Related papers: Real Differences between OT and CRDT under a Gener…
Although foundation models (FMs) claim to be powerful, their generalization ability significantly decreases when faced with distribution shifts, weak supervision, or malicious attacks in the open world. On the other hand, most domain…
Machine Translation (MT) tools are widely used today, often in contexts where professional translators are not present. Despite progress in MT technology, a gap persists between system development and real-world usage, particularly for…
Generalization to novel compound tasks under distribution shift is important for deploying transformer-based language models (LMs). This work investigates Chain-of-Thought (CoT) reasoning as a means to enhance OOD generalization. Through…
Multi-agent LLM systems fail to realize parallel speedups due to costly coordination. We present CodeCRDT, an observation-driven coordination pattern where agents coordinate by monitoring a shared state with observable updates and…
Digitization of historical documents is a challenging task in many digital humanities projects. A popular approach for digitization is to scan the documents into images, and then convert images into text using Optical Character Recognition…
Large language models (LLMs) can now solve complex problems through long chain-of-thought (CoT) reasoning, but the trade-off between performance and token cost remains a central challenge. To address this issue, supervised fine-tuning (SFT)…
By the CAP Theorem, a distributed data storage system can ensure either Consistency under Partition (CP) or Availability under Partition (AP), but not both. This has led to a split between CP databases, in which updates are synchronous, and…
Dwell time (DT) is a critical post-click metric for evaluating user preference in recommender systems, complementing the traditional click-through rate (CTR). Although multi-task learning is widely adopted to jointly optimize DT and CTR, we…
Given a language model (LM), maximum probability is a poor decoding objective for open-ended generation, because it produces short and repetitive text. On the other hand, sampling can often produce incoherent text that drifts from the…
Optical coherence tomography (OCT) uses low-coherence reflectometry to obtain cross-sectional images of inhomogeneous media, such as biological tissue. OCT is particularly useful in the biomedical ea, since the imaging can be performed…
Recently, one-stage visual grounders attract high attention due to their comparable accuracy but significantly higher efficiency than two-stage grounders. However, inter-object relation modeling has not been well studied for one-stage…
Quantum Optical Coherence Tomography (Q-OCT) uses quantum properties of light to provide several advantages over its classical counterpart, OCT: it achieves a twice better axial resolution with the same spectral bandwidth and it is immune…
Open-vocabulary object detection (OVOD) enables novel category detection via vision-language alignment, but massive model sizes hinder deployment on resource-constrained devices. While quantization offers practical compression, we reveal…
Despite the success of contrastive learning (CL) in vision and language, its theoretical foundations and mechanisms for building representations remain poorly understood. In this work, we build connections between noise contrastive…
The success of most existing cross-modal retrieval methods heavily relies on the assumption that the given queries follow the same distribution of the source domain. However, such an assumption is easily violated in real-world scenarios due…
Finding effective representations for time series data is a useful but challenging task. Several works utilize self-supervised or unsupervised learning methods to address this. However, there still remains the open question of how to…
Optical coherence tomography (OCT) is a noninvasive technology that enables real-time imaging of tissue microanatomies. The axial resolution of OCT is intrinsically constrained by the spectral bandwidth of the employed light source while…
The primary goal of online change detection (OCD) is to promptly identify changes in the data stream. OCD problem find a wide variety of applications in diverse areas, e.g., security detection in smart grids and intrusion detection in…
Optical coherence tomography (OCT) is a non-invasive volumetric imaging modality with high spatial and temporal resolution. For imaging larger tissue structures, OCT probes need to be moved to scan the respective area. For handheld…
In addition to relevance, diversity is an important yet less studied performance metric of cross-modal image retrieval systems, which is critical to user experience. Existing solutions for diversity-aware image retrieval either explicitly…