arXiv subjects

Yang Li

Publications and source records attributed to Yang Li.

At least 703 records · Page 39Linked to original sources

arXiv2024

Gradual Learning: Optimizing Fine-Tuning with Partially Mastered Knowledge in Large Language Models

During the pretraining phase, large language models (LLMs) acquire vast amounts of knowledge from extensive text corpora. Nevertheless, in later stages such as fine-tuning and inference, the model may encounter knowledge not covered in the initial training, which can lead to hallucinations and degraded performance. This issue has a profound impact on the model's capabilities, as it will inevitably face out-of-scope knowledge after pretraining. Furthermore, fine-tuning is often required to adapt LLMs to domain-specific tasks. However, this phenomenon limits the model's ability to learn and integrate new information during fine-tuning. The effectiveness of fine-tuning largely depends on the type of knowledge involved. Existing research suggests that fine-tuning the model on partially mastered knowledge-for instance, question-answer pairs where the model has a chance of providing correct responses under non-greedy decoding-can enable the model to acquire new knowledge while mitigating hallucination. Notably, this approach can still lead to the forgetting of fully mastered knowledge, constraining the fine-tuning dataset to a narrower range and limiting the model's overall potential for improvement. Given the model's intrinsic reasoning abilities and the interconnectedness of different knowledge areas, it is likely that as the model's capacity to utilize existing knowledge improves during fine-tuning, previously unmastered knowledge may become more understandable. To explore this hypothesis, we conducted experiments and, based on the results, proposed a two-stage fine-tuning strategy. This approach not only improves the model's overall test accuracy and knowledge retention but also preserves its accuracy on previously mastered content. When fine-tuning on the WikiQA dataset, our method increases the amount of knowledge acquired by the model in this stage by 24%.

cs.CL↗

arXiv2024

Active Evaluation Acquisition for Efficient LLM Benchmarking

As large language models (LLMs) become increasingly versatile, numerous large scale benchmarks have been developed to thoroughly assess their capabilities. These benchmarks typically consist of diverse datasets and prompts to evaluate different aspects of LLM performance. However, comprehensive evaluations on hundreds or thousands of prompts incur tremendous costs in terms of computation, money, and time. In this work, we investigate strategies to improve evaluation efficiency by selecting a subset of examples from each benchmark using a learned policy. Our approach models the dependencies across test examples, allowing accurate prediction of the evaluation outcomes for the remaining examples based on the outcomes of the selected ones. Consequently, we only need to acquire the actual evaluation outcomes for the selected subset. We rigorously explore various subset selection policies and introduce a novel RL-based policy that leverages the captured dependencies. Empirical results demonstrate that our approach significantly reduces the number of evaluation prompts required while maintaining accurate performance estimates compared to previous methods.

cs.LG↗

arXiv2024

Fueter sections and $\mathbb{Z}_2$-harmonic 1-forms

Motivated by a conjecture of Donaldson and Segal on the counts of monopoles and special Lagrangians in Calabi-Yau 3-folds, we prove a compactness theorem for Fueter sections of charge 2 monopole bundles over 3-manifolds: Let $u_k$ be a sequence of Fueter sections of the charge 2 monopole bundle over a closed oriented Riemannian 3-manifold $(M,g)$, with $L^\infty$-norm diverging to infinity. Then a renormalized sequence derived from $u_k$ subsequentially converges to a non-zero $\mathbb{Z}_2$-harmonic 1-form $\mathcal{V}$ on $M$ in the $W^{1,2}$-topology.

math.DG↗

arXiv2024

Large time behavior for solutions to the anisotropic Navier-Stokes equations in a 3D half-space

We consider the large time behavior of the solution to the anisotropic Navier--Stokes equations in a $3$D half-space. Investigating the precise anisotropic nature of linearized solutions, we obtain the optimal decay estimates for the nonlinear global solutions in anisotropic Lebesgue norms. In particular, we reveal the enhanced dissipation mechanism for the third component of velocity field. We notice that, in contrast to the whole space case, some difficulties arises on the $L^1(\mathbb{R}^3_+)$-estimates of the solution due to the nonlocal operators appearing in the linear solution formula. To overcome this, we introduce suitable Besov type spaces and employ the Littlewood--Paley analysis on the tangential space.

math.AP↗

arXiv2024

AIM 2024 Challenge on Video Super-Resolution Quality Assessment: Methods and Results

This paper presents the Video Super-Resolution (SR) Quality Assessment (QA) Challenge that was part of the Advances in Image Manipulation (AIM) workshop, held in conjunction with ECCV 2024. The task of this challenge was to develop an objective QA method for videos upscaled 2x and 4x by modern image- and video-SR algorithms. QA methods were evaluated by comparing their output with aggregate subjective scores collected from >150,000 pairwise votes obtained through crowd-sourced comparisons across 52 SR methods and 1124 upscaled videos. The goal was to advance the state-of-the-art in SR QA, which had proven to be a challenging problem with limited applicability of traditional QA methods. The challenge had 29 registered participants, and 5 teams had submitted their final results, all outperforming the current state-of-the-art. All data, including the private test subset, has been made publicly available on the challenge homepage at https://challenges.videoprocessing.ai/challenges/super-resolution-metrics-challenge.html

eess.IV↗

arXiv2024

Scaling Parameter-Constrained Language Models with Quality Data

Scaling laws in language modeling traditionally quantify training loss as a function of dataset size and model parameters, providing compute-optimal estimates but often neglecting the impact of data quality on model generalization. In this paper, we extend the conventional understanding of scaling law by offering a microscopic view of data quality within the original formulation -- effective training tokens -- which we posit to be a critical determinant of performance for parameter-constrained language models. Specifically, we formulate the proposed term of effective training tokens to be a combination of two readily-computed indicators of text: (i) text diversity and (ii) syntheticity as measured by a teacher model. We pretrained over $200$ models of 25M to 1.5B parameters on a diverse set of sampled, synthetic data, and estimated the constants that relate text quality, model size, training tokens, and eight reasoning task accuracy scores. We demonstrated the estimated constants yield +0.83 Pearson correlation with true accuracies, and analyzed it in scenarios involving widely-used data techniques such as data sampling and synthesis which aim to improve data quality.

cs.CL↗

arXiv2024

Towards Cost Sensitive Decision Making

Many real-world situations allow for the acquisition of additional relevant information when making decisions with limited or uncertain data. However, traditional RL approaches either require all features to be acquired beforehand (e.g. in a MDP) or regard part of them as missing data that cannot be acquired (e.g. in a POMDP). In this work, we consider RL models that may actively acquire features from the environment to improve the decision quality and certainty, while automatically balancing the cost of feature acquisition process and the reward of task decision process. We propose the Active-Acquisition POMDP and identify two types of the acquisition process for different application domains. In order to assist the agent in the actively-acquired partially-observed environment and alleviate the exploration-exploitation dilemma, we develop a model-based approach, where a deep generative model is utilized to capture the dependencies of the features and impute the unobserved features. The imputations essentially represent the beliefs of the agent. Equipped with the dynamics model, we develop hierarchical RL algorithms to resolve both types of the AA-POMDPs. Empirical results demonstrate that our approach achieves considerably better performance than existing POMDP-RL solutions.

cs.LG↗

arXiv2024

Distribution Guided Active Feature Acquisition

Human agents routinely reason on instances with incomplete and muddied data (and weigh the cost of obtaining further features). In contrast, much of ML is devoted to the unrealistic, sterile environment where all features are observed and further information on an instance is obviated. Here we extend past static ML and develop an active feature acquisition (AFA) framework that interacts with the environment to obtain new information on-the-fly and can: 1) make inferences on an instance in the face of incomplete features, 2) determine a plan for feature acquisitions to obtain additional information on the instance at hand. We build our AFA framework on a backbone of understanding the information and conditional dependencies that are present in the data. First, we show how to build generative models that can capture dependencies over arbitrary subsets of features and employ these models for acquisitions in a greedy scheme. After, we show that it is possible to guide the training of RL agents for AFA via side-information and auxiliary rewards stemming from our generative models. We also examine two important factors for deploying AFA models in real-world scenarios, namely interpretability and robustness. Extensive experiments demonstrate the state-of-the-art performance of our AFA framework.

cs.LG↗

arXiv2024

Effective Tuning Strategies for Generalist Robot Manipulation Policies

Generalist robot manipulation policies (GMPs) have the potential to generalize across a wide range of tasks, devices, and environments. However, existing policies continue to struggle with out-of-distribution scenarios due to the inherent difficulty of collecting sufficient action data to cover extensively diverse domains. While fine-tuning offers a practical way to quickly adapt a GMPs to novel domains and tasks with limited samples, we observe that the performance of the resulting GMPs differs significantly with respect to the design choices of fine-tuning strategies. In this work, we first conduct an in-depth empirical study to investigate the effect of key factors in GMPs fine-tuning strategies, covering the action space, policy head, supervision signal and the choice of tunable parameters, where 2,500 rollouts are evaluated for a single configuration. We systematically discuss and summarize our findings and identify the key design choices, which we believe give a practical guideline for GMPs fine-tuning. We observe that in a low-data regime, with carefully chosen fine-tuning strategies, a GMPs significantly outperforms the state-of-the-art imitation learning algorithms. The results presented in this work establish a new baseline for future studies on fine-tuned GMPs, and provide a significant addition to the GMPs toolbox for the community.

cs.RO↗

arXiv2024

DsubCox: A Fast Subsampling Algorithm for Cox Model with Distributed and Massive Survival Data

To ensure privacy protection and alleviate computational burden, we propose a fast subsmaling procedure for the Cox model with massive survival datasets from multi-centered, decentralized sources. The proposed estimator is computed based on optimal subsampling probabilities that we derived and enables transmission of subsample-based summary level statistics between different storage sites with only one round of communication. For inference, the asymptotic properties of the proposed estimator were rigorously established. An extensive simulation study demonstrated that the proposed approach is effective. The methodology was applied to analyze a large dataset from the U.S. airlines.

stat.CO↗

arXiv2024

HOLA-Drone: Hypergraphic Open-ended Learning for Zero-Shot Multi-Drone Cooperative Pursuit

Zero-shot coordination (ZSC) is a significant challenge in multi-agent collaboration, aiming to develop agents that can coordinate with unseen partners they have not encountered before. Recent cutting-edge ZSC methods have primarily focused on two-player video games such as OverCooked!2 and Hanabi. In this paper, we extend the scope of ZSC research to the multi-drone cooperative pursuit scenario, exploring how to construct a drone agent capable of coordinating with multiple unseen partners to capture multiple evaders. We propose a novel Hypergraphic Open-ended Learning Algorithm (HOLA-Drone) that continuously adapts the learning objective based on our hypergraphic-form game modeling, aiming to improve cooperative abilities with multiple unknown drone teammates. To empirically verify the effectiveness of HOLA-Drone, we build two different unseen drone teammate pools to evaluate their performance in coordination with various unseen partners. The experimental results demonstrate that HOLA-Drone outperforms the baseline methods in coordination with unseen drone teammates. Furthermore, real-world experiments validate the feasibility of HOLA-Drone in physical systems. Videos can be found on the project homepage~\url{https://sites.google.com/view/hola-drone}.

cs.RO↗

arXiv2024

DOEPatch: Dynamically Optimized Ensemble Model for Adversarial Patches Generation

Object detection is a fundamental task in various applications ranging from autonomous driving to intelligent security systems. However, recognition of a person can be hindered when their clothing is decorated with carefully designed graffiti patterns, leading to the failure of object detection. To achieve greater attack potential against unknown black-box models, adversarial patches capable of affecting the outputs of multiple-object detection models are required. While ensemble models have proven effective, current research in the field of object detection typically focuses on the simple fusion of the outputs of all models, with limited attention being given to developing general adversarial patches that can function effectively in the physical world. In this paper, we introduce the concept of energy and treat the adversarial patches generation process as an optimization of the adversarial patches to minimize the total energy of the ``person'' category. Additionally, by adopting adversarial training, we construct a dynamically optimized ensemble model. During training, the weight parameters of the attacked target models are adjusted to find the balance point at which the generated adversarial patches can effectively attack all target models. We carried out six sets of comparative experiments and tested our algorithm on five mainstream object detection models. The adversarial patches generated by our algorithm can reduce the recognition accuracy of YOLOv2 and YOLOv3 to 13.19\% and 29.20\%, respectively. In addition, we conducted experiments to test the effectiveness of T-shirts covered with our adversarial patches in the physical world and could achieve that people are not recognized by the object detection model. Finally, leveraging the Grad-CAM tool, we explored the attack mechanism of adversarial patches from an energetic perspective.

cs.CV↗

arXiv2024

An evolutionary approach for discovering non-Gaussian stochastic dynamical systems based on nonlocal Kramers-Moyal formulas

Discovering explicit governing equations of stochastic dynamical systems with both (Gaussian) Brownian noise and (non-Gaussian) Lévy noise from data is chanllenging due to possible intricate functional forms and the inherent complexity of Lévy motion. This present research endeavors to develop an evolutionary symbol sparse regression (ESSR) approach to extract non-Gaussian stochastic dynamical systems from sample path data, based on nonlocal Kramers-Moyal formulas, genetic programming, and sparse regression. More specifically, the genetic programming is employed to generate a diverse array of candidate functions, the sparse regression technique aims at learning the coefficients associated with these candidates, and the nonlocal Kramers-Moyal formulas serve as the foundation for constructing the fitness measure in genetic programming and the loss function in sparse regression. The efficacy and capabilities of this approach are showcased through its application to several illustrative models. This approach stands out as a potent instrument for deciphering non-Gaussian stochastic dynamics from available datasets, indicating a wide range of applications across different fields.

stat.ML↗

arXiv2024

Differential cross-section measurements for neutron-induced $α$ production reactions on carbon across neutron energy range of 6.2 to 76 MeV

Angle-differential cross sections for neutron-induced $α$ production in carbon were determined at thirty discrete neutron energy levels ranging from 6.2 to 76 MeV at the Back-n white neutron source of the China Spallation Neutron Source. Utilizing the $ΔE-E$ telescopes within the Light-charged Particle Detector Array spanning angular measurements from 24.5°to 155.5° in the laboratory frame, the $^{12}C(n,α)x$ reaction cross sections were obtained. These experimental findings exhibit a strong concordance with prior results and have been benchmarked against theoretical estimates from codes such as TALYS, Geant4, and assessments from the ENDF/B-VIII.0 database. Remarkably, distinct resonance-like features were observed at neutron energies of 13.7, 22.4, 29.5, and 61.8 MeV, marking their first-time identification in the literature.Furthermore, a comparative analysis involving the theoretical Distorted Wave Born Approximation was conducted.

nucl-ex↗

arXiv2024

Target-Aware Language Modeling via Granular Data Sampling

Language model pretraining generally targets a broad range of use cases and incorporates data from diverse sources. However, there are instances where we desire a model that excels in specific areas without markedly compromising performance in other areas. A cost-effective and straightforward approach is sampling with low-dimensional data features, which allows to select large-scale pretraining data for domain-specific use cases. In this work, we revisit importance sampling with n-gram features consisting of multi-granular tokens, which strikes a good balance between sentence compression and representation capabilities. We observed the sampled data to have a high correlation with the target downstream task performance while preserving its effectiveness on other tasks. This leads to the proposed data sampling paradigm where language models can be pretrained more efficiently on selected documents. On eight benchmarks we demonstrate with $\sim$1% of the data, pretrained models perform on par with the full RefinedWeb data and outperform randomly selected samples for model sizes ranging from 125M to 1.5B.

cs.CL↗

arXiv2024

TG-LLaVA: Text Guided LLaVA via Learnable Latent Embeddings

Currently, inspired by the success of vision-language models (VLMs), an increasing number of researchers are focusing on improving VLMs and have achieved promising results. However, most existing methods concentrate on optimizing the connector and enhancing the language model component, while neglecting improvements to the vision encoder itself. In contrast, we propose Text Guided LLaVA (TG-LLaVA) in this paper, which optimizes VLMs by guiding the vision encoder with text, offering a new and orthogonal optimization direction. Specifically, inspired by the purpose-driven logic inherent in human behavior, we use learnable latent embeddings as a bridge to analyze textual instruction and add the analysis results to the vision encoder as guidance, refining it. Subsequently, another set of latent embeddings extracts additional detailed text-guided information from high-resolution local patches as auxiliary information. Finally, with the guidance of text, the vision encoder can extract text-related features, similar to how humans focus on the most relevant parts of an image when considering a question. This results in generating better answers. Experiments on various datasets validate the effectiveness of the proposed method. Remarkably, without the need for additional training data, our propsoed method can bring more benefits to the baseline (LLaVA-1.5) compared with other concurrent methods. Furthermore, the proposed method consistently brings improvement in different settings.

cs.CV↗

arXiv2024

Cross-Utterance Conditioned VAE for Speech Generation

Speech synthesis systems powered by neural networks hold promise for multimedia production, but frequently face issues with producing expressive speech and seamless editing. In response, we present the Cross-Utterance Conditioned Variational Autoencoder speech synthesis (CUC-VAE S2) framework to enhance prosody and ensure natural speech generation. This framework leverages the powerful representational capabilities of pre-trained language models and the re-expression abilities of variational autoencoders (VAEs). The core component of the CUC-VAE S2 framework is the cross-utterance CVAE, which extracts acoustic, speaker, and textual features from surrounding sentences to generate context-sensitive prosodic features, more accurately emulating human prosody generation. We further propose two practical algorithms tailored for distinct speech synthesis applications: CUC-VAE TTS for text-to-speech and CUC-VAE SE for speech editing. The CUC-VAE TTS is a direct application of the framework, designed to generate audio with contextual prosody derived from surrounding texts. On the other hand, the CUC-VAE SE algorithm leverages real mel spectrogram sampling conditioned on contextual information, producing audio that closely mirrors real sound and thereby facilitating flexible speech editing based on text such as deletion, insertion, and replacement. Experimental results on the LibriTTS datasets demonstrate that our proposed models significantly enhance speech synthesis and editing, producing more natural and expressive speech.

cs.SD↗

arXiv2024

Dynamic Prediction Model for NOx Emission of SCR System Based on Hybrid Data-driven Algorithms

Aiming at the problem that delay time is difficult to determine and prediction accuracy is low in building prediction model of SCR system, a dynamic modeling scheme based on a hybrid of multiple data-driven algorithms was proposed. First, processed abnormal values and normalized the data. To improve the relevance of the input data, used MIC to estimate delay time and reconstructed production data. Then used combined feature selection method to determine input variables. To further mine data information, VMD was used to decompose input time series. Finally, established NOx emission prediction model combining ELM and EC model. Experimental results based on actual historical operating data show that the MAPE of predicted results is 2.61%. Model sensitivity analysis shows that besides the amount of ammonia injection, the inlet oxygen concentration and the flue gas temperature have a significant impact on NOx emission, which should be considered in SCR process control and optimization.

eess.SP↗