CAD-MLLM: Unifying Multimodality-Conditioned CAD Generation With MLLM

This paper aims to design a unified Computer-Aided Design (CAD) generation system that can easily generate CAD models based on the user's inputs in the form of textual description, images, point clouds, or even a combination of them. Towards this goal, we introduce the CAD-MLLM, the first system capable of generating parametric CAD models conditioned on the multimodal input. Specifically, within the CAD-MLLM framework, we leverage the command sequences of CAD models and then employ advanced large language models (LLMs) to align the feature space across these diverse multi-modalities data and CAD models' vectorized representations. To facilitate the model training, we design a comprehensive data construction and annotation pipeline that equips each CAD model with corresponding multimodal data. Our resulting dataset, named Omni-CAD, is the first multimodal CAD dataset that contains textual description, multi-view images, points, and command sequence for each CAD model. It contains approximately 450K instances and their CAD construction sequences. To thoroughly evaluate the quality of our generated CAD models, we go beyond current evaluation metrics that focus on reconstruction quality by introducing additional metrics that assess topology quality and surface enclosure extent. Extensive experimental results demonstrate that CAD-MLLM significantly outperforms existing conditional generative methods and remains highly robust to noises and missing points. The project page and more visualizations can be found at: https://cad-mllm.github.io/

Generative Semantic Communications with Foundation Models: Perception-Error Analysis and Semantic-Aware Power Allocation

Generative foundation models can revolutionize the design of semantic communication (SemCom) systems allowing high fidelity exchange of semantic information at ultra low rates. In this work, a generative SemCom framework with pretrained foundation models is proposed, where both uncoded forward-with-error and coded discard-with-error schemes are developed for the semantic decoder. To characterize the impact of transmission reliability on the perceptual quality of the regenerated signal, their mathematical relationship is analyzed from a rate-distortion-perception perspective, which is proved to be non-decreasing. The semantic values are defined to measure the semantic information of multimodal semantic features accordingly. We also investigate semantic-aware power allocation problems aiming at power consumption minimization for ultra low rate and high fidelity SemComs. To solve these problems, two semantic-aware power allocation methods are proposed by leveraging the non-decreasing property of the perception-error relationship. Numerically, perception-error functions and semantic values of semantic data streams under both schemes for image tasks are obtained based on the Kodak dataset. Simulation results show that our proposed semanticaware method significantly outperforms conventional approaches, particularly in the channel-coded case (up to 90% power saving).

Diffusion-based Generative Multicasting with Intent-aware Semantic Decomposition

Generative diffusion models (GDMs) have recently shown great success in synthesizing multimedia signals with high perceptual quality enabling highly efficient semantic communications in future wireless networks. In this paper, we develop an intent-aware generative semantic multicasting framework utilizing pre-trained diffusion models. In the proposed framework, the transmitter decomposes the source signal to multiple semantic classes based on the multi-user intent, i.e. each user is assumed to be interested in details of only a subset of the semantic classes. The transmitter then sends to each user only its intended classes, and multicasts a highly compressed semantic map to all users over shared wireless resources that allows them to locally synthesize the other classes, i.e. non-intended classes, utilizing pre-trained diffusion models. The signal retrieved at each user is thereby partially reconstructed and partially synthesized utilizing the received semantic map. This improves utilization of the wireless resources, with better preserving privacy of the non-intended classes. We design a communication/computation-aware scheme for per-class adaptation of the communication parameters, such as the transmission power and compression rate to minimize the total latency of retrieving signals at multiple receivers, tailored to the prevailing channel conditions as well as the users reconstruction/synthesis distortion/perception requirements. The simulation results demonstrate significantly reduced per-user latency compared with non-generative and intent-unaware multicasting benchmarks while maintaining high perceptual quality of the signals retrieved at the users.

Improving Neuron-level Interpretability with White-box Language Models

Neurons in auto-regressive language models like GPT-2 can be interpreted by analyzing their activation patterns. Recent studies have shown that techniques such as dictionary learning, a form of post-hoc sparse coding, enhance this neuron-level interpretability. In our research, we are driven by the goal to fundamentally improve neural network interpretability by embedding sparse coding directly within the model architecture, rather than applying it as an afterthought. In our study, we introduce a white-box transformer-like architecture named Coding RAte TransformEr (CRATE), explicitly engineered to capture sparse, low-dimensional structures within data distributions. Our comprehensive experiments showcase significant improvements (up to 103% relative improvement) in neuron-level interpretability across a variety of evaluation metrics. Detailed investigations confirm that this enhanced interpretability is steady across different layers irrespective of the model size, underlining CRATE's robust performance in enhancing neural network interpretability. Further analysis shows that CRATE's increased interpretability comes from its enhanced ability to consistently and distinctively activate on relevant tokens. These findings point towards a promising direction for creating white-box foundation models that excel in neuron-level interpretation.

On the Evaluation of Generative Robotic Simulations

Due to the difficulty of acquiring extensive real-world data, robot simulation has become crucial for parallel training and sim-to-real transfer, highlighting the importance of scalable simulated robotic tasks. Foundation models have demonstrated impressive capacities in autonomously generating feasible robotic tasks. However, this new paradigm underscores the challenge of adequately evaluating these autonomously generated tasks. To address this, we propose a comprehensive evaluation framework tailored to generative simulations. Our framework segments evaluation into three core aspects: quality, diversity, and generalization. For single-task quality, we evaluate the realism of the generated task and the completeness of the generated trajectories using large language models and vision-language models. In terms of diversity, we measure both task and data diversity through text similarity of task descriptions and world model loss trained on collected task trajectories. For task-level generalization, we assess the zero-shot generalization ability on unseen tasks of a policy trained with multiple generated tasks. Experiments conducted on three representative task generation pipelines demonstrate that the results from our framework are highly consistent with human evaluations, confirming the feasibility and validity of our approach. The findings reveal that while metrics of quality and diversity can be achieved through certain methods, no single approach excels across all metrics, suggesting a need for greater focus on balancing these different metrics. Additionally, our analysis further highlights the common challenge of low generalization capability faced by current works. Our anonymous website: https://sites.google.com/view/evaltasks.

A Physical Layer Security Framework for Integrated Sensing and Semantic Communication Systems

In this paper, we address a physical layer security (PLS) framework for the integrated sensing and semantic communication (ISASC) system, where a multi-antenna dual-function semantic base station serves multiple single-antenna semantic communication users (SCUs) and monitors a malicious sensing target (MST), in the presence of a single-antenna eavesdropper (EVE), with both the MST and EVE aiming to wiretap information from the SCUs' signals. To enhance PLS, we employ joint artificial noise (AN) and dedicated sensing signal (DSS) in addition to wiretap coding. To evaluate the sensing accuracy, we derive the Cramer-Rao bound (CRB) as a function of the communication, sensing, and AN beamforming (BF) vectors. Subsequently, to assess the PLS level of the ISASC system, we determine a closed-form expression for the semantic secrecy rate (SSR). To achieve an optimal trade-off region between these two competing objectives, we formulate a multi-objective optimization problem for the joint design of the BF vectors. We apply semi-definite programming, Gaussian randomization method, and golden-section search techniques to address this problem. Simulation results demonstrate that the proposed scheme outperforms baseline schemes, achieving a superior trade-off between SSR and CRB.

Estimating Body and Hand Motion in an Ego-sensed World

We present EgoAllo, a system for human motion estimation from a head-mounted device. Using only egocentric SLAM poses and images, EgoAllo guides sampling from a conditional diffusion model to estimate 3D body pose, height, and hand parameters that capture the wearer's actions in the allocentric coordinate frame of the scene. To achieve this, our key insight is in representation: we propose spatial and temporal invariance criteria for improving model performance, from which we derive a head motion conditioning parameterization that improves estimation by up to 18%. We also show how the bodies estimated by our system can improve the hands: the resulting kinematic and temporal constraints result in over 40% lower hand estimation errors compared to noisy monocular estimates. Project page: https://egoallo.github.io/

Closed-Loop Visuomotor Control with Generative Expectation for Robotic Manipulation

Despite significant progress in robotics and embodied AI in recent years, deploying robots for long-horizon tasks remains a great challenge. Majority of prior arts adhere to an open-loop philosophy and lack real-time feedback, leading to error accumulation and undesirable robustness. A handful of approaches have endeavored to establish feedback mechanisms leveraging pixel-level differences or pre-trained visual representations, yet their efficacy and adaptability have been found to be constrained. Inspired by classic closed-loop control systems, we propose CLOVER, a closed-loop visuomotor control framework that incorporates feedback mechanisms to improve adaptive robotic control. CLOVER consists of a text-conditioned video diffusion model for generating visual plans as reference inputs, a measurable embedding space for accurate error quantification, and a feedback-driven controller that refines actions from feedback and initiates replans as needed. Our framework exhibits notable advancement in real-world robotic tasks and achieves state-of-the-art on CALVIN benchmark, improving by 8% over previous open-loop counterparts. Code and checkpoints are maintained at https://github.com/OpenDriveLab/CLOVER.

Diffusion Models Learn Low-Dimensional Distributions via Subspace Clustering

Recent empirical studies have demonstrated that diffusion models can effectively learn the image distribution and generate new samples. Remarkably, these models can achieve this even with a small number of training samples despite a large image dimension, circumventing the curse of dimensionality. In this work, we provide theoretical insights into this phenomenon by leveraging key empirical observations: (i) the low intrinsic dimensionality of image data, (ii) a union of manifold structure of image data, and (iii) the low-rank property of the denoising autoencoder in trained diffusion models. These observations motivate us to assume the underlying data distribution of image data as a mixture of low-rank Gaussians and to parameterize the denoising autoencoder as a low-rank model according to the score function of the assumed distribution. With these setups, we rigorously show that optimizing the training loss of diffusion models is equivalent to solving the canonical subspace clustering problem over the training samples. Based on this equivalence, we further show that the minimal number of samples required to learn the underlying distribution scales linearly with the intrinsic dimensions under the above data and model assumptions. This insight sheds light on why diffusion models can break the curse of dimensionality and exhibit the phase transition in learning distributions. Moreover, we empirically establish a correspondence between the subspaces and the semantic representations of image data, facilitating image editing. We validate these results with corroborated experimental results on both simulated distributions and image datasets.

Fast Iterative ELAA-MIMO Detection Exploiting Static Channel Components

Extremely large aperture array (ELAA) is a promising multiple-input multiple-output (MIMO) technique for next generation mobile networks. In this paper, we propose two novel approaches to accelerate the convergence of current iterative MIMO detectors in ELAA channels. Our approaches exploit the static components of the ELAA channel, which include line of sight (LoS) paths and deterministic non-LoS (NLoS) components due to channel hardening effects. This paper proposes novel convergence acceleration techniques for fast iterative ELAA-MIMO detection by leveraging the static channel component, including the LoS paths and deterministic NLoS components that arise due to channel hardening. Specifically, these static channel components are utilized in two ways: as preconditioning matrices for general iterative algorithms, and as initialization for quasi-Newton (QN) methods. Simulation results show that the proposed approaches converge significantly faster compared to current iterative MIMO detectors, especially under strong LoS conditions with high Rician K-factor. Furthermore, QN methods with the proposed initialization matrix consistently achieve the best convergence performance while maintaining low complexity.