相关论文: CAFE: Towards Compact, Adaptive, and Fast Embeddin…

In this study, we introduce adaptive KV cache compression, a plug-and-play method that reduces the memory footprint of generative inference for Large Language Models (LLMs). Different from the conventional KV cache that retains key and…

Representation learning using network embedding has received tremendous attention due to its efficacy to solve downstream tasks. Popular embedding methods (such as deepwalk, node2vec, LINE) are based on a neural architecture, thus unable to…

High-density biosignal recordings are critical for neural decoding and clinical monitoring, yet real-world deployments often rely on low-density (LD) montages due to hardware and operational constraints. This motivates spatial…

Finding a low dimensional representation of hierarchical, structured data described by a network remains a challenging problem in the machine learning community. An emerging approach is embedding these networks into hyperbolic space because…

Recommender systems have become an essential component of many online platforms, providing personalized recommendations to users. A crucial aspect is embedding techniques that convert the high-dimensional discrete features, such as user and…

In rapid and massive data streams, it is often not possible to estimate the frequency of items with complete accuracy. To perform the operation in a reasonable amount of space and with sufficiently low latency, approximated methods are…

Recommender systems have advanced markedly over the past decade by transforming each user/item into a dense embedding vector with deep learning models. At industrial scale, embedding tables constituted by such vectors of all users/items…

Test-time adaptation with pre-trained vision-language models has gained increasing attention for addressing distribution shifts during testing. Among these approaches, memory-based algorithms stand out due to their training-free nature and…

Transformer-based detectors have advanced small-object detection, but they often remain inefficient and vulnerable to background-induced query noise, which motivates deep decoders to refine low-quality queries. We present HELP…

In deep learning, embeddings are widely used to represent categorical entities such as words, apps, and movies. An embedding layer maps each entity to a unique vector, causing the layer's memory requirement to be proportional to the number…

In recent years, many research works propose to embed the network structured data into a low-dimensional feature space, where each node is represented as a feature vector. However, due to the detachment of embedding process with external…

Advancements in Large Language Models (LLMs) have extended their input context length, yet they still struggle with retrieval and reasoning in long-context inputs. Existing methods propose to utilize the prompt strategy and retrieval head…

Understanding the coordinated activity underlying brain computations requires large-scale, simultaneous recordings from distributed neuronal structures at a cellular-level resolution. One major hurdle to design high-bandwidth,…

Current Transformer-based methods for small object detection continue emerging, yet they have still exhibited significant shortcomings. This paper introduces HeatMap Position Embedding (HMPE), a novel Transformer Optimization technique that…

Diffusion models achieve state-of-the-art video generation quality, but their inference remains expensive due to the large number of sequential denoising steps. This has motivated a growing line of research on accelerating diffusion…

Impressive advances in acquisition and sharing technologies have made the growth of multimedia collections and their applications almost unlimited. However, the opposite is true for the availability of labeled data, which is needed for…

Explainable recommendation is far from being well solved partly due to three challenges. The first is the personalization of preference learning, which requires that different items/users have different contributions to the learning of user…

Embedding image features into a binary Hamming space can improve both the speed and accuracy of large-scale query-by-example image retrieval systems. Supervised hashing aims to map the original features to compact binary codes in a manner…

Production recommendation systems rely on embedding methods to represent various features. An impeding challenge in practice is that the large embedding matrix incurs substantial memory footprint in serving as the number of features grows…

Learning high-quality feature embeddings efficiently and effectively is critical for the performance of web-scale machine learning systems. A typical model ingests hundreds of features with vocabularies on the order of millions to billions…