arXiv subjects

Jie Ren

Publications and source records attributed to Jie Ren.

At least 109 records · Page 6Linked to original sources

arXiv2024

FT-Shield: A Watermark Against Unauthorized Fine-tuning in Text-to-Image Diffusion Models

Text-to-image generative models, especially those based on latent diffusion models (LDMs), have demonstrated outstanding ability in generating high-quality and high-resolution images from textual prompts. With this advancement, various fine-tuning methods have been developed to personalize text-to-image models for specific applications such as artistic style adaptation and human face transfer. However, such advancements have raised copyright concerns, especially when the data are used for personalization without authorization. For example, a malicious user can employ fine-tuning techniques to replicate the style of an artist without consent. In light of this concern, we propose FT-Shield, a watermarking solution tailored for the fine-tuning of text-to-image diffusion models. FT-Shield addresses copyright protection challenges by designing new watermark generation and detection strategies. In particular, it introduces an innovative algorithm for watermark generation. It ensures the seamless transfer of watermarks from training images to generated outputs, facilitating the identification of copyrighted material use. To tackle the variability in fine-tuning methods and their impact on watermark detection, FT-Shield integrates a Mixture of Experts (MoE) approach for watermark detection. Comprehensive experiments validate the effectiveness of our proposed FT-Shield.

cs.CV↗

arXiv2024

Noiseless linear amplification-based quantum Ziv-Zakai bound for phase estimation and its Heisenberg error limits in noisy scenarios

In this work, we address the central problem about how to effectively find the available precision limit of unknown parameters. In the framework of the quantum Ziv-Zakai bound (QZZB), we employ noiseless linear amplification (NLA)techniques to an initial coherent state (CS) as the probe state, and focus on whether the phase estimation performance is improved significantly in noisy scenarios, involving the photon-loss and phase-diffusion cases. More importantly, we also obtain two kinds of Heisenberg error limits of the QZZB with the NLA-based CS in these noisy scenarios, making comparisons with both the Margolus-Levitin (ML) type bound and the Mandelstam-Tamm (MT) type bound. Our analytical results show that in cases of photon loss and phase diffusion, the phase estimation performance of the QZZB can be improved remarkably by increasing the NLA gain factor. Particularly, the improvement is more pronounced with severe photon losses. Furthermore in minimal photon losses, our Heisenberg error limit shows better compactness than the cases of the ML-type and MT-type bounds. Our findings will provide an useful guidance for accomplishing more complex quantum information processing tasks.

quant-ph↗

arXiv2024

Proceedings of 3rd Workshop on Heterogeneous Composable and Disaggregated Systems

The future of computing systems is inevitably embracing a disaggregated and composable pattern: from clusters of computers to pools of resources that can be dynamically combined together and tailored around applications requirements. Transitioning to this new paradigm requires ground-breaking research, ranging from new hardware architectures up to new models and abstractions at all levels of the software stack. Recent hardware advancements in CPU and interconnection technologies, enabled the possibility of disaggregating peripherals and system memory. The memory system heterogeneity is further increasing, composability and disaggregation are beneficial to increase memory capacity and improve memory utilization in a cost-effective way, and reduce total cost of ownership. Heterogeneous and Composable Disaggregated Systems (HCDS) provide a system design approach for reducing the imbalance between workloads resource requirements and the static availability of resources in a computing system. The HCDS workshop aims at exploring the novel research ideas around composable disaggregated systems and their integration with operating systems and software runtimes to maximize the benefit perceived from user workloads.

cs.DC↗

arXiv2024

MLDT: Multi-Level Decomposition for Complex Long-Horizon Robotic Task Planning with Open-Source Large Language Model

In the realm of data-driven AI technology, the application of open-source large language models (LLMs) in robotic task planning represents a significant milestone. Recent robotic task planning methods based on open-source LLMs typically leverage vast task planning datasets to enhance models' planning abilities. While these methods show promise, they struggle with complex long-horizon tasks, which require comprehending more context and generating longer action sequences. This paper addresses this limitation by proposing MLDT, theMulti-Level Decomposition Task planning method. This method innovatively decomposes tasks at the goal-level, task-level, and action-level to mitigate the challenge of complex long-horizon tasks. In order to enhance open-source LLMs' planning abilities, we introduce a goal-sensitive corpus generation method to create high-quality training data and conduct instruction tuning on the generated corpus. Since the complexity of the existing datasets is not high enough, we construct a more challenging dataset, LongTasks, to specifically evaluate planning ability on complex long-horizon tasks. We evaluate our method using various LLMs on four datasets in VirtualHome. Our results demonstrate a significant performance enhancement in robotic task planning, showcasing MLDT's effectiveness in overcoming the limitations of existing methods based on open-source LLMs as well as its practicality in complex, real-world scenarios.

cs.RO↗

arXiv2024

A Robust Semantics-based Watermark for Large Language Model against Paraphrasing

Large language models (LLMs) have show great ability in various natural language tasks. However, there are concerns that LLMs are possible to be used improperly or even illegally. To prevent the malicious usage of LLMs, detecting LLM-generated text becomes crucial in the deployment of LLM applications. Watermarking is an effective strategy to detect the LLM-generated content by encoding a pre-defined secret watermark to facilitate the detection process. However, the majority of existing watermark methods leverage the simple hashes of precedent tokens to partition vocabulary. Such watermark can be easily eliminated by paraphrase and correspondingly the detection effectiveness will be greatly compromised. Thus, to enhance the robustness against paraphrase, we propose a semantics-based watermark framework SemaMark. It leverages the semantics as an alternative to simple hashes of tokens since the paraphrase will likely preserve the semantic meaning of the sentences. Comprehensive experiments are conducted to demonstrate the effectiveness and robustness of SemaMark under different paraphrases.

cs.CR↗

arXiv2024

A Theoretical Understanding of Gradient Bias in Meta-Reinforcement Learning

Gradient-based Meta-RL (GMRL) refers to methods that maintain two-level optimisation procedures wherein the outer-loop meta-learner guides the inner-loop gradient-based reinforcement learner to achieve fast adaptations. In this paper, we develop a unified framework that describes variations of GMRL algorithms and points out that existing stochastic meta-gradient estimators adopted by GMRL are actually \textbf{biased}. Such meta-gradient bias comes from two sources: 1) the compositional bias incurred by the two-level problem structure, which has an upper bound of $\mathcal{O}\big(Kα^{K}\hatσ_{\text{In}}|τ|^{-0.5}\big)$ \emph{w.r.t.} inner-loop update step $K$, learning rate $α$, estimate variance $\hatσ^{2}_{\text{In}}$ and sample size $|τ|$, and 2) the multi-step Hessian estimation bias $\hatΔ_{H}$ due to the use of autodiff, which has a polynomial impact $\mathcal{O}\big((K-1)(\hatΔ_{H})^{K-1}\big)$ on the meta-gradient bias. We study tabular MDPs empirically and offer quantitative evidence that testifies our theoretical findings on existing stochastic meta-gradient estimators. Furthermore, we conduct experiments on Iterated Prisoner's Dilemma and Atari games to show how other methods such as off-policy learning and low-bias estimator can help fix the gradient bias for GMRL algorithms in general.

cs.LG↗

arXiv2024

Thermodynamic Geometry of Nonequilibrium Fluctuations in Cyclically Driven Transport

Nonequilibrium thermal machines under cyclic driving generally outperform steady-state counterparts. However, there is still lack of coherent understanding of versatile transport and fluctuation features under time modulations. Here, we formulate a theoretical framework of thermodynamic geometry in terms of full counting statistics of nonequilibrium driven transports. We find that, besides the conventional dynamic and adiabatic geometric curvature contributions, the generating function is divided into an additional nonadiabatic contribution, manifested as the metric term of full counting statistics. This nonadiabatic metric generalizes recent results of thermodynamic geometry in near-equilibrium entropy production to far-from-equilibrium fluctuations of general currents. Furthermore, the framework proves geometric thermodynamic uncertainty relations of near-adiabatic thermal devices, constraining fluctuations in terms of statistical metric quantities. We exemplify the theory in experimentally accessible driving-induced quantum chiral transport and Brownian heat pump.

cond-mat.stat-mech↗

arXiv2024

Coherence-enhanced thermodynamic performance in a periodically-driven inelastic heat engine

Quantum thermodynamics with microscopic inelastic scattering processes has been intensively investigated in recent years. Here, we apply quantum master equation combined with full counting statistics approach to investigate the role of quantum coherence on the periodically-driven inelastic heat engine. We demonstrate that the inelastic quantum heat engine exhibits dramatic advantage of thermodynamic performance compared to their elastic counterpart. Moreover, it is found that inelastic currents, {output work}, and the efficiency can be enhanced by quantum coherence. In particular, the geometric effect proves crucial in achieving maximal values of generated output work and energy conversion efficiency. The Berry curvature boosted by quantum coherence unveils the underlying mechanism of periodically-driven inelastic heat engine. Our findings may provide some insights for further understanding and optimizing periodically-driven heat engines via quantum coherence resource and inelastic scattering processes.

cond-mat.mes-hall↗

arXiv2024

The Good and The Bad: Exploring Privacy Issues in Retrieval-Augmented Generation (RAG)

Retrieval-augmented generation (RAG) is a powerful technique to facilitate language model with proprietary and private data, where data privacy is a pivotal concern. Whereas extensive research has demonstrated the privacy risks of large language models (LLMs), the RAG technique could potentially reshape the inherent behaviors of LLM generation, posing new privacy issues that are currently under-explored. In this work, we conduct extensive empirical studies with novel attack methods, which demonstrate the vulnerability of RAG systems on leaking the private retrieval database. Despite the new risk brought by RAG on the retrieval data, we further reveal that RAG can mitigate the leakage of the LLMs' training data. Overall, we provide new insights in this paper for privacy protection of retrieval-augmented LLMs, which benefit both LLMs and RAG systems builders. Our code is available at https://github.com/phycholosogy/RAG-privacy.

cs.CR↗

arXiv2024

Exploring Memorization in Fine-tuned Language Models

Large language models (LLMs) have shown great capabilities in various tasks but also exhibited memorization of training data, raising tremendous privacy and copyright concerns. While prior works have studied memorization during pre-training, the exploration of memorization during fine-tuning is rather limited. Compared to pre-training, fine-tuning typically involves more sensitive data and diverse objectives, thus may bring distinct privacy risks and unique memorization behaviors. In this work, we conduct the first comprehensive analysis to explore language models' (LMs) memorization during fine-tuning across tasks. Our studies with open-sourced and our own fine-tuned LMs across various tasks indicate that memorization presents a strong disparity among different fine-tuning tasks. We provide an intuitive explanation of this task disparity via sparse coding theory and unveil a strong correlation between memorization and attention score distribution.

cs.AI↗

arXiv2024

A novel spatial-frequency domain network for zero-shot incremental learning

Zero-shot incremental learning aims to enable the model to generalize to new classes without forgetting previously learned classes. However, the semantic gap between old and new sample classes can lead to catastrophic forgetting. Additionally, existing algorithms lack capturing significant information from each sample image domain, impairing models' classification performance. Therefore, this paper proposes a novel Spatial-Frequency Domain Network (SFDNet) which contains a Spatial-Frequency Feature Extraction (SFFE) module and Attention Feature Alignment (AFA) module to improve the Zero-Shot Translation for Class Incremental algorithm. Firstly, SFFE module is designed which contains a dual attention mechanism for obtaining salient spatial-frequency feature information. Secondly, a novel feature fusion module is conducted for obtaining fused spatial-frequency domain features. Thirdly, the Nearest Class Mean classifier is utilized to select the most suitable category. Finally, iteration between tasks is performed using the Zero-Shot Translation model. The proposed SFDNet has the ability to effectively extract spatial-frequency feature representation from input images, improve the accuracy of image classification, and fundamentally alleviate catastrophic forgetting. Extensive experiments on the CUB 200-2011 and CIFAR100 datasets demonstrate that our proposed algorithm outperforms state-of-the-art incremental learning algorithms.

cs.CV↗

arXiv2024

Well-posedness and propagation of chaos for jump-type McKean-Vlasov SDEs with irregular coefficients

In this paper, we study the existence and pathwise uniqueness of strong solutions for jump-type McKean-Vlasov SDEs with irregular coefficients but uniform linear growth assumption. Moreover, the propagation of chaos and the convergence rate for Euler's scheme of jump-type McKean-Vlasov SDEs are also obtained by taking advantage of Yamada-Watanabe's approximation approach and stopping time.

math.PR↗

arXiv2024

Superiority of Multi-Head Attention in In-Context Linear Regression

We present a theoretical analysis of the performance of transformer with softmax attention in in-context learning with linear regression tasks. While the existing literature predominantly focuses on the convergence of transformers with single-/multi-head attention, our research centers on comparing their performance. We conduct an exact theoretical analysis to demonstrate that multi-head attention with a substantial embedding dimension performs better than single-head attention. When the number of in-context examples D increases, the prediction loss using single-/multi-head attention is in O(1/D), and the one for multi-head attention has a smaller multiplicative constant. In addition to the simplest data distribution setting, we consider more scenarios, e.g., noisy labels, local examples, correlated features, and prior knowledge. We observe that, in general, multi-head attention is preferred over single-head attention. Our results verify the effectiveness of the design of multi-head attention in the transformer architecture.

cs.LG↗

arXiv2024

Critical Cohomological Hall Algebra and Edge Contraction

We study the behaviors of cohomological Hall algebras and relevant subjects under an edge contraction. Given a quiver with potential and fix an arrow, the edge contraction is a way to construct a new quiver with potential. We show that there is an algebra homomorphism between the cohomological Hall algebras induced by the edge contraction, which preserves the Hopf algebra structure, Drinfeld double, mutation, and the dimensional reduction, and induces relations between scattering diagram and Donaldson-Thomas series.

math.AG↗

arXiv2024

Calabi-Yau categories and graded quivers with potential

We prove that the equivalence classes of d-dimensional Calabi-Yau $A_\infty$-categories (dCY category for short) of certain type are in one-to-one correspondence with the gauge equivalence classes of graded quivers with potential.

math.AG↗

arXiv2024

Machine Learning of Knot Topology in Non-Hermitian Band Braids

The deep connection among braids, knots and topological physics has provided valuable insights into studying topological states in various physical systems. However, identifying distinct braid groups and knot topology embedded in non-Hermitian systems is challenging and requires significant efforts. Here, we demonstrate that an unsupervised learning with the representation basis of $su(n)$ Lie algebra on $n$-fold extended non-Hermitian bands can fully classify braid group and knot topology therein, without requiring any prior mathematical knowledge or any pre-defined topological invariants. We demonstrate that the approach successfully identifies different topological elements, such as unlink, unknot, Hopf link, Solomon ring, trefoil, and so on, by employing generalized Gell-Mann matrices in non-Hermitian models with $n$=2 and $n$=3 energy bands. Moreover, since eigenstate information of non-Hermitian bands is incorporated in addition to eigenvalues, the approach distinguishes the different parity-time symmetry and breaking phases, recognizes the opposite chirality of braids and knots, and identifies out distinct topological phases that were overlooked before. Our study shows significant potential of machine learning in classification of knots, braid groups, and non-Hermitian topological phases.

cond-mat.mes-hall↗

arXiv2024

Spin-Transfer-Torque Induced Spatially Nonuniform Switching in Ferrimagnets

Ferrimagnet (FiM), (FeCo)1-xGdx, attracts research attention due to its ultrafast magnetic dynamics and finite net magnetization. Incorporating FiM into the magnetic tunnel junction will be beneficial to further improve the writing speed of magnetic random access memory (MRAM). It is commonly assumed that the FeCo and Gd atoms are switched together due to the strong exchange coupling, which remains valid even if one performs the two-sublattice macrospin simulation. Interestingly, using the atomistic model developed by our group, it is clearly seen that different atoms are not switched together. In addition, our study reveals that the nature of switching is spatially nonuniform even in the small sample with the dimension of 20 nm-20 nm. Furthermore, the characteristics of nonuniformity are completely different for samples with different Gd composition (x). When x is close to the magnetization compensation point, successful switching cannot be obtained, but is accompanied by the stable oscillation. The atom type that dominates the oscillation is different from that predicted by the two-sublattice macrospin model. In addition, the size of singular region is a non-monotonic function of current density. All these results can only be understood by considering the spatial nonuniform magnetization dynamics.

cond-mat.mes-hall↗

arXiv2023

Superdiffusive Transport in Quasi-Particle Dephasing Models

Investigating the behavior of noninteracting fermions subjected to local dephasing, we reveal that quasi-particle dephasing can induce superdiffusive transport. This superdiffusion arises from nodal points within the momentum distribution of local dephasing quasi-particles, leading to asymptotic long-lived modes. By studying the dynamics of the Wigner function, we rigorously elucidate how the dynamics of these enduring modes give rise to Lévy walk processes, a renowned mechanism underlying superdiffusion phenomena. Our research demonstrates the controllability of dynamical scaling exponents by selecting quasi-particles and extends its applicability to higher dimensions, underlining the pervasive nature of superdiffusion in dephasing models.

cond-mat.stat-mech↗