UVRM: A Scalable 3D Reconstruction Model from Unposed Videos

Large Reconstruction Models (LRMs) have recently become a popular method for creating 3D foundational models. Training 3D reconstruction models with 2D visual data traditionally requires prior knowledge of camera poses for the training samples, a process that is both time-consuming and prone to errors. Consequently, 3D reconstruction training has been confined to either synthetic 3D datasets or small-scale datasets with annotated poses. In this study, we investigate the feasibility of 3D reconstruction using unposed video data of various objects. We introduce UVRM, a novel 3D reconstruction model capable of being trained and evaluated on monocular videos without requiring any information about the pose. UVRM uses a transformer network to implicitly aggregate video frames into a pose-invariant latent feature space, which is then decoded into a tri-plane 3D representation. To obviate the need for ground-truth pose annotations during training, UVRM employs a combination of the score distillation sampling (SDS) method and an analysis-by-synthesis approach, progressively synthesizing pseudo novel-views using a pre-trained diffusion model. We qualitatively and quantitatively evaluate UVRM's performance on the G-Objaverse and CO3D datasets without relying on pose information. Extensive experiments show that UVRM is capable of effectively and efficiently reconstructing a wide range of 3D objects from unposed videos.

Foundation Model for Lossy Compression of Spatiotemporal Scientific Data

We present a foundation model (FM) for lossy scientific data compression, combining a variational autoencoder (VAE) with a hyper-prior structure and a super-resolution (SR) module. The VAE framework uses hyper-priors to model latent space dependencies, enhancing compression efficiency. The SR module refines low-resolution representations into high-resolution outputs, improving reconstruction quality. By alternating between 2D and 3D convolutions, the model efficiently captures spatiotemporal correlations in scientific data while maintaining low computational cost. Experimental results demonstrate that the FM generalizes well to unseen domains and varying data shapes, achieving up to 4 times higher compression ratios than state-of-the-art methods after domain-specific fine-tuning. The SR module improves compression ratio by 30 percent compared to simple upsampling techniques. This approach significantly reduces storage and transmission costs for large-scale scientific simulations while preserving data integrity and fidelity.

Understanding and Mitigating Memorization in Diffusion Models for Tabular Data

Tabular data generation has attracted significant research interest in recent years, with the tabular diffusion models greatly improving the quality of synthetic data. However, while memorization, where models inadvertently replicate exact or near-identical training data, has been thoroughly investigated in image and text generation, its effects on tabular data remain largely unexplored. In this paper, we conduct the first comprehensive investigation of memorization phenomena in diffusion models for tabular data. Our empirical analysis reveals that memorization appears in tabular diffusion models and increases with larger training epochs. We further examine the influence of factors such as dataset sizes, feature dimensions, and different diffusion models on memorization. Additionally, we provide a theoretical explanation for why memorization occurs in tabular diffusion models. To address this issue, we propose TabCutMix, a simple yet effective data augmentation technique that exchanges randomly selected feature segments between random same-class training sample pairs. Building upon this, we introduce TabCutMixPlus, an enhanced method that clusters features based on feature correlations and ensures that features within the same cluster are exchanged together during augmentation. This clustering mechanism mitigates out-of-distribution (OOD) generation issues by maintaining feature coherence. Experimental results across various datasets and diffusion models demonstrate that TabCutMix effectively mitigates memorization while maintaining high-quality data generation.

Safe Adaptive Cruise Control Under Perception Uncertainty: A Deep Ensemble and Conformal Tube Model Predictive Control Approach

Autonomous driving heavily relies on perception systems to interpret the environment for decision-making. To enhance robustness in these safety critical applications, this paper considers a Deep Ensemble of Deep Neural Network regressors integrated with Conformal Prediction to predict and quantify uncertainties. In the Adaptive Cruise Control setting, the proposed method performs state and uncertainty estimation from RGB images, informing the downstream controller of the DNN perception uncertainties. An adaptive cruise controller using Conformal Tube Model Predictive Control is designed to ensure probabilistic safety. Evaluations with a high-fidelity simulator demonstrate the algorithm's effectiveness in speed tracking and safe distance maintaining, including in Out-Of-Distribution scenarios.

Channel Customization for Low-Complexity CSI Acquisition in Multi-RIS-Assisted MIMO Systems

The deployment of multiple reconfigurable intelligent surfaces (RISs) enhances the propagation environment by improving channel quality, but it also complicates channel estimation. Following the conventional wireless communication system design, which involves full channel state information (CSI) acquisition followed by RIS configuration, can reduce transmission efficiency due to substantial pilot overhead and computational complexity. This study introduces an innovative approach that integrates CSI acquisition and RIS configuration, leveraging the channel-altering capabilities of the RIS to reduce both the overhead and complexity of CSI acquisition. The focus is on multi-RIS-assisted systems, featuring both direct and reflected propagation paths. By applying a fast-varying reflection sequence during RIS configuration for channel training, the complex problem of channel estimation is decomposed into simpler, independent tasks. These fast-varying reflections effectively isolate transmit signals from different paths, streamlining the CSI acquisition process for both uplink and downlink communications with reduced complexity. In uplink scenarios, a positioning-based algorithm derives partial CSI, informing the adjustment of RIS parameters to create a sparse reflection channel, enabling precise reconstruction of the uplink channel. Downlink communication benefits from this strategically tailored reflection channel, allowing effective CSI acquisition with fewer pilot signals. Simulation results highlight the proposed methodology's ability to accurately reconstruct the reflection channel with minimal impact on the normalized mean square error while simultaneously enhancing spectral efficiency.

FASTNav: Fine-tuned Adaptive Small-language-models Trained for Multi-point Robot Navigation

With the rapid development of large language models (LLM), robots are starting to enjoy the benefits of new interaction methods that large language models bring. Because edge computing fulfills the needs for rapid response, privacy, and network autonomy, we believe it facilitates the extensive deployment of large models for robot navigation across various industries. To enable local deployment of language models on edge devices, we adopt some model boosting methods. In this paper, we propose FASTNav - a method for boosting lightweight LLMs, also known as small language models (SLMs), for robot navigation. The proposed method contains three modules: fine-tuning, teacher-student iteration, and language-based multi-point robot navigation. We train and evaluate models with FASTNav in both simulation and real robots, proving that we can deploy them with low cost, high accuracy and low response time. Compared to other model compression methods, FASTNav shows potential in the local deployment of language models and tends to be a promising solution for language-guided robot navigation on edge devices.

ISAC Prototype System for Multi-Domain Cooperative Communication Networks

Future wireless networks are poised to transform into integrated sensing and communication (ISAC) networks, unlocking groundbreaking services such as digital twinning. To harness the full potential of ISAC networks, it is essential to experimentally validate their sensing capabilities and the role of sensing in boosting communication. However, current prototype systems fall short in supporting multiple sensing functions or validating sensing-assisted communication. In response, we have developed an advanced ISAC prototype system that incorporates monostatic, bistatic, and network sensing modes. This system supports multimodal data collection and synchronization, ensuring comprehensive experimental validation. On the communication front, it excels in sensing-aided beam tracking and real-time high-definition video transmission. For sensing applications, it provides precise angle and range measurements, real-time angle-range imaging, and radio-based simultaneous localization and mapping (SLAM). Our prototype aligns with the 5G New Radio standard, offering scalability for up to 16 user equipments (UEs) in uplink transmission and 10 UEs in downlink transmission. Real-world tests showcase the system's superior accuracy, with root mean square errors of 2.3 degrees for angle estimation and 0.3 meters (m) for range estimation. Additionally, the estimation errors for multimodal-aided real-time radio SLAM localization and mapping are 0.25 m and 0.8 m, respectively.

Joint User Scheduling and Precoding for RIS-Aided MU-MISO Systems: A MADRL Approach

With the increasing demand for spectrum efficiency and energy efficiency, reconfigurable intelligent surfaces (RISs) have attracted massive attention due to its low-cost and capability of controlling wireless environment. However, there is still a lack of treatments to deal with the growth of the number of users and RIS elements, which may incur performance degradation or computational complexity explosion. In this paper, we investigate the joint optimization of user scheduling and precoding for distributed RIS-aided communication systems. Firstly, we propose an optimization-based numerical method to obtain suboptimal solutions with the aid of the approximation of ergodic sum rate. Secondly, to reduce the computational complexity caused by the high dimensionality, we propose a data-driven scalable and generalizable multi-agent deep reinforcement learning (MADRL) framework with the aim to maximize the ergodic sum rate approximation through the cooperation of all agents. Further, we propose a novel dynamic working process exploiting the trained MADRL algorithm, which enables distributed RISs to configure their own passive precoding independently. Simulation results show that our algorithm substantially reduces the computational complexity by a time reduction of three orders of magnitude at the cost of 3% performance degradation, compared with the optimization-based method, and achieves 6% performance improvement over the state-of-the-art MADRL algorithms.

Faster-GCG: Efficient Discrete Optimization Jailbreak Attacks against Aligned Large Language Models

Aligned Large Language Models (LLMs) have demonstrated remarkable performance across various tasks. However, LLMs remain susceptible to jailbreak adversarial attacks, where adversaries manipulate prompts to elicit malicious responses that aligned LLMs should have avoided. Identifying these vulnerabilities is crucial for understanding the inherent weaknesses of LLMs and preventing their potential misuse. One pioneering work in jailbreaking is the GCG attack, a discrete token optimization algorithm that seeks to find a suffix capable of jailbreaking aligned LLMs. Despite the success of GCG, we find it suboptimal, requiring significantly large computational costs, and the achieved jailbreaking performance is limited. In this work, we propose Faster-GCG, an efficient adversarial jailbreak method by delving deep into the design of GCG. Experiments demonstrate that Faster-GCG can surpass the original GCG with only 1/10 of the computational cost, achieving significantly higher attack success rates on various open-source aligned LLMs. In addition, We demonstrate that Faster-GCG exhibits improved attack transferability when testing on closed-sourced LLMs such as ChatGPT.

HumanEval-V: Evaluating Visual Understanding and Reasoning Abilities of Large Multimodal Models Through Coding Tasks

Coding tasks have been valuable for evaluating Large Language Models (LLMs), as they demand the comprehension of high-level instructions, complex reasoning, and the implementation of functional programs -- core capabilities for advancing Artificial General Intelligence. Despite the progress in Large Multimodal Models (LMMs), which extend LLMs with visual perception and understanding capabilities, there remains a notable lack of coding benchmarks that rigorously assess these models, particularly in tasks that emphasize visual reasoning. To address this gap, we introduce HumanEval-V, a novel and lightweight benchmark specifically designed to evaluate LMMs' visual understanding and reasoning capabilities through code generation. HumanEval-V includes 108 carefully crafted, entry-level Python coding tasks derived from platforms like CodeForces and Stack Overflow. Each task is adapted by modifying the context and algorithmic patterns of the original problems, with visual elements redrawn to ensure distinction from the source, preventing potential data leakage. LMMs are required to complete the code solution based on the provided visual context and a predefined Python function signature outlining the task requirements. Every task is equipped with meticulously handcrafted test cases to ensure a thorough and reliable evaluation of model-generated solutions. We evaluate 19 state-of-the-art LMMs using HumanEval-V, uncovering significant challenges. Proprietary models like GPT-4o achieve only 13% pass@1 and 36.4% pass@10, while open-weight models with 70B parameters score below 4% pass@1. Ablation studies further reveal the limitations of current LMMs in vision reasoning and coding capabilities. These results underscore key areas for future research to enhance LMMs' capabilities. We have open-sourced our code and benchmark at https://github.com/HumanEval-V/HumanEval-V-Benchmark.