Related papers: DAT: Dual-Aware Adaptive Transmission for Efficien…

We propose the Multi-Head Density Adaptive Attention Mechanism (DAAM), a novel probabilistic attention framework that can be used for Parameter-Efficient Fine-tuning (PEFT), and the Density Adaptive Transformer (DAT), designed to enhance…

Hybrid retrieval techniques in Retrieval-Augmented Generation (RAG) systems enhance information retrieval by combining dense and sparse (e.g., BM25-based) retrieval methods. However, existing approaches struggle with adaptability, as fixed…

Deploying Vision-Language Models (VLMs) on edge devices remains challenging due to their substantial computational and memory demands, which exceed the capabilities of resource-constrained embedded platforms. Conversely, fully offloading…

Recent advances in transformer-based Large Language Models (LLMs) have demonstrated remarkable capabilities across various tasks. However, their quadratic computational complexity concerning sequence length remains a significant bottleneck…

Transformers have shown superior performance on various vision tasks. Their large receptive field endows Transformer models with higher representation power than their CNN counterparts. Nevertheless, simply enlarging the receptive field…

Large-scale Vision-Language Models (VLMs) encode rich multimodal semantics that are highly beneficial for fine-grained visual categorization (FGVC). However, their prohibitive computational cost hinders practical deployment in…

Intelligent anomaly detection in dynamic visual environments requires reconciling real-time performance with semantic interpretability. Conventional approaches address only fragments of this challenge. Reconstruction-based models capture…

Weakly supervised point cloud segmentation, i.e. semantically segmenting a point cloud with only a few labeled points in the whole 3D scene, is highly desirable due to the heavy burden of collecting abundant dense annotations for the model…

Large Language Models (LLMs) face computational inefficiencies and redundant processing when handling long context inputs, prompting a focus on compression techniques. While existing semantic vector-based compression methods achieve…

Event-based multimodal large language models (MLLMs) enable robust perception in high-speed and low-light scenarios, addressing key limitations of frame-based MLLMs. However, current event-based MLLMs often rely on dense image-like…

Relational reasoning is a central component of generally intelligent systems, enabling robust and data-efficient inductive generalization. Recent empirical evidence shows that many existing neural architectures, including Transformers,…

LiDAR (Light Detection And Ranging) is an essential and widely adopted sensor for autonomous vehicles, particularly for those vehicles operating at higher levels (L4-L5) of autonomy. Recent work has demonstrated the promise of deep-learning…

Adapting Multimodal Large Language Models (MLLMs) for hour-long videos is bottlenecked by context limits. Dense visual streams saturate token budgets and exacerbate the lost-in-the-middle phenomenon. Existing heuristics, like sparse…

Most multi-agent systems rely exclusively on autoregressive language models (ARMs) that are based on sequential generation. Although effective for fluent text, ARMs limit global reasoning and plan revision. On the other hand, Discrete…

Large language models (LLMs) have demonstrated strong performance across various tasks, leveraging their exceptional in-context learning ability with only a few examples. Accordingly, the selection of optimal in-context examples has been…

Adaptive reasoning is essential for aligning the computational effort of large language models (LLMs) with the intrinsic difficulty of problems. Current chain-of-thought methods boost reasoning ability but indiscriminately generate long…

Large Language Models (LLMs) have recently been extended to the video domain, enabling sophisticated video-language understanding. However, existing Video LLMs often exhibit limitations in fine-grained temporal reasoning, restricting their…

Deep learning architectures with powerful reasoning capabilities have driven significant advancements in autonomous driving technology. Large language models (LLMs) applied in this field can describe driving scenes and behaviors with a…

Domain Adaptive Object Detection (DAOD) models a joint distribution of images and labels from an annotated source domain and learns a domain-invariant transformation to estimate the target labels with the given target domain images.…

The human auditory system has the ability to selectively focus on key speech elements in an audio stream while giving secondary attention to less relevant areas such as noise or distortion within the background, dynamically adjusting its…