Related papers: Local Information Matters: Inference Acceleration …

Fine-tuning and inference with large Language Models (LM) are generally known to be expensive. Parameter-efficient fine-tuning over pretrained LMs reduces training memory by updating a small number of LM parameters but does not improve…

Surgical scene understanding and multi-tasking learning are crucial for image-guided robotic surgery. Training a real-time robotic system for the detection and segmentation of high-resolution images provides a challenging problem with the…

Visual Autoregressive (VAR) models enable efficient image generation via next-scale prediction but face escalating computational costs as sequence length grows. Existing static pruning methods degrade performance by permanently removing…

While humans effortlessly draw visual objects and shapes by adaptively allocating attention based on their complexity, existing multimodal large language models (MLLMs) remain constrained by rigid token representations. Bridging this gap,…

In this paper, we study the problem of temporal video grounding (TVG), which aims to predict the starting/ending time points of moments described by a text sentence within a long untrimmed video. Benefiting from fine-grained 3D visual…

Multimodal large language models (MLLMs) often miss small details and spatial relations in cluttered scenes, leading to errors in fine-grained perceptual grounding. We introduce AttWarp, a lightweight method that allocates more resolution…

Vision-language models such as CLIP have shown impressive capabilities in aligning images and text, but they often struggle with lengthy and detailed text descriptions due to pre-training on short and concise captions. We present FAST-GOAL…

In the decentralized distributed learning, achieving fast convergence and low communication cost is essential for scalability and high efficiency. Adaptive gradient methods, such as Adam, have demonstrated strong practical performance in…

Network pruning is an effective technique for enabling lightweight Large Vision-Language Models (LVLMs), which primarily incorporates both weights and activations into the importance metric. However, existing efforts typically process…

Point management is critical for optimizing 3D Gaussian Splatting models, as point initiation (e.g., via structure from motion) is often distributionally inappropriate. Typically, Adaptive Density Control (ADC) algorithm is adopted,…

Video temporal grounding (VTG) is a critical task in video understanding and a key capability for extending video large language models (Vid-LLMs) to broader applications. However, existing Vid-LLMs rely on uniform frame sampling to extract…

Grounding natural language questions to functionally relevant regions in 3D objects -- termed language-driven 3D affordance grounding -- is essential for embodied intelligence and human-AI interaction. Existing methods, while progressing…

Automatic Speech Recognition (ASR) in dialect-heavy settings remains challenging due to strong regional variation and limited labeled data. We propose GLoRIA, a parameter-efficient adaptation framework that leverages metadata (e.g.,…

Temporal action proposal generation (TAPG) is a fundamental and challenging task in video understanding, especially in temporal action detection. Most previous works focus on capturing the local temporal context and can well locate simple…

Efficient vision-language understanding of large Remote Sensing Images (RSIs) is meaningful but challenging. Current Large Vision-Language Models (LVLMs) typically employ limited pre-defined grids to process images, leading to information…

Recent studies often exploit Graph Convolutional Network (GCN) to model label dependencies to improve recognition accuracy for multi-label image recognition. However, constructing a graph by counting the label co-occurrence possibilities of…

We present LatentAM, an online 3D Gaussian Splatting (3DGS) mapping framework that builds scalable latent feature maps from streaming RGB-D observations for open-vocabulary robotic perception. Instead of distilling high-dimensional…

Making large language models (LLMs) more efficient in memory, latency, and serving cost is crucial for edge deployment, interactive applications, and sustainable inference at scale. Pruning is a promising technique, but existing pruning…

Multimodal large language models (MLLMs) incur substantial inference cost due to the processing of hundreds of visual tokens per image. Although token pruning has proven effective for accelerating inference, determining when and where to…

Large language models (LLMs) struggle to effectively utilize a growing number of external tools, such as those defined by the Model Context Protocol (MCP)\cite{IntroducingMCP}, due to prompt bloat and selection complexity. We introduce…