13 accepted papers
Vision-Language Navigation (VLN) requires agents to follow natural language instructions by grounding them in sequential visual observations over long horizons. Explicit reasoning could enhance temporal consistency and perception–action alignment, but reasoning at fixed steps often leads to suboptim…
Current evaluation for Large Language Model (LLM) code agents predominantly focus on generating functional code in single-turn scenarios, which fails to evaluate the agent's capability for continuous code optimization and multi-turn iterative development. To bridge this gap, we introduce CATArena, a…
Quantization and cache mechanisms are typically applied individually in efficient generation tasks, each showing notable potential for acceleration. However, their joint effect on efficiency remains under-explored. Through both empirical investigation and theoretical analysis, we find that that comb…
Post-training quantization (PTQ) has played a pivotal role in compressing large language models (LLMs) at ultra-low costs. Although current PTQ methods have achieved promising results by addressing outliers and employing layer- or block-wise loss optimization techniques, they still suffer from signi…
Recent years have witnessed the great success of denoising diffusion samplers in improving the generative capability and sampling efficiency given a pre-trained diffusion model. However, most sampling schedulers in diffusion models lack the sampling dynamics and planning capability for future genera…
With the rise of real-world human-AI interaction applications, such as AI assistants, the need for Streaming Video Dialogue is critical. To address this need, we introduce StreamMind, a video LLM framework that achieves ultra-FPS streaming video processing (100 fps on a single A100) and enables proa…
Graph Neural Networks (GNNs) have shown remarkable success across various scientific fields, yet their adoption in critical decision-making is often hindered by a lack of interpretability. Recently, intrinsic interpretable GNNs have been studied to provide insights into model predictions by identify…
Recently, LLM-powered driver agents have demonstrated considerable potential in the field of autonomous driving, showcasing human-like reasoning and decision-making abilities. However, current research on aligning driver agent behaviors with human driving styles remains limited, partly due to the sc…
"Segment anything model (SAM) is a promising prompt-guided vision foundation model to segment objects of interest. However, the extensive computational requirements of SAM have limited its applicability in resource-constraint edge devices. Post-training quantization (PTQ) is an effective potential f…
Continuous Conditional Generative Adversarial Networks (CcGANs) enable generative modeling conditional on continuous scalar variables (termed regression labels). However, they can produce subpar fake images due to limited training data. Although Negative Data Augmentation (NDA) effectively enhances…
This work proposes the continuous conditional generative adversarial network (CcGAN), the first generative model for image generation conditional on continuous, scalar conditions (termed regression labels). Existing conditional GANs (cGANs) are mainly designed for categorical conditions (e.g., class…
In silicon sensors, the interference between visible and near-infrared (NIR) signals is a crucial problem. For all-day video surveillance, commercial camera systems usually adopt auxiliary NIR cut filter and NIR LED illumination to selectively block or enhance NIR signal according to the surrounding…
This paper focuses on the reconstruction of a tensor captured using Compressive Sensing (CS). Instead of processing the signals via vectorization as is done in conventional CS, in tensor CS high dimensional signals are kept in their original formats, which benefits hardware implementation and eases…