arXiv subjects

Yue Yu

Publications and source records attributed to Yue Yu.

At least 199 records · Page 11Linked to original sources

arXiv2024

COPR: Continual Human Preference Learning via Optimal Policy Regularization

Reinforcement Learning from Human Feedback (RLHF) is commonly utilized to improve the alignment of Large Language Models (LLMs) with human preferences. Given the evolving nature of human preferences, continual alignment becomes more crucial and practical in comparison to traditional static alignment. Nevertheless, making RLHF compatible with Continual Learning (CL) is challenging due to its complex process. Meanwhile, directly learning new human preferences may lead to Catastrophic Forgetting (CF) of historical preferences, resulting in helpless or harmful outputs. To overcome these challenges, we propose the Continual Optimal Policy Regularization (COPR) method, which draws inspiration from the optimal policy theory. COPR utilizes a sampling distribution as a demonstration and regularization constraints for CL. It adopts the Lagrangian Duality (LD) method to dynamically regularize the current policy based on the historically optimal policy, which prevents CF and avoids over-emphasizing unbalanced objectives. We also provide formal proof for the learnability of COPR. The experimental results show that COPR outperforms strong CL baselines on our proposed benchmark, in terms of reward-based, GPT-4 evaluations and human assessment. Furthermore, we validate the robustness of COPR under various CL settings, including different backbones, replay memory sizes, and learning orders.

cs.LG↗

arXiv2024

Correcting Large Language Model Behavior via Influence Function

Recent advancements in AI alignment techniques have significantly improved the alignment of large language models (LLMs) with static human preferences. However, the dynamic nature of human preferences can render some prior training data outdated or even erroneous, ultimately causing LLMs to deviate from contemporary human preferences and societal norms. Existing methodologies, whether they involve the curation of new data for continual alignment or the manual correction of outdated data for re-alignment, demand costly human resources. To address this challenge, we propose a novel approach, Large Language Model Behavior Correction with Influence Function Recall and Post-Training (LANCET), which requires no human involvement. LANCET consists of two phases: (1) using influence functions to identify the training data that significantly impact undesirable model outputs, and (2) applying an Influence function-driven Bregman Optimization (IBO) technique to adjust the model's behavior based on these influence distributions. Our experiments demonstrate that LANCET effectively and efficiently correct inappropriate behaviors of LLMs. Furthermore, LANCET can outperform methods that rely on collecting human preferences, and it enhances the interpretability of learning human preferences within LLMs.

cs.LG↗

arXiv2024

A mechanical quantum memory for microwave photons

Long-lived mechanical oscillators are actively pursued as critical resources for quantum storage, sensing, and transduction. However, achieving deterministic quantum control while limiting mechanical dissipation remains a persistent challenge. Here, we demonstrate strong coupling between a transmon superconducting qubit and an ultra-long-lived nanomechanical oscillator ($T_\text{1} \approx 25 \text{ ms}$ at 5 GHz, $Q \approx 0.8 \times 10^9$) by leveraging the low acoustic loss in silicon and phononic bandgap engineering. The qubit-oscillator system achieves large cooperativity ($C_{T_1}\approx 1.5\times10^5$, $C_{T_2}\approx 150$), enabling the generation of non-classical states and the investigation of mechanisms underlying mechanical decoherence. We show that dynamical decoupling$\unicode{x2014}$implemented through the qubit$\unicode{x2014}$can mitigate decoherence, leading to a mechanical coherence time of $T_2\approx 1 \text{ ms}$. These findings extend the exceptional storage capabilities of mechanical oscillators to the quantum regime, putting them forward as compact bosonic elements for future applications in quantum computing and metrology.

quant-ph↗

arXiv2024

GenView: Enhancing View Quality with Pretrained Generative Model for Self-Supervised Learning

Self-supervised learning has achieved remarkable success in acquiring high-quality representations from unlabeled data. The widely adopted contrastive learning framework aims to learn invariant representations by minimizing the distance between positive views originating from the same image. However, existing techniques to construct positive views highly rely on manual transformations, resulting in limited diversity and potentially false positive pairs. To tackle these challenges, we present GenView, a controllable framework that augments the diversity of positive views leveraging the power of pretrained generative models while preserving semantics. We develop an adaptive view generation method that dynamically adjusts the noise level in sampling to ensure the preservation of essential semantic meaning while introducing variability. Additionally, we introduce a quality-driven contrastive loss, which assesses the quality of positive pairs by considering both foreground similarity and background diversity. This loss prioritizes the high-quality positive pairs we construct while reducing the influence of low-quality pairs, thereby mitigating potential semantic inconsistencies introduced by generative models and aggressive data augmentation. Thanks to the improved positive view quality and the quality-driven contrastive loss, GenView significantly improves self-supervised learning across various tasks. For instance, GenView improves MoCov2 performance by 2.5%/2.2% on ImageNet linear/semi-supervised classification. Moreover, GenView even performs much better than naively augmenting the ImageNet dataset with Laion400M or ImageNet21K. Code: https://github.com/xiaojieli0903/genview.

cs.CV↗

arXiv2024

Instruct or Interact? Exploring and Eliciting LLMs' Capability in Code Snippet Adaptation Through Prompt Engineering

Code snippet adaptation is a fundamental activity in the software development process. Unlike code generation, code snippet adaptation is not a "free creation", which requires developers to tailor a given code snippet in order to fit specific requirements and the code context. Recently, large language models (LLMs) have confirmed their effectiveness in the code generation task with promising results. However, their performance on adaptation, a reuse-oriented and context-dependent code change prediction task, is still unclear. To bridge this gap, we conduct an empirical study to investigate the performance and issues of LLMs on the adaptation task. We first evaluate the adaptation performances of three popular LLMs and compare them to the code generation task. Our result indicates that their adaptation ability is weaker than generation, with a nearly 15% decrease on pass@1 and more context-related errors. By manually inspecting 200 cases, we further investigate the causes of LLMs' sub-optimal performance, which can be classified into three categories, i.e., Unclear Requirement, Requirement Misalignment and Context Misapplication. Based on the above empirical research, we propose an interactive prompting approach to eliciting LLMs' adaptation ability. Experimental result reveals that our approach greatly improve LLMs' adaptation performance. The best-performing Human-LLM interaction successfully solves 159 out of the 202 identified defects and improves the pass@1 and pass@5 by over 40% compared to the initial instruction-based prompt. Considering human efforts, we suggest multi-agent interaction as a trade-off, which can achieve comparable performance with excellent generalization ability. We deem that our approach could provide methodological assistance for autonomous code snippet reuse and adaptation with LLMs.

cs.SE↗

arXiv2024

FinTeamExperts: Role Specialized MOEs For Financial Analysis

Large Language Models (LLMs), such as ChatGPT, Phi3 and Llama-3, are leading a significant leap in AI, as they can generalize knowledge from their training to new tasks without fine-tuning. However, their application in the financial domain remains relatively limited. The financial field is inherently complex, requiring a deep understanding across various perspectives, from macro, micro economic trend to quantitative analysis. Motivated by this complexity, a mixture of expert LLMs tailored to specific financial domains could offer a more comprehensive understanding for intricate financial tasks. In this paper, we present the FinTeamExperts, a role-specialized LLM framework structured as a Mixture of Experts (MOEs) for financial analysis. The framework simulates a collaborative team setting by training each model to specialize in distinct roles: Macro Analysts, Micro analysts, and Quantitative Analysts. This role-specific specialization enhances the model's ability to integrate their domain-specific expertise. We achieve this by training three 8-billion parameter models on different corpus, each dedicated to excelling in specific finance-related roles. We then instruct-tune FinTeamExperts on downstream tasks to align with practical financial tasks. The experimental results show that FinTeamExperts outperform all models of the same size and larger on three out of four datasets. On the fourth dataset, which presents a more complex task, FinTeamExperts still surpass all models of the same size. This highlights the success of our role-based specialization approach and the continued training approach for FinTeamExperts.

cs.CL↗

arXiv2024

Dynamic Typography: Bringing Text to Life via Video Diffusion Prior

Text animation serves as an expressive medium, transforming static communication into dynamic experiences by infusing words with motion to evoke emotions, emphasize meanings, and construct compelling narratives. Crafting animations that are semantically aware poses significant challenges, demanding expertise in graphic design and animation. We present an automated text animation scheme, termed "Dynamic Typography", which combines two challenging tasks. It deforms letters to convey semantic meaning and infuses them with vibrant movements based on user prompts. Our technique harnesses vector graphics representations and an end-to-end optimization-based framework. This framework employs neural displacement fields to convert letters into base shapes and applies per-frame motion, encouraging coherence with the intended textual concept. Shape preservation techniques and perceptual loss regularization are employed to maintain legibility and structural integrity throughout the animation process. We demonstrate the generalizability of our approach across various text-to-video models and highlight the superiority of our end-to-end methodology over baseline methods, which might comprise separate tasks. Through quantitative and qualitative evaluations, we demonstrate the effectiveness of our framework in generating coherent text animations that faithfully interpret user prompts while maintaining readability. Our code is available at: https://animate-your-word.github.io/demo/.

cs.CV↗

arXiv2024

Inverse Diffusion Approximation for Extraction of Scattering and Absorption Coefficients in Highly Scattering Media

Photon transport through a diffusing slab can be described by the radiative transfer equation (RTE). When the slab is highly scattering and weakly absorbing, the RTE simplifies to the diffusion equation. In this paper, an inverse diffusion approximation (IDA) method is numerically developed to determine the optical properties (reduced scattering $μ'_s$ and absorption coefficient $μ_a$) of a homogeneous slab using simple reflectance and transmission measurements with a spectrometer. The reflectance and transmission of a diffusing slab with an arbitrary thickness can then be predicted by solving the forward problem by using the calculated $μ'_s$ and $μ_a$. Our method is validated both numerically, by directly comparing with Monte-Carlo simulations, and experimentally, by comparing with measurements on ZnO/PDMS and TiO$_2$/PDMS composite polymer films with varying thicknesses. The IDA method is also applied to distinguish between different types of tissue. Overall, our method could be used to guide the design of radiative cooling reflectors, or lighting and optical display diffusers for applications in medical imaging and other fields.

physics.optics↗

arXiv2024

FaaSTube: Optimizing GPU-oriented Data Transfer for Serverless Computing

Serverless computing has gained significant traction for machine learning inference applications, which are often deployed as serverless workflows consisting of multiple CPU and GPU functions with data dependency. However, existing data-passing solutions for serverless computing primarily reply on host memory for fast data transfer, mandating substantial data movement and resulting in salient I/O overhead. In this paper, we present FaaSTube, a GPU-efficient data passing system for serverless inference. FaaSTube manages intermediate data within a GPU memory pool to facilitate direct data exchange between GPU functions. It enables fine-grained bandwidth sharing over PCIe and NVLink, minimizing data-passing latency for both host-to-GPU and GPU-to-GPU while providing performance isolation between functions. Additionally, FaaSTube implements an elastic GPU memory pool that dynamically scales to accommodate varying data-passing demands. Evaluations on real-world applications show that FaaSTube reduces end-to-end latency by up to 90\% and achieves up to 12x higher throughput compared to the state-of-the-art.

cs.DC↗

arXiv2024

Embedded Nonlocal Operator Regression (ENOR): Quantifying model error in learning nonlocal operators

Nonlocal, integral operators have become an efficient surrogate for bottom-up homogenization, due to their ability to represent long-range dependence and multiscale effects. However, the nonlocal homogenized model has unavoidable discrepancy from the microscale model. Such errors accumulate and propagate in long-term simulations, making the resultant prediction unreliable. To develop a robust and reliable bottom-up homogenization framework, we propose a new framework, which we coin Embedded Nonlocal Operator Regression (ENOR), to learn a nonlocal homogenized surrogate model and its structural model error. This framework provides discrepancy-adaptive uncertainty quantification for homogenized material response predictions in long-term simulations. The method is built on Nonlocal Operator Regression (NOR), an optimization-based nonlocal kernel learning approach, together with an embedded model error term in the trainable kernel. Then, Bayesian inference is employed to infer the model error term parameters together with the kernel parameters. To make the problem computationally feasible, we use a multilevel delayed acceptance Markov chain Monte Carlo (MLDA-MCMC) method, enabling efficient Bayesian model calibration and model error estimation. We apply this technique to predict long-term wave propagation in a heterogeneous one-dimensional bar, and compare its performance with additive noise models. Owing to its ability to capture model error, the learned ENOR achieves improved estimation of posterior predictive uncertainty.

cs.LG↗

arXiv2024

HYDRA: Model Factorization Framework for Black-Box LLM Personalization

Personalization has emerged as a critical research area in modern intelligent systems, focusing on mining users' behavioral history and adapting to their preferences for delivering tailored experiences. Despite the remarkable few-shot capabilities exhibited by black-box large language models (LLMs), the inherent opacity of their model parameters presents significant challenges in aligning the generated output with individual expectations. Existing solutions have primarily focused on prompt design to incorporate user-specific profiles and behaviors; however, such approaches often struggle to generalize effectively due to their inability to capture shared knowledge among all users. To address these challenges, we propose HYDRA, a model factorization framework that captures both user-specific behavior patterns from historical data and shared general knowledge among all users to deliver personalized generation. In order to capture user-specific behavior patterns, we first train a reranker to prioritize the most useful information from top-retrieved relevant historical records. By combining the prioritized history with the corresponding query, we train an adapter to align the output with individual user-specific preferences, eliminating the reliance on access to inherent model parameters of black-box LLMs. Both the reranker and the adapter can be decomposed into a base model with multiple user-specific heads, resembling a hydra. The base model maintains shared knowledge across users, while the multiple personal heads capture user-specific preferences. Experimental results demonstrate that HYDRA outperforms existing state-of-the-art prompt-based methods by an average relative improvement of 9.01% across five diverse personalization tasks in the LaMP benchmark. Our implementation is available at https://github.com/night-chen/HYDRA.

cs.CL↗

arXiv2024

Active Inverse Learning in Stackelberg Trajectory Games

Game-theoretic inverse learning is the problem of inferring a player's objectives from their actions. We formulate an inverse learning problem in a Stackelberg game between a leader and a follower, where each player's action is the trajectory of a dynamical system. We propose an active inverse learning method for the leader to infer which hypothesis among a finite set of candidates best describes the follower's objective function. Instead of using passively observed trajectories like existing methods, we actively maximize the differences in the follower's trajectories under different hypotheses by optimizing the leader's control inputs. Compared with uniformly random inputs, the optimized inputs accelerate the convergence of the estimated probability of different hypotheses conditioned on the follower's trajectory. We demonstrate the proposed method in a receding-horizon repeated trajectory game and simulate the results using virtual TurtleBots in Gazebo.

cs.GT↗

arXiv2024

Minimal Models for Altermagnetism

Altermagnets feature vanishing net magnetization, like antiferromagnets, but exhibit time-reversal symmetry breaking and momentum-dependent spin-split band structures. Motivated by the prevalence of altermagnetic materials with non-symmorphic symmetry-dictated band degeneracies, we provide realistic minimal models for altermagnetism by constructing tight-binding models for nonsymmorphic space groups with a sublattice defined by two magnetic atoms. These models can be applied to monoclinic, orthorhombic, tetragonal, rhombohedral, hexagonal, and cubic materials and can describe d-wave, g-wave, and i-wave altermagnetism. By examining the altermagnetic susceptibility and mean field instabilities within a Hubbard model we reveal that these models have altermagnetic ground states and yield a Berry curvature that is linear in the spin-orbit coupling. We apply our models to RuO$_2$, MnF$_2$, FeSb$_2$, $κ$-Cl, CrSb, and MnTe.

cond-mat.str-el↗

arXiv2024

EHRAgent: Code Empowers Large Language Models for Few-shot Complex Tabular Reasoning on Electronic Health Records

Large language models (LLMs) have demonstrated exceptional capabilities in planning and tool utilization as autonomous agents, but few have been developed for medical problem-solving. We propose EHRAgent, an LLM agent empowered with a code interface, to autonomously generate and execute code for multi-tabular reasoning within electronic health records (EHRs). First, we formulate an EHR question-answering task into a tool-use planning process, efficiently decomposing a complicated task into a sequence of manageable actions. By integrating interactive coding and execution feedback, EHRAgent learns from error messages and improves the originally generated code through iterations. Furthermore, we enhance the LLM agent by incorporating long-term memory, which allows EHRAgent to effectively select and build upon the most relevant successful cases from past experiences. Experiments on three real-world multi-tabular EHR datasets show that EHRAgent outperforms the strongest baseline by up to 29.6% in success rate. EHRAgent leverages the emerging few-shot learning capabilities of LLMs, enabling autonomous code generation and execution to tackle complex clinical tasks with minimal demonstrations.

cs.CL↗

arXiv2024

BMRetriever: Tuning Large Language Models as Better Biomedical Text Retrievers

Developing effective biomedical retrieval models is important for excelling at knowledge-intensive biomedical tasks but still challenging due to the deficiency of sufficient publicly annotated biomedical data and computational resources. We present BMRetriever, a series of dense retrievers for enhancing biomedical retrieval via unsupervised pre-training on large biomedical corpora, followed by instruction fine-tuning on a combination of labeled datasets and synthetic pairs. Experiments on 5 biomedical tasks across 11 datasets verify BMRetriever's efficacy on various biomedical applications. BMRetriever also exhibits strong parameter efficiency, with the 410M variant outperforming baselines up to 11.7 times larger, and the 2B variant matching the performance of models with over 5B parameters. The training data and model checkpoints are released at \url{https://huggingface.co/BMRetriever} to ensure transparency, reproducibility, and application to new domains.

cs.CL↗

arXiv2024

MedAdapter: Efficient Test-Time Adaptation of Large Language Models towards Medical Reasoning

Despite their improved capabilities in generation and reasoning, adapting large language models (LLMs) to the biomedical domain remains challenging due to their immense size and corporate privacy. In this work, we propose MedAdapter, a unified post-hoc adapter for test-time adaptation of LLMs towards biomedical applications. Instead of fine-tuning the entire LLM, MedAdapter effectively adapts the original model by fine-tuning only a small BERT-sized adapter to rank candidate solutions generated by LLMs. Experiments demonstrate that MedAdapter effectively adapts both white-box and black-box LLMs in biomedical reasoning, achieving average performance improvements of 25.48% and 11.31%, respectively, without requiring extensive computational resources or sharing data with third parties. MedAdapter also yields superior performance when combined with train-time adaptation, highlighting a flexible and complementary solution to existing adaptation methods. Faced with the challenges of balancing model performance, computational resources, and data privacy, MedAdapter provides an efficient, privacy-preserving, cost-effective, and transparent solution for adapting LLMs to the biomedical domain.

cs.CL↗

arXiv2024

Multi-Designated Detector Watermarking for Language Models

In this paper, we initiate the study of \emph{multi-designated detector watermarking (MDDW)} for large language models (LLMs). This technique allows model providers to generate watermarked outputs from LLMs with two key properties: (i) only specific, possibly multiple, designated detectors can identify the watermarks, and (ii) there is no perceptible degradation in the output quality for ordinary users. We formalize the security definitions for MDDW and present a framework for constructing MDDW for any LLM using multi-designated verifier signatures (MDVS). Recognizing the significant economic value of LLM outputs, we introduce claimability as an optional security feature for MDDW, enabling model providers to assert ownership of LLM outputs within designated-detector settings. To support claimable MDDW, we propose a generic transformation converting any MDVS to a claimable MDVS. Our implementation of the MDDW scheme highlights its advanced functionalities and flexibility over existing methods, with satisfactory performance metrics.

cs.CR↗

arXiv2024

Filtering-Linearization: A First-Order Method for Nonconvex Trajectory Optimization with Filter-Based Warm-Starting

Nonconvex trajectory optimization is at the core of designing trajectories for complex autonomous systems. A challenge for nonconvex trajectory optimization methods, such as sequential convex programming, is to find an effective warm-starting point to approximate the nonconvex optimization with a sequence of convex ones. We introduce a first-order method with filter-based warm-starting for nonconvex trajectory optimization. The idea is to first generate sampled trajectories using constraint-aware particle filtering, which solves the problem as an estimation problem. We then identify different locally optimal trajectories through agglomerative hierarchical clustering. Finally, we choose the best locally optimal trajectory to warm-start the prox-linear method, a first-order method with guaranteed convergence. We demonstrate the proposed method on a multi-agent trajectory optimization problem with linear dynamics and nonconvex collision avoidance. Compared with sequential quadratic programming and interior-point method, the proposed method reduces the objective function value by up to approximately 96\% within the same amount of time for a two-agent problem, and 98\% for a six-agent problem.

math.OC↗