing patterns, acquiring knowledge, reasoning, planning, reflecting and using tools. This paper explores how their underlying…

3D semantic occupancy prediction is crucial for finely representing the surrounding environment, which is essential for ensuring the safety in autonomous driving. Existing fusion-based occupancy methods typically involve performing a…

Federated Learning has emerged as a transformative paradigm for collaborative machine learning across distributed environments. However, its performance is strongly influenced by the aggregation strategy used to combine local model updates…

Text summarization aims to condense long documents and retain key information. Critical to the success of a summarization model is the faithful inference of latent representations of words or tokens in the source documents. Most recent…

Quantum machine learning was recently applied to various applications and leads to results that are comparable or, in certain instances, superior to classical methods, in particular when few training data is available. These results warrant…

Sequence decoding is one of the core components of most visual-lingual models. However, typical neural decoders when faced with decoding multiple, possibly correlated, sequences of tokens resort to simple independent decoding schemes. In…

Since self-attention layers in Transformers are permutation invariant by design, positional encodings must be explicitly incorporated to enable spatial understanding. However, fixed-size lookup tables used in traditional learnable position…

Several recent works use positional encodings to extend the receptive fields of graph neural network (GNN) layers equipped with attention mechanisms. These techniques, however, extend receptive fields to the complete graph, at substantial…

The rapid advancements of AI rely on the support of ICs. However, the growing complexity of digital ICs makes the traditional IC design process costly and time-consuming. In recent years, AI-assisted IC design methods have demonstrated…

In this work, we study whether enforcing strict compositional structure in sequence embeddings yields meaningful geometric organization when applied to protein-protein interaction networks. Using Event2Vec, an additive sequence embedding…

We investigate how embedding dimension affects the emergence of an internal "world model" in a transformer trained with reinforcement learning to perform bubble-sort-style adjacent swaps. Models achieve high accuracy even with very small…

To ensure the safe and efficient navigation of autonomous vehicles and advanced driving assistance systems in complex traffic scenarios, predicting the future bounding boxes of surrounding traffic agents is crucial. However, simultaneously…

Positional encoding has become a standard component in graph learning, especially for graph Transformers and other models that must distinguish structurally similar nodes, yet its fundamental identifiability remains poorly understood. In…