Related papers: Typos-aware Bottlenecked Pre-Training for Robust D…
Ranker and retriever are two important components in dense passage retrieval. The retriever typically adopts a dual-encoder model, where queries and documents are separately input into two pre-trained models, and the vectors generated by…
We introduce LADDER (Learning through Autonomous Difficulty-Driven Example Recursion), a framework which enables Large Language Models to autonomously improve their problem-solving capabilities through self-guided learning by recursively…
Masked diffusion models (MDMs) have emerged as a promising alternative to autoregressive models, enabling parallel token generation while achieving competitive performance. Despite these advantages, MDMs face a fundamental limitation: once…
Despite the evolution of deep-learning-based visual-textual processing systems, precise multi-modal matching remains a challenging task. In this work, we tackle the task of cross-modal retrieval through image-sentence matching based on…
Pre-trained language model (PTM) has been shown to yield powerful text representations for dense passage retrieval task. The Masked Language Modeling (MLM) is a major sub-task of the pre-training process. However, we found that the…
Neural codec language models enable high-quality discrete speech synthesis, yet their inference remains vulnerable to token-level artifacts and distributional drift that degrade perceptual realism. Rather than relying on preference…
In monolingual dense retrieval, lots of works focus on how to distill knowledge from cross-encoder re-ranker to dual-encoder retriever and these methods achieve better performance due to the effectiveness of cross-encoder re-ranker.…
Large Language Models (LLMs) have demonstrated impressive performance on multiple-choice question answering (MCQA) benchmarks, yet they remain highly vulnerable to minor input perturbations. In this paper, we introduce and evaluate Token…
Popular transformer detectors have achieved promising performance through query-based learning using attention mechanisms. However, the roles of existing decoder query types (e.g., content query and positional query) are still…
In this paper, we propose SimLM (Similarity matching with Language Model pre-training), a simple yet effective pre-training method for dense passage retrieval. It employs a simple bottleneck architecture that learns to compress the passage…
The ability of machine learning models to store input information in hidden layer vector embeddings, analogous to the concept of `memory', is widely employed but not well characterized. We find that language model embeddings typically…
Adapting pre-trained deep learning models to customized tasks has become a popular choice for developers to cope with limited computational resources and data volume. More specifically, probing--training a downstream head on a pre-trained…
Recent rapid advancements in deep pre-trained language models and the introductions of large datasets have powered research in embedding-based dense retrieval. While several good research papers have emerged, many of them come with their…
Dual encoder (DE) models, where a pair of matching query and document are embedded into similar vector representations, are widely used in information retrieval due to their simplicity and scalability. However, the Euclidean geometry of the…
Learned Sparse Retrievers (LSR) have evolved into an effective retrieval strategy that can bridge the gap between traditional keyword-based sparse retrievers and embedding-based dense retrievers. At its core, learned sparse retrievers try…
This paper examines the problems of severe image-text misalignment and high redundancy in the widely-used large-scale Vision-Language Pre-Training (VLP) datasets. To address these issues, we propose an efficient and straightforward…
Speculative decoding (SD) accelerates Large Language Model (LLM) generation by using an efficient draft model to propose the next few tokens, which are verified by the LLM in a single forward call, reducing latency while preserving its…
Attention-based recurrent neural encoder-decoder models present an elegant solution to the automatic speech recognition problem. This approach folds the acoustic model, pronunciation model, and language model into a single network and…
Learned Sparse Retrieval (LSR) is an effective IR approach that exploits pre-trained language models for encoding text into a learned bag of words. Several efforts in the literature have shown that sparsity is key to enabling a good…
DEtection TRansformer (DETR) for object detection reaches competitive performance compared with Faster R-CNN via a transformer encoder-decoder architecture. However, trained with scratch transformers, DETR needs large-scale training data…