相关论文: QueryMamba: A Mamba-Based Encoder-Decoder Architec…

Language model agents (LMA) recently emerged as a promising paradigm on muti-step decision making tasks, often outperforming humans and other reinforcement learning agents. Despite the promise, their performance on real-world applications…

Sequential recommendation aims to estimate the dynamic user preferences and sequential dependencies among historical user behaviors. Although Transformer-based models have proven to be effective for sequential recommendation, they suffer…

This technical report provides a detailed description of our approach to the EgoSchema Challenge 2024. The EgoSchema Challenge aims to identify the most appropriate responses to questions regarding a given video clip. In this paper, we…

Video Question Answering (VQA) inherently relies on multimodal reasoning, integrating visual, temporal, and linguistic cues to achieve a deeper understanding of video content. However, many existing methods rely on feeding frame-level…

Event cameras draw inspiration from biological systems, boasting low latency and high dynamic range while consuming minimal power. The most current approach to processing Event Cloud often involves converting it into frame-based…

The Interspeech 2025 URGENT Challenge aimed to advance universal, robust, and generalizable speech enhancement by unifying speech enhancement tasks across a wide variety of conditions, including seven different distortion types and five…

State-space models (SSMs) have recently demonstrated competitive performance to transformers at large-scale language modeling benchmarks while achieving linear time and memory complexity as a function of sequence length. Mamba, a recently…

In the past decade, Convolutional Neural Networks (CNNs) and Transformers have achieved wide applicaiton in semantic segmentation tasks. Although CNNs with Transformer models greatly improve performance, the global context modeling remains…

Long-term time series forecasting (LTSF) provides longer insights into future trends and patterns. Over the past few years, deep learning models especially Transformers have achieved advanced performance in LTSF tasks. However, LTSF faces…

Human trajectory forecasting is crucial for safe navigation in crowded environments, requiring models that balance accuracy with computational efficiency. Efficiently modeling social interactions is key to performance in dense crowds. Yet,…

The rapid proliferation of user-generated content (UGC) on short-form video platforms has made video engagement prediction increasingly important for optimizing recommendation systems and guiding content creation. However, this task remains…

Linear RNN architectures, like Mamba, can be competitive with Transformer models in language modeling while having advantageous deployment characteristics. Given the focus on training large-scale Transformer models, we consider the…

Training deep learning models for semantic occupancy prediction is challenging due to factors such as a large number of occupancy cells, severe occlusion, limited visual cues, complicated driving scenarios, etc. Recent methods often adopt…

State-of-the-art video object detection methods maintain a memory structure, either a sliding window or a memory queue, to enhance the current frame using attention mechanisms. However, we argue that these memory structures are not…

We propose ss-Mamba, a novel foundation model that enhances time series forecasting by integrating semantic-aware embeddings and adaptive spline-based temporal encoding within a selective state-space modeling framework. Building upon the…

This work demonstrates the implementation and use of an encoder-decoder model to perform a many-to-many mapping of video data to text captions. The many-to-many mapping occurs via an input temporal sequence of video frames to an output…

Sequential recommendation systems aim to provide personalized recommendations by analyzing dynamic preferences and dependencies within user behavior sequences. Recently, Transformer models can effectively capture user preferences. However,…

We study efficiency as a first-class objective in Neural Combinatorial Optimization (NCO) and present ECO, an efficient learning framework that combines batched preference optimization with a Mamba backbone. Instead of tightly interleaving…

Referring Image Segmentation~(RIS) leveraging transformers has achieved great success on the interpretation of complex visual-language tasks. However, the quadratic computation cost makes it resource-consuming in capturing long-range…

Cross-modal alignment is crucial for multimodal representation fusion due to the inherent heterogeneity between modalities. While Transformer-based methods have shown promising results in modeling inter-modal relationships, their quadratic…