arXiv subjects

Yiqi Song

Publications and source records attributed to Yiqi Song.

4 recordsLinked to original sources

arXiv2026

Observation antibunching with classical light in a linear interferometer

Understanding the boundary between classical and nonclassical phenomena is important for both fundamental researches in quantum optics and applications in quantum information. One of the most interesting research directions in this field is exploring nonclassical effects with classical light. In this paper, we will show that it is possible to observe antibunching with thermal light in a Hanbury Brown-Twiss interferometer by treating single-photon detectors as photon-number-resolving detectors to perform photon-number projection measurements. Both temporal and spatial antibunching is observed via the correlation of two detectors detecting one and zero photon, respectively. By comparing the measured results of thermal and laser light, it is found that the observed antibunching arises from the combined effect of photon statistics of thermal light and photon-number projection measurement.The classical and nonclassical nature of the observed antibunching is analyzed. The results are helpful to understand the connection between classical and nonclassical correlation and may find applications in multiphoton interference and quantum imaging.

quant-ph↗

arXiv2026

Ghost imaging with zero photons

Ghost imaging was first demonstrated with entangled photon pairs and well-known for its peculiar properties. The signal beam that illuminates the object possesses no spatial resolution, whereas the reference beam, which never interacts with the object, is spatially resolved. Either beam alone cannot retrieve the image, which can only be obtained when the signal and reference beams are correlated. Here we will report a ghost imaging experiment with even more peculiar properties, in which the image can be reconstructed when no photon interacts with the object or even no photon in neither signal nor reference beam. All the photons interacted with the object are discarded. Only the time bins with zero photon are employed to retrieve the image, a process referred to as "ghost imaging with zero photons" hereafter. The reason why ghost image can be retrieved with zero photons is jointly determined by photon-number projection measurement and photon statistics of thermal light. The results are helpful to resolve the debate on the physics of ghost imaging and understand the relation between quantum and classical correlations.

quant-ph↗

arXiv2024

How Vision-Language Tasks Benefit from Large Pre-trained Models: A Survey

The exploration of various vision-language tasks, such as visual captioning, visual question answering, and visual commonsense reasoning, is an important area in artificial intelligence and continuously attracts the research community's attention. Despite the improvements in overall performance, classic challenges still exist in vision-language tasks and hinder the development of this area. In recent years, the rise of pre-trained models is driving the research on vision-language tasks. Thanks to the massive scale of training data and model parameters, pre-trained models have exhibited excellent performance in numerous downstream tasks. Inspired by the powerful capabilities of pre-trained models, new paradigms have emerged to solve the classic challenges. Such methods have become mainstream in current research with increasing attention and rapid advances. In this paper, we present a comprehensive overview of how vision-language tasks benefit from pre-trained models. First, we review several main challenges in vision-language tasks and discuss the limitations of previous solutions before the era of pre-training. Next, we summarize the recent advances in incorporating pre-trained models to address the challenges in vision-language tasks. Finally, we analyze the potential risks associated with the inherent limitations of pre-trained models and discuss possible solutions, attempting to provide future research directions.

cs.CV↗

arXiv2024

VideoLLaMB: Long Streaming Video Understanding with Recurrent Memory Bridges

Recent advancements in large-scale video-language models have shown significant potential for real-time planning and detailed interactions. However, their high computational demands and the scarcity of annotated datasets limit their practicality for academic researchers. In this work, we introduce VideoLLaMB, a novel and efficient framework for long video understanding that leverages recurrent memory bridges and temporal memory tokens to enable seamless encoding of entire video sequences with preserved semantic continuity. Central to our approach is a SceneTiling algorithm that segments videos into coherent semantic units, facilitating robust understanding across tasks without requiring additional training. VideoLLaMB achieves state-of-the-art performance, surpassing existing models by 4.2 points on four VideoQA benchmarks and by 2.06 points on egocentric planning tasks. Notably, it maintains strong performance under extreme video length scaling (up to 8 times) and excels at fine-grained frame retrieval on our proposed Needle in a Video Haystack (NIAVH) benchmark. With linear GPU memory scaling, VideoLLaMB processes up to 320 frames using a single Nvidia A100 GPU, despite being trained on only 16 frames-offering an unprecedented balance of accuracy, scalability, and cost-effectiveness. This makes it highly accessible and practical for the academic community.

cs.CV↗