Related papers: DEO: Training-Free Direct Embedding Optimization f…

We present an efficient method of pretraining large-scale autoencoding language models using training signals generated by an auxiliary model. Originated in ELECTRA, this training strategy has demonstrated sample-efficiency to pretrain…

Despite advances in generative large language models (LLMs), practical application of specialized conversational AI agents remains constrained by computation costs, latency requirements, and the need for precise domain-specific relevance…

The generative learning phase of Autoencoder (AE) and its successor Denosing Autoencoder (DAE) enhances the flexibility of data stream method in exploiting unlabelled samples. Nonetheless, the feasibility of DAE for data stream analytic…

Despite rapid adoption of autoregressive large language models, smaller text encoders still play an important role in text understanding tasks that require rich contextualized representations. Negation is an important semantic function that…

Neural prediction offers a promising approach to forecasting the individual variability of neurocognitive functions and disorders and providing prognostic indicators for personalized invention. However, it is challenging to translate neural…

Recent research demonstrates the effectiveness of using fine-tuned language models~(LM) for dense retrieval. However, dense retrievers are hard to train, typically requiring heavily engineered fine-tuning pipelines to realize their full…

Offline model-based optimization (MBO) aims to maximize a black-box objective function using only an offline dataset of designs and scores. These tasks span various domains, such as robotics, material design, and protein and molecular…

Deep metric learning has been effectively used to learn distance metrics for different visual tasks like image retrieval, clustering, etc. In order to aid the training process, existing methods either use a hard mining strategy to extract…

Retrieval-Augmented Generation (RAG) has been shown to enhance the factual accuracy of Large Language Models (LLMs), but existing methods often suffer from limited reasoning capabilities in effectively using the retrieved evidence,…

Dense retrieval systems increasingly need to handle complex queries. In many realistic settings, users express intent through long instructions or task-specific descriptions, while target documents remain relatively simple and static. This…

Vehicle re-identification plays a crucial role in the management of transportation infrastructure and traffic flow. However, this is a challenging task due to the large view-point variations in appearance, environmental and instance-related…

Group Relative Policy Optimization (GRPO) effectively scales LLM reasoning but incurs prohibitive computational costs due to its extensive group-based sampling requirement. While recent selective data utilization methods can mitigate this…

Recently, the retrieval models based on dense representations have been gradually applied in the first stage of the document retrieval tasks, showing better performance than traditional sparse vector space models. To obtain high efficiency,…

We propose RSO (random search optimization), a gradient free Markov Chain Monte Carlo search based approach for training deep neural networks. To this end, RSO adds a perturbation to a weight in a deep neural network and tests if it reduces…

Deep neural models for relation extraction tend to be less reliable when perfectly labeled data is limited, despite their success in label-sufficient scenarios. Instead of seeking more instance-level labels from human annotators, here we…

Despite considerable progress in neural relevance ranking techniques, search engines still struggle to process complex queries effectively - both in terms of precision and recall. Sparse and dense Pseudo-Relevance Feedback (PRF) approaches…

Dense embedding models have become critical for modern information retrieval, particularly in RAG pipelines, but their performance often degrades when applied to specialized corpora outside their pre-training distribution. To address thi we…

Recent Large Reasoning Models (LRMs) have achieved remarkable performance in solving complex problems via supervised fine-tuning (SFT) and reinforcement learning (RL). Although existing RL algorithms significantly enhance model accuracy,…

In text-video retrieval, auxiliary captions are often used to enhance video understanding, bridging the gap between the modalities. While recent advances in multi-modal large language models (MLLMs) have enabled strong zero-shot caption…

Recent research has delved into speech enhancement (SE) approaches that leverage audio embeddings from pre-trained models, diverging from time-frequency masking or signal prediction techniques. This paper introduces an efficient and…