Video Coding with Cross-Component Sample Offset

Beyond the exploration of traditional spatial, temporal and subjective visual signal redundancy in image and video compression, recent research has focused on leveraging cross-color component redundancy to enhance coding efficiency. Cross-component coding approaches are motivated by the statistical correlations among different color components, such as those in the Y'CbCr color space, where luma (Y) color component typically exhibits finer details than chroma (Cb/Cr) color components. Inspired by previous cross-component coding algorithms, this paper introduces a novel in-loop filtering approach named Cross-Component Sample Offset (CCSO). CCSO utilizes co-located and neighboring luma samples to generate correction signals for both luma and chroma reconstructed samples. It is a multiplication-free, non-linear mapping process implemented using a look-up-table. The input to the mapping is a group of reconstructed luma samples, and the output is an offset value applied on the center luma or co-located chroma sample. Experimental results demonstrate that the proposed CCSO can be applied to both image and video coding, resulting in improved coding efficiency and visual quality. The method has been adopted into an experimental next-generation video codec beyond AV1 developed by the Alliance for Open Media (AOMedia), achieving significant objective coding gains up to 3.5\,\% and 1.8\,\% for PSNR and VMAF quality metrics, respectively, under random access configuration. Additionally, CCSO notably improves the subjective visual quality.

Partial train and isolate, mitigate backdoor attack

Neural networks are widely known to be vulnerable to backdoor attacks, a method that poisons a portion of the training data to make the target model perform well on normal data sets, while outputting attacker-specified or random categories on the poisoned samples. Backdoor attacks are full of threats. Poisoned samples are becoming more and more similar to corresponding normal samples, and even the human eye cannot easily distinguish them. On the other hand, the accuracy of models carrying backdoors on normal samples is no different from that of clean models.In this article, by observing the characteristics of backdoor attacks, We provide a new model training method (PT) that freezes part of the model to train a model that can isolate suspicious samples. Then, on this basis, a clean model is fine-tuned to resist backdoor attacks.

Grounding DINO 1.5: Advance the "Edge" of Open-Set Object Detection

This paper introduces Grounding DINO 1.5, a suite of advanced open-set object detection models developed by IDEA Research, which aims to advance the "Edge" of open-set object detection. The suite encompasses two models: Grounding DINO 1.5 Pro, a high-performance model designed for stronger generalization capability across a wide range of scenarios, and Grounding DINO 1.5 Edge, an efficient model optimized for faster speed demanded in many applications requiring edge deployment. The Grounding DINO 1.5 Pro model advances its predecessor by scaling up the model architecture, integrating an enhanced vision backbone, and expanding the training dataset to over 20 million images with grounding annotations, thereby achieving a richer semantic understanding. The Grounding DINO 1.5 Edge model, while designed for efficiency with reduced feature scales, maintains robust detection capabilities by being trained on the same comprehensive dataset. Empirical results demonstrate the effectiveness of Grounding DINO 1.5, with the Grounding DINO 1.5 Pro model attaining a 54.3 AP on the COCO detection benchmark and a 55.7 AP on the LVIS-minival zero-shot transfer benchmark, setting new records for open-set object detection. Furthermore, the Grounding DINO 1.5 Edge model, when optimized with TensorRT, achieves a speed of 75.2 FPS while attaining a zero-shot performance of 36.2 AP on the LVIS-minival benchmark, making it more suitable for edge computing scenarios. Model examples and demos with API will be released at https://github.com/IDEA-Research/Grounding-DINO-1.5-API

DIG3D: Marrying Gaussian Splatting with Deformable Transformer for Single Image 3D Reconstruction

In this paper, we study the problem of 3D reconstruction from a single-view RGB image and propose a novel approach called DIG3D for 3D object reconstruction and novel view synthesis. Our method utilizes an encoder-decoder framework which generates 3D Gaussians in decoder with the guidance of depth-aware image features from encoder. In particular, we introduce the use of deformable transformer, allowing efficient and effective decoding through 3D reference point and multi-layer refinement adaptations. By harnessing the benefits of 3D Gaussians, our approach offers an efficient and accurate solution for 3D reconstruction from single-view images. We evaluate our method on the ShapeNet SRN dataset, getting PSNR of 24.21 and 24.98 in car and chair dataset, respectively. The result outperforming the recent method by around 2.25%, demonstrating the effectiveness of our method in achieving superior results.

ASPIRe: An Informative Trajectory Planner with Mutual Information Approximation for Target Search and Tracking

This paper proposes an informative trajectory planning approach, namely, \textit{adaptive particle filter tree with sigma point-based mutual information reward approximation} (ASPIRe), for mobile target search and tracking (SAT) in cluttered environments with limited sensing field of view. We develop a novel sigma point-based approximation to accurately estimate mutual information (MI) for general, non-Gaussian distributions utilizing particle representation of the belief state, while simultaneously maintaining high computational efficiency. Building upon the MI approximation, we develop the Adaptive Particle Filter Tree (APFT) approach with MI as the reward, which features belief state tree nodes for informative trajectory planning in continuous state and measurement spaces. An adaptive criterion is proposed in APFT to adjust the planning horizon based on the expected information gain. Simulations and physical experiments demonstrate that ASPIRe achieves real-time computation and outperforms benchmark methods in terms of both search efficiency and estimation accuracy.

IntactKV: Improving Large Language Model Quantization by Keeping Pivot Tokens Intact

Large language models (LLMs) excel in natural language processing but demand intensive computation. To mitigate this, various quantization methods have been explored, yet they compromise LLM performance. This paper unveils a previously overlooked type of outlier in LLMs. Such outliers are found to allocate most of the attention scores on initial tokens of input, termed as pivot tokens, which is crucial to the performance of quantized LLMs. Given that, we propose IntactKV to generate the KV cache of pivot tokens losslessly from the full-precision model. The approach is simple and easy to combine with existing quantization solutions. Besides, IntactKV can be calibrated as additional LLM parameters to boost the quantized LLMs further. Mathematical analysis also proves that IntactKV effectively reduces the upper bound of quantization error. Empirical results show that IntactKV brings consistent improvement and achieves lossless weight-only INT4 quantization on various downstream tasks, leading to the new state-of-the-art for LLM quantization.

Generative Learning for Forecasting the Dynamics of Complex Systems

We introduce generative models for accelerating simulations of complex systems through learning and evolving their effective dynamics. In the proposed Generative Learning of Effective Dynamics (G-LED), instances of high dimensional data are down sampled to a lower dimensional manifold that is evolved through an auto-regressive attention mechanism. In turn, Bayesian diffusion models, that map this low-dimensional manifold onto its corresponding high-dimensional space, capture the statistics of the system dynamics. We demonstrate the capabilities and drawbacks of G-LED in simulations of several benchmark systems, including the Kuramoto-Sivashinsky (KS) equation, two-dimensional high Reynolds number flow over a backward-facing step, and simulations of three-dimensional turbulent channel flow. The results demonstrate that generative learning offers new frontiers for the accurate forecasting of the statistical properties of complex systems at a reduced computational cost.

SwarmPRM: Probabilistic Roadmap Motion Planning for Swarm Robotic Systems

Swarm robotic systems consisting of large-scale cooperative agents hold promise for performing autonomous tasks in diverse fields. However, existing planning strategies for swarm robotic systems often encounter a trade-off between scalability and solution quality. We introduce here SwarmPRM, a hierarchical, highly scalable, computationally efficient, and risk-aware sampling-based motion planning approach for swarm robotic systems, which is asymptotically optimal under mild assumptions. We employ probability density functions (PDFs) to represent the swarm's macroscopic state and utilize optimal mass transport (OMT) theory to measure the swarm's cost to go. A risk-aware Gaussian roadmap is constructed wherein each node encapsulates a distinct PDF and conditional-value-at-risk (CVaR) is employed to assess the collision risk, facilitating the generation of macroscopic PDFs in Wasserstein-GMM space. Extensive simulations demonstrate that the proposed approach outperforms state-of-the-art methods in terms of computational efficiency and the average travelling distance.

ROVER: Risk-Aware Swarm Robotics MOtion Planner Using Conditional ValuE at Risk

The field of swarm robotics has attracted considerable interest for its capacity to complete intricate and synchronized tasks. Existing methodologies for motion planning within swarm robotic systems mainly encounter difficulties in scalability and safety guarantee. To address these two limitations, we propose a Risk-aware swarm mOtion planner using conditional ValuE at Risk (ROVER) that systematically modulates the safety and conservativeness and navigates the swarm to the target area through cluttered environments. Our approach formulates a finite-time model predictive control (FTMPC) problem predicated upon the macroscopic state of the robot swarm represented by Gaussian Mixture Model (GMM) and integrates conditional value-at-risk (CVaR) to avoid collision. We leverage the linearized Signed Distance Function for the efficient computation of CVaR concerning the proximity between the robot swarm to obstacles. The key component of this method is implementing CVaR constraint under GMM uncertainty in the FTMPC to measure the collision risk that a robot swarm faces. However, the non-convex constrained FTMPC is nontrival to solve. To navigate this complexity, we develop a computationally tractable strategy through 1) an explicit linear approximation of the CVaR constraint; and 2) a sequential quadratic programming formulation. Simulations and comparisons with other approaches demonstrate the effectiveness of the proposed method in flexibility, scalability, and risk mitigation.

The Development of LLMs for Embodied Navigation

In recent years, the rapid advancement of Large Language Models (LLMs) such as the Generative Pre-trained Transformer (GPT) has attracted increasing attention due to their potential in a variety of practical applications. The application of LLMs with Embodied Intelligence has emerged as a significant area of focus. Among the myriad applications of LLMs, navigation tasks are particularly noteworthy because they demand a deep understanding of the environment and quick, accurate decision-making. LLMs can augment embodied intelligence systems with sophisticated environmental perception and decision-making support, leveraging their robust language and image-processing capabilities. This article offers an exhaustive summary of the symbiosis between LLMs and embodied intelligence with a focus on navigation. It reviews state-of-the-art models, research methodologies, and assesses the advantages and disadvantages of existing embodied navigation models and datasets. Finally, the article elucidates the role of LLMs in embodied intelligence, based on current research, and forecasts future directions in the field. A comprehensive list of studies in this survey is available at https://github.com/Rongtao-Xu/Awesome-LLM-EN