Related papers: Parser-Oriented Structural Refinement for a Stable…

Deep-learning-based video processing has yielded transformative results in recent years. However, the video analytics pipeline is energy-intensive due to high data rates and reliance on complex inference algorithms, which limits its…

Despite being the current de-facto models in most NLP tasks, transformers are often limited to short sequences due to their quadratic attention complexity on the number of tokens. Several attempts to address this issue were studied, either…

Document structure analysis, aka document layout analysis, is crucial for understanding both the physical layout and logical structure of documents, serving information retrieval, document summarization, knowledge extraction, etc.…

With the rapid advancement of tool-use capabilities in Large Language Models (LLMs), Retrieval-Augmented Generation (RAG) is shifting from static, one-shot retrieval toward autonomous, multi-turn evidence acquisition. However, existing…

Domain-specific finetuning is essential for dense retrievers, yet not all training pairs contribute equally to the learning process. We introduce OPERA, a data pruning framework that exploits this heterogeneity to improve both the…

Diffusion models have achieved success in high-fidelity data synthesis, yet their capacity for more complex, structured reasoning like text following tasks remains constrained. While advances in language models have leveraged strategies…

There is a recent surge of interest in designing deep architectures based on the update steps in traditional algorithms, or learning neural networks to improve and replace traditional algorithms. While traditional algorithms have certain…

Many discriminative natural language understanding (NLU) tasks have large label spaces. Learning such a process of large-space decision making is particularly challenging due to the lack of training instances per label and the difficulty of…

Linear attention offers a linear-time alternative to self-attention but often struggles to capture long-range patterns. We revisit linear attention through a prediction-correction lens and show that prevalent variants can be written as a…

In neural Information Retrieval (IR), ongoing research is directed towards improving the first retriever in ranking pipelines. Learning dense embeddings to conduct retrieval using efficient approximate nearest neighbors methods has proven…

End-to-end text spotting has attached great attention recently due to its benefits on global optimization and high maintainability for real applications. However, the input scale has always been a tough trade-off since recognizing a small…

Scaling autoregressive large language models (LLMs) has driven unprecedented progress but comes with vast computational costs. In this work, we tackle these costs by leveraging unstructured sparsity within an LLM's feedforward layers, the…

Assessing ways in which Language Models can reduce their hallucinations and improve the outputs' quality is crucial to ensure their large-scale use. However, methods such as fine-tuning on domain-specific data or the training of a separate…

Much of the recent efforts on salient object detection (SOD) have been devoted to producing accurate saliency maps without being aware of their instance labels. To this end, we propose a new pipeline for end-to-end salient instance…

Boundary detection of irregular and translucent objects is an important problem with applications in medical imaging, environmental monitoring and manufacturing, where many of these applications are plagued with scarce labeled data and low…

Token prediction stability remains a challenge in autoregressive generative models, where minor variations in early inference steps often lead to significant semantic drift over extended sequences. A structured modulation mechanism was…

An important component of computer vision research is object detection. In recent years, there has been tremendous progress in the study of construction site images. However, there are obvious problems in construction object detection,…

Prefix caching is a key latency optimization for autoregressive LLM serving, yet existing systems assume dense per-token key/value reuse. State-space models change the structure of the problem: a recurrent layer can resume from a single…

Retrieval-augmented generation has achieved strong performance on knowledge-intensive tasks where query-document relevance can be identified through direct lexical or semantic matches. However, many real-world queries involve abstract…

We develop a unified matrix-spectral framework for analyzing stability and interpretability in deep neural networks. Representing networks as data-dependent products of linear operators reveals spectral quantities governing sensitivity to…