arXiv subjects

Yi Ma

Publications and source records attributed to Yi Ma.

At least 109 records · Page 6Linked to original sources

arXiv2025

Scaling White-Box Transformers for Vision

CRATE, a white-box transformer architecture designed to learn compressed and sparse representations, offers an intriguing alternative to standard vision transformers (ViTs) due to its inherent mathematical interpretability. Despite extensive investigations into the scaling behaviors of language and vision transformers, the scalability of CRATE remains an open question which this paper aims to address. Specifically, we propose CRATE-$α$, featuring strategic yet minimal modifications to the sparse coding block in the CRATE architecture design, and a light training recipe designed to improve the scalability of CRATE. Through extensive experiments, we demonstrate that CRATE-$α$ can effectively scale with larger model sizes and datasets. For example, our CRATE-$α$-B substantially outperforms the prior best CRATE-B model accuracy on ImageNet classification by 3.7%, achieving an accuracy of 83.2%. Meanwhile, when scaling further, our CRATE-$α$-L obtains an ImageNet classification accuracy of 85.1%. More notably, these model performance improvements are achieved while preserving, and potentially even enhancing the interpretability of learned CRATE models, as we demonstrate through showing that the learned token representations of increasingly larger trained CRATE-$α$ models yield increasingly higher-quality unsupervised object segmentation of images. The project page is https://rayjryang.github.io/CRATE-alpha/.

cs.CV↗

arXiv2025

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).

eess.SP↗

arXiv2025

ExPO: Explainable Phonetic Trait-Oriented Network for Speaker Verification

In speaker verification, we use computational method to verify if an utterance matches the identity of an enrolled speaker. This task is similar to the manual task of forensic voice comparison, where linguistic analysis is combined with auditory measurements to compare and evaluate voice samples. Despite much success, we have yet to develop a speaker verification system that offers explainable results comparable to those from manual forensic voice comparison. A novel approach, Explainable Phonetic Trait-Oriented (ExPO) network, is proposed in this paper to introduce the speaker's phonetic trait which describes the speaker's characteristics at the phonetic level, resembling what forensic comparison does. ExPO not only generates utterance-level speaker embeddings but also allows for fine-grained analysis and visualization of phonetic traits, offering an explainable speaker verification process. Furthermore, we investigate phonetic traits from within-speaker and between-speaker variation perspectives to determine which trait is most effective for speaker verification, marking an important step towards explainable speaker verification. Our code is available at https://github.com/mmmmayi/ExPO.

cs.SD↗

arXiv2025

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

In this paper, we propose a physical layer security (PLS) framework for an intelligent reflecting surface (IRS)-assisted integrated sensing and semantic communication (ISASC) system, where a multi-antenna dual-functional semantic base station (BS) serves multiple semantic communication users (SCUs) and monitors a potentially malicious sensing target (MST) in the presence of an eavesdropper (EVE). Both MST and EVE attempt to wiretap information from the signals transmitted to the SCUs. The deployment of the IRS not only enhances PLS by directing a strong beam towards the SCUs, but also improves the localization information for the target without disclosing information about the SCUs. To further strengthen PLS, we employ joint artificial noise (AN) and dedicated sensing signal (DSS), in addition to wiretap coding. To evaluate sensing accuracy, we derive the Cramer-Rao bound (CRB) for estimating the direction of arrival (DoA), and 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 between these two competing objectives, we formulate a multi-objective optimization problem (MOOP) for the joint design of the BS's beamforming (BF) vectors and the IRS's phase shift vector. To tackle this MOOP problem, the $ε$-constraint method is employed, followed by an alternating optimization (AO)-based algorithm that leverages the classical successive convex approximation (SCA) and semidefinite relaxation (SDR) techniques. Simulation results demonstrate that the proposed scheme outperforms the baseline schemes, achieving a superior trade-off between SSR and CRB. Specifically, our proposed approach improves the sensing accuracy by 5 dB compared to the commonly adopted maximal ratio transmission (MRT) approach.

eess.SP↗

arXiv2025

From Simple to Complex Skills: The Case of In-Hand Object Reorientation

Learning policies in simulation and transferring them to the real world has become a promising approach in dexterous manipulation. However, bridging the sim-to-real gap for each new task requires substantial human effort, such as careful reward engineering, hyperparameter tuning, and system identification. In this work, we present a system that leverages low-level skills to address these challenges for more complex tasks. Specifically, we introduce a hierarchical policy for in-hand object reorientation based on previously acquired rotation skills. This hierarchical policy learns to select which low-level skill to execute based on feedback from both the environment and the low-level skill policies themselves. Compared to learning from scratch, the hierarchical policy is more robust to out-of-distribution changes and transfers easily from simulation to real-world environments. Additionally, we propose a generalizable object pose estimator that uses proprioceptive information, low-level skill predictions, and control errors as inputs to estimate the object pose over time. We demonstrate that our system can reorient objects, including symmetrical and textureless ones, to a desired pose.

cs.RO↗

arXiv2024

Canonical Factors for Hybrid Neural Fields

Factored feature volumes offer a simple way to build more compact, efficient, and intepretable neural fields, but also introduce biases that are not necessarily beneficial for real-world data. In this work, we (1) characterize the undesirable biases that these architectures have for axis-aligned signals -- they can lead to radiance field reconstruction differences of as high as 2 PSNR -- and (2) explore how learning a set of canonicalizing transformations can improve representations by removing these biases. We prove in a two-dimensional model problem that simultaneously learning these transformations together with scene appearance succeeds with drastically improved efficiency. We validate the resulting architectures, which we call TILTED, using image, signed distance, and radiance field reconstruction tasks, where we observe improvements across quality, robustness, compactness, and runtime. Results demonstrate that TILTED can enable capabilities comparable to baselines that are 2x larger, while highlighting weaknesses of neural field evaluation procedures.

cs.CV↗

arXiv2024

Token Statistics Transformer: Linear-Time Attention via Variational Rate Reduction

The attention operator is arguably the key distinguishing factor of transformer architectures, which have demonstrated state-of-the-art performance on a variety of tasks. However, transformer attention operators often impose a significant computational burden, with the computational complexity scaling quadratically with the number of tokens. In this work, we propose a novel transformer attention operator whose computational complexity scales linearly with the number of tokens. We derive our network architecture by extending prior work which has shown that a transformer style architecture naturally arises by "white-box" architecture design, where each layer of the network is designed to implement an incremental optimization step of a maximal coding rate reduction objective (MCR$^2$). Specifically, we derive a novel variational form of the MCR$^2$ objective and show that the architecture that results from unrolled gradient descent of this variational objective leads to a new attention module called Token Statistics Self-Attention (TSSA). TSSA has linear computational and memory complexity and radically departs from the typical attention architecture that computes pairwise similarities between tokens. Experiments on vision, language, and long sequence tasks show that simply swapping TSSA for standard self-attention, which we refer to as the Token Statistics Transformer (ToST), achieves competitive performance with conventional transformers while being significantly more computationally efficient and interpretable. Our results also somewhat call into question the conventional wisdom that pairwise similarity style attention mechanisms are critical to the success of transformer architectures. Code will be available at https://github.com/RobinWu218/ToST.

cs.LG↗

arXiv2024

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 a device 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 hand estimation: the resulting kinematic and temporal constraints can reduce world-frame errors in single-frame estimates by 40%. Project page: https://egoallo.github.io/

cs.CV↗

arXiv2024

DeepFGS: Fine-Grained Scalable Coding for Learned Image Compression

Scalable coding, which can adapt to channel bandwidth variation, performs well in today's complex network environment. However, most existing scalable compression methods face two challenges: reduced compression performance and insufficient scalability. To overcome the above problems, this paper proposes a learned fine-grained scalable image compression framework, namely DeepFGS. Specifically, we introduce a feature separation backbone to divide the image information into basic and scalable features, then redistribute the features channel by channel through an information rearrangement strategy. In this way, we can generate a continuously scalable bitstream via one-pass encoding. For entropy coding, we design a mutual entropy model to fully explore the correlation between the basic and scalable features. In addition, we reuse the decoder to reduce the parameters and computational complexity. Experiments demonstrate that our proposed DeepFGS outperforms previous learning-based scalable image compression models and traditional scalable image codecs in both PSNR and MS-SSIM metrics.

eess.IV↗

arXiv2024

Differentially Private Representation Learning via Image Captioning

Differentially private (DP) machine learning is considered the gold-standard solution for training a model from sensitive data while still preserving privacy. However, a major barrier to achieving this ideal is its sub-optimal privacy-accuracy trade-off, which is particularly visible in DP representation learning. Specifically, it has been shown that under modest privacy budgets, most models learn representations that are not significantly better than hand-crafted features. In this work, we show that effective DP representation learning can be done via image captioning and scaling up to internet-scale multimodal datasets. Through a series of engineering tricks, we successfully train a DP image captioner (DP-Cap) on a 233M subset of LAION-2B from scratch using a reasonable amount of computation, and obtaining unprecedented high-quality image features that can be used in a variety of downstream vision and vision-language tasks. For example, under a privacy budget of $\varepsilon=8$ for the LAION dataset, a linear classifier trained on top of learned DP-Cap features attains $65.8\%$ accuracy on ImageNet-1K, considerably improving the previous SOTA of $56.5\%$.

cs.CV↗

arXiv2024

CleanDiffuser: An Easy-to-use Modularized Library for Diffusion Models in Decision Making

Leveraging the powerful generative capability of diffusion models (DMs) to build decision-making agents has achieved extensive success. However, there is still a demand for an easy-to-use and modularized open-source library that offers customized and efficient development for DM-based decision-making algorithms. In this work, we introduce CleanDiffuser, the first DM library specifically designed for decision-making algorithms. By revisiting the roles of DMs in the decision-making domain, we identify a set of essential sub-modules that constitute the core of CleanDiffuser, allowing for the implementation of various DM algorithms with simple and flexible building blocks. To demonstrate the reliability and flexibility of CleanDiffuser, we conduct comprehensive evaluations of various DM algorithms implemented with CleanDiffuser across an extensive range of tasks. The analytical experiments provide a wealth of valuable design choices and insights, reveal opportunities and challenges, and lay a solid groundwork for future research. CleanDiffuser will provide long-term support to the decision-making community, enhancing reproducibility and fostering the development of more robust solutions. The code and documentation of CleanDiffuser are open-sourced on the https://github.com/CleanDiffuserTeam/CleanDiffuser.

cs.AI↗

arXiv2024

Lessons from Learning to Spin "Pens"

In-hand manipulation of pen-like objects is an important skill in our daily lives, as many tools such as hammers and screwdrivers are similarly shaped. However, current learning-based methods struggle with this task due to a lack of high-quality demonstrations and the significant gap between simulation and the real world. In this work, we push the boundaries of learning-based in-hand manipulation systems by demonstrating the capability to spin pen-like objects. We first use reinforcement learning to train an oracle policy with privileged information and generate a high-fidelity trajectory dataset in simulation. This serves two purposes: 1) pre-training a sensorimotor policy in simulation; 2) conducting open-loop trajectory replay in the real world. We then fine-tune the sensorimotor policy using these real-world trajectories to adapt it to the real world dynamics. With less than 50 trajectories, our policy learns to rotate more than ten pen-like objects with different physical properties for multiple revolutions. We present a comprehensive analysis of our design choices and share the lessons learned during development.

cs.RO↗

arXiv2024

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.

cs.RO↗

arXiv2024

Generalizing Deep Learning-Based CSI Feedback in Massive MIMO via ID-Photo-Inspired Preprocessing

Deep learning (DL)-based channel state information (CSI) feedback has shown great potential in improving spectrum efficiency in massive MIMO systems. However, DL models optimized for specific environments often experience performance degradation in others due to model mismatch. To overcome this barrier in the practical deployment, we propose UniversalNet, an ID-photo-inspired universal CSI feedback framework that enhances model generalizability by standardizing the input format across diverse data distributions. Specifically, UniversalNet employs a standardized input format to mitigate the influence of environmental variability, coupled with a lightweight sparsity-aligning operation in the transformed sparse domain and marginal control bits for original format recovery. This enables seamless integration with existing CSI feedback models, requiring minimal modifications in preprocessing and postprocessing without updating neural network weights. Furthermore, we propose an efficient eigenvector joint optimization method to enhance the sparsity of the precoding matrix by projecting the channel correlation into the eigenspace, thus improving the implicit CSI compression efficiency. Test results demonstrate that UniversalNet effectively improves generalization performance and ensures precise CSI feedback, even in scenarios with limited training diversity and previously unseen CSI environments.

cs.IT↗

arXiv2024

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.

cs.RO↗

arXiv2024

Semantic-Aware Power Allocation for Generative Semantic Communications with Foundation Models

Recent advancements in diffusion models have made a significant breakthrough in generative modeling. The combination of the generative model and semantic communication (SemCom) enables high-fidelity semantic information exchange at ultra-low rates. A novel generative SemCom framework for image tasks is proposed, wherein pre-trained foundation models serve as semantic encoders and decoders for semantic feature extractions and image regenerations, respectively. The mathematical relationship between the transmission reliability and the perceptual quality of the regenerated image and the semantic values of semantic features are modeled, which are obtained by conducting numerical simulations on the Kodak dataset. We also investigate the semantic-aware power allocation problem, with the objective of minimizing the total power consumption while guaranteeing semantic performance. To solve this problem, two semanticaware power allocation methods are proposed by constraint decoupling and bisection search, respectively. Numerical results show that the proposed semantic-aware methods demonstrate superior performance compared to the conventional one in terms of total power consumption.

eess.SP↗

arXiv2024

Fine-Tuning Large Vision-Language Models as Decision-Making Agents via Reinforcement Learning

Large vision-language models (VLMs) fine-tuned on specialized visual instruction-following data have exhibited impressive language reasoning capabilities across various scenarios. However, this fine-tuning paradigm may not be able to efficiently learn optimal decision-making agents in multi-step goal-directed tasks from interactive environments. To address this challenge, we propose an algorithmic framework that fine-tunes VLMs with reinforcement learning (RL). Specifically, our framework provides a task description and then prompts the VLM to generate chain-of-thought (CoT) reasoning, enabling the VLM to efficiently explore intermediate reasoning steps that lead to the final text-based action. Next, the open-ended text output is parsed into an executable action to interact with the environment to obtain goal-directed task rewards. Finally, our framework uses these task rewards to fine-tune the entire VLM with RL. Empirically, we demonstrate that our proposed framework enhances the decision-making capabilities of VLM agents across various tasks, enabling 7b models to outperform commercial models such as GPT4-V or Gemini. Furthermore, we find that CoT reasoning is a crucial component for performance improvement, as removing the CoT reasoning results in a significant decrease in the overall performance of our method.

cs.AI↗

arXiv2024

Insight: A Multi-Modal Diagnostic Pipeline using LLMs for Ocular Surface Disease Diagnosis

Accurate diagnosis of ocular surface diseases is critical in optometry and ophthalmology, which hinge on integrating clinical data sources (e.g., meibography imaging and clinical metadata). Traditional human assessments lack precision in quantifying clinical observations, while current machine-based methods often treat diagnoses as multi-class classification problems, limiting the diagnoses to a predefined closed-set of curated answers without reasoning the clinical relevance of each variable to the diagnosis. To tackle these challenges, we introduce an innovative multi-modal diagnostic pipeline (MDPipe) by employing large language models (LLMs) for ocular surface disease diagnosis. We first employ a visual translator to interpret meibography images by converting them into quantifiable morphology data, facilitating their integration with clinical metadata and enabling the communication of nuanced medical insight to LLMs. To further advance this communication, we introduce a LLM-based summarizer to contextualize the insight from the combined morphology and clinical metadata, and generate clinical report summaries. Finally, we refine the LLMs' reasoning ability with domain-specific insight from real-life clinician diagnoses. Our evaluation across diverse ocular surface disease diagnosis benchmarks demonstrates that MDPipe outperforms existing standards, including GPT-4, and provides clinically sound rationales for diagnoses.

cs.CL↗