Search

Score-based diffusion models have achieved incredible performance in generating realistic images, audio, and video data. While these models produce high-quality samples with impressive details, they often introduce unrealistic artifacts, such as distorted fingers or hallucinated texts with no meaning. This paper focuses on textual hallucinations, where diffusion models correctly generate individual symbols but assemble them in a nonsensical manner. Through experimental probing, we consistently observe that such phenomenon is attributed it to the network's local generation bias. Denoising networks tend to produce outputs that rely heavily on highly correlated local regions, particularly when different dimensions of the data distribution are nearly pairwise independent. This behavior leads to a generation process that decomposes the global distribution into separate, independent distributions for each symbol, ultimately failing to capture the global structure, including underlying grammar. Intriguingly, this bias persists across various denoising network architectures including MLP and transformers which have the structure to model global dependency. These findings also provide insights into understanding other types of hallucinations, extending beyond text, as a result of implicit biases in the denoising models. Additionally, we theoretically analyze the training dynamics for a specific case involving a two-layer MLP learning parity points on a hypercube, offering an explanation of its underlying mechanism.

Multitask Representation Learning (MRL) has emerged as a prevalent technique to improve sample efficiency in Reinforcement Learning (RL). Empirical studies have found that training agents on multiple tasks simultaneously within online and transfer learning environments can greatly improve efficiency. Despite its popularity, a comprehensive theoretical framework that elucidates its operational efficacy remains incomplete. Prior analyses have predominantly assumed that agents either possess a pre-known representation function or utilize functions from a linear class, where both are impractical. The complexity of real-world applications typically requires the use of sophisticated, non-linear functions such as neural networks as representation function, which are not pre-existing but must be learned. Our work tries to fill the gap by extending the analysis to \textit{unknown non-linear} representations, giving a comprehensive analysis for its mechanism in online and transfer learning setting. We consider the setting that an agent simultaneously playing $M$ contextual bandits (or MDPs), developing a shared representation function $\phi$ from a non-linear function class $\Phi$ using our novel Generalized Functional Upper Confidence Bound algorithm (GFUCB). We formally prove that this approach yields a regret upper bound that outperforms the lower bound associated with learning $M$ separate tasks, marking the first demonstration of MRL's efficacy in a general function class. This framework also explains the contribution of representations to transfer learning when faced with new, yet related tasks, and identifies key conditions for successful transfer. Empirical experiments further corroborate our theoretical findings., Comment: arXiv admin note: substantial text overlap with arXiv:2205.15701

With the popularity of 3D volumetric video applications, such as Autonomous Driving, Virtual Reality, and Mixed Reality, current developers have turned to deep learning for compressing volumetric video frames, i.e., point clouds for video upstreaming. The latest deep learning-based solutions offer higher efficiency, lower distortion, and better hardware support compared to traditional ones like MPEG and JPEG. However, privacy threats arise, especially reconstruction attacks targeting to recover the original input point cloud from the intermediate results. In this paper, we design VVRec, to the best of our knowledge, which is the first targeting DL-based Volumetric Video Reconstruction attack scheme. VVRec demonstrates the ability to reconstruct high-quality point clouds from intercepted transmission intermediate results using four well-trained neural network modules we design. Leveraging the latest latent diffusion models with Gamma distribution and a refinement algorithm, VVRec excels in reconstruction quality, color recovery, and surpasses existing defenses. We evaluate VVRec using three volumetric video datasets. The results demonstrate that VVRec achieves 64.70dB reconstruction accuracy, with an impressive 46.39% reduction of distortion over baselines.

Large language models (LLMs) have demonstrated remarkable capabilities in complex reasoning tasks. However, existing approaches mainly rely on imitation learning and struggle to achieve effective test-time scaling. While reinforcement learning (RL) holds promise for enabling self-exploration and learning from feedback, recent attempts yield only modest improvements in complex reasoning. In this paper, we present T1 to scale RL by encouraging exploration and understand inference scaling. We first initialize the LLM using synthesized chain-of-thought data that integrates trial-and-error and self-verification. To scale RL training, we promote increased sampling diversity through oversampling. We further employ an entropy bonus as an auxiliary loss, alongside a dynamic anchor for regularization to facilitate reward optimization. We demonstrate that T1 with open LLMs as its base exhibits inference scaling behavior and achieves superior performance on challenging math reasoning benchmarks. For example, T1 with Qwen2.5-32B as the base model outperforms the recent Qwen QwQ-32B-Preview model on MATH500, AIME2024, and Omni-math-500. More importantly, we present a simple strategy to examine inference scaling, where increased inference budgets directly lead to T1's better performance without any additional verification. We will open-source the T1 models and the data used to train them at \url{https://github.com/THUDM/T1}.

Theory-of-Mind (ToM) is a fundamental psychological capability that allows humans to understand and interpret the mental states of others. Humans infer others' thoughts by integrating causal cues and indirect clues from broad contextual information, often derived from past interactions. In other words, human ToM heavily relies on the understanding about the backgrounds and life stories of others. Unfortunately, this aspect is largely overlooked in existing benchmarks for evaluating machines' ToM capabilities, due to their usage of short narratives without global backgrounds. In this paper, we verify the importance of understanding long personal backgrounds in ToM and assess the performance of LLMs in such realistic evaluation scenarios. To achieve this, we introduce a novel benchmark, CharToM-QA, comprising 1,035 ToM questions based on characters from classic novels. Our human study reveals a significant disparity in performance: the same group of educated participants performs dramatically better when they have read the novels compared to when they have not. In parallel, our experiments on state-of-the-art LLMs, including the very recent o1 model, show that LLMs still perform notably worse than humans, despite that they have seen these stories during pre-training. This highlights the limitations of current LLMs in capturing the nuanced contextual information required for ToM reasoning., Comment: 17 pages, under review

OpenAI's Sora highlights the potential of video generation for developing world models that adhere to fundamental physical laws. However, the ability of video generation models to discover such laws purely from visual data without human priors can be questioned. A world model learning the true law should give predictions robust to nuances and correctly extrapolate on unseen scenarios. In this work, we evaluate across three key scenarios: in-distribution, out-of-distribution, and combinatorial generalization. We developed a 2D simulation testbed for object movement and collisions to generate videos deterministically governed by one or more classical mechanics laws. This provides an unlimited supply of data for large-scale experimentation and enables quantitative evaluation of whether the generated videos adhere to physical laws. We trained diffusion-based video generation models to predict object movements based on initial frames. Our scaling experiments show perfect generalization within the distribution, measurable scaling behavior for combinatorial generalization, but failure in out-of-distribution scenarios. Further experiments reveal two key insights about the generalization mechanisms of these models: (1) the models fail to abstract general physical rules and instead exhibit "case-based" generalization behavior, i.e., mimicking the closest training example; (2) when generalizing to new cases, models are observed to prioritize different factors when referencing training data: color > size > velocity > shape. Our study suggests that scaling alone is insufficient for video generation models to uncover fundamental physical laws, despite its role in Sora's broader success. See our project page at https://phyworld.github.io, Comment: preprint

Power Density Spectrum (PDS) is one of the powerful tools to study light curves of gamma-ray bursts (GRBs). We show the average PDS and individual PDS analysis with {\it Hard X-ray Modulation Telescope} (also named \insighthxmt) GRBs data. The values of power-law index of average PDS ($\alpha_{\bar{P}}$) for long GRBs (LGRBs) vary from 1.58-1.29 (for 100-245, 245-600, and 600-2000 keV). The \insighthxmt\ data allow us to extend the energy of the LGRBs up to 2000 keV, and a relation between $\alpha_{\bar{P}}$ and energy $E$, $\alpha_{\bar{P}}\propto E^{-0.09}$ (8-2000 keV) is obtained. We first systematically investigate the average PDS and individual PDS for short GRBs (SGRBs), and obtain $\alpha_{\bar{P}}\propto E^{-0.07}$ (8-1000 keV), where the values of $\alpha_{\bar{P}}$ vary from 1.86 to 1.34. The distribution of power-law index of individual PDS ($\alpha$) of SGRB, is consistent with that of LGRB, and the $\alpha$ value for the dominant timescale group (the bent power-law, BPL) is higher than that for the no-dominant timescale group (the single power-law, PL). Both LGRBs and SGRBs show similar $\alpha$ and $\alpha_{\bar{P}}$, which indicates that they may be the result of similar stochastic processes. The typical value of dominant timescale $\tau$ for LGRBs and SGRBs is 1.58 s and 0.02 s, respectively. It seems that the $\tau$ in proportion to the duration of GRBs $T_{90}$, with a relation $\tau \propto T_{90}^{0.86}$. The GRB light curve may result from superposing a number of pulses with different timescales. No periodic and quasi-periodical signal above the 3$\sigma$ significance threshold is found in our sample.

As artificial intelligence continues to evolve, it is increasingly capable of handling a wide range of video analytics tasks with merely one large model. One of the key foundation technologies is the Segment Anything Model (SAM), which allows the video analytics tasks to be determined on the fly according to the input prompts from the user. However, achieving real-time response in video analytics applications is crucial for user experiences due to the limited communication and computation resources on the edge, especially with SAM, where users may continuously interact by adding or adjusting prompts. In this paper, we propose SAMEdge, a novel edge-cloud computing architecture designed to support SAM computations for edge users. SAMEdge integrates new modules on the edge and the cloud to maximize analytics accuracy under visual prompts and image prompts input with latency constraints. It addresses resource challenges associated with prompt encoding and image encoding by offering a visual prompt transformation algorithm for visual prompts and efficient workload partitioning for image encoding. SAMEdge is implemented by extending the open-source SAM project from Meta AI. We demonstrate the practical application of SAMEdge through a case study on a Visual Tour Guide application. Our evaluation indicates that SAMEdge significantly enhances the accuracy of the video analytics application under distinct network bandwidths across various prompts.

Recent studies have demonstrated the effectiveness of token-based methods for visual content generation. As a representative work, non-autoregressive Transformers (NATs) are able to synthesize images with decent quality in a small number of steps. However, NATs usually necessitate configuring a complicated generation policy comprising multiple manually-designed scheduling rules. These heuristic-driven rules are prone to sub-optimality and come with the requirements of expert knowledge and labor-intensive efforts. Moreover, their one-size-fits-all nature cannot flexibly adapt to the diverse characteristics of each individual sample. To address these issues, we propose AdaNAT, a learnable approach that automatically configures a suitable policy tailored for every sample to be generated. In specific, we formulate the determination of generation policies as a Markov decision process. Under this framework, a lightweight policy network for generation can be learned via reinforcement learning. Importantly, we demonstrate that simple reward designs such as FID or pre-trained reward models, may not reliably guarantee the desired quality or diversity of generated samples. Therefore, we propose an adversarial reward design to guide the training of policy networks effectively. Comprehensive experiments on four benchmark datasets, i.e., ImageNet-256 & 512, MS-COCO, and CC3M, validate the effectiveness of AdaNAT. Code and pre-trained models will be released at https://github.com/LeapLabTHU/AdaNAT., Comment: Accepted by ECCV2024

Gamma-ray bursts (GRBs) as the most energetic explosions in the modern universe have been studied over half a century, but the physics of the particle acceleration and radiation responsible for their observed spectral behaviors are still not well understood. Based on the comprehensive analysis of the pulse properties in both bright GRB~160625B and GRB~160509A, for the first time, we identify evidences of particle acceleration by relativistic magnetic reconnection from the evolutionary behavior of the two spectral breaks ($E_{\rm p}$ and $E_{\rm cut}$). Meanwhile, the adiabatic cooling process of the emitting particles in the magnetic reconnection regions produces a relation between the spectral index and the flux. We also discuss the physics behind spectral energy correlations. Finally, we argue that the identification of an anticorrelation between $E_{\rm cut}$ and $L_{\rm iso}$ may opens a new avenue for diagnostics of the physics of the particle acceleration and radiation in a variety of astrophysical sources., Comment: 17 pages, 8 figures. Accepted for publication in ApJ

Large Language Models (LLMs) have demonstrated great potential as generalist assistants, showcasing powerful task understanding and problem-solving capabilities. To deploy LLMs as AI assistants, it is crucial that these models exhibit desirable behavioral traits, such as non-toxicity and resilience against jailbreak attempts. Current approaches for detoxification or preventing jailbreaking usually involve Supervised Fine-Tuning (SFT) or Reinforcement Learning from Human Feedback (RLHF), which requires finetuning billions of parameters through gradient descent with substantial computational cost. Furthermore, models modified through SFT and RLHF may deviate from the pretrained models, potentially leading to a degradation in foundational LLM capabilities. In this paper, we observe that surprisingly, directly editing a small subset of parameters can effectively modulate specific behaviors of LLMs, such as detoxification and resistance to jailbreaking, with only inference-level computational resources. Experiments demonstrate that in the detoxification task, our approach achieves reductions of up to 90.0% in toxicity on the RealToxicityPrompts dataset and 49.2% on ToxiGen, while maintaining the LLM's general capabilities in areas such as common sense, question answering, and mathematics, Comment: 23 pages, 14 figures

We introduce ChatGLM, an evolving family of large language models that we have been developing over time. This report primarily focuses on the GLM-4 language series, which includes GLM-4, GLM-4-Air, and GLM-4-9B. They represent our most capable models that are trained with all the insights and lessons gained from the preceding three generations of ChatGLM. To date, the GLM-4 models are pre-trained on ten trillions of tokens mostly in Chinese and English, along with a small set of corpus from 24 languages, and aligned primarily for Chinese and English usage. The high-quality alignment is achieved via a multi-stage post-training process, which involves supervised fine-tuning and learning from human feedback. Evaluations show that GLM-4 1) closely rivals or outperforms GPT-4 in terms of general metrics such as MMLU, GSM8K, MATH, BBH, GPQA, and HumanEval, 2) gets close to GPT-4-Turbo in instruction following as measured by IFEval, 3) matches GPT-4 Turbo (128K) and Claude 3 for long context tasks, and 4) outperforms GPT-4 in Chinese alignments as measured by AlignBench. The GLM-4 All Tools model is further aligned to understand user intent and autonomously decide when and which tool(s) touse -- including web browser, Python interpreter, text-to-image model, and user-defined functions -- to effectively complete complex tasks. In practical applications, it matches and even surpasses GPT-4 All Tools in tasks like accessing online information via web browsing and solving math problems using Python interpreter. Over the course, we have open-sourced a series of models, including ChatGLM-6B (three generations), GLM-4-9B (128K, 1M), GLM-4V-9B, WebGLM, and CodeGeeX, attracting over 10 million downloads on Hugging face in the year 2023 alone. The open models can be accessed through https://github.com/THUDM and https://huggingface.co/THUDM.

The superior performance of modern visual backbones usually comes with a costly training procedure. We contribute to this issue by generalizing the idea of curriculum learning beyond its original formulation, i.e., training models using easier-to-harder data. Specifically, we reformulate the training curriculum as a soft-selection function, which uncovers progressively more difficult patterns within each example during training, instead of performing easier-to-harder sample selection. Our work is inspired by an intriguing observation on the learning dynamics of visual backbones: during the earlier stages of training, the model predominantly learns to recognize some 'easier-to-learn' discriminative patterns in the data. These patterns, when observed through frequency and spatial domains, incorporate lower-frequency components, and the natural image contents without distortion or data augmentation. Motivated by these findings, we propose a curriculum where the model always leverages all the training data at every learning stage, yet the exposure to the 'easier-to-learn' patterns of each example is initiated first, with harder patterns gradually introduced as training progresses. To implement this idea in a computationally efficient way, we introduce a cropping operation in the Fourier spectrum of the inputs, enabling the model to learn from only the lower-frequency components. Then we show that exposing the contents of natural images can be readily achieved by modulating the intensity of data augmentation. Finally, we integrate these aspects and design curriculum schedules with tailored search algorithms. The resulting method, EfficientTrain++, is simple, general, yet surprisingly effective. It reduces the training time of a wide variety of popular models by 1.5-3.0x on ImageNet-1K/22K without sacrificing accuracy. It also demonstrates efficacy in self-supervised learning (e.g., MAE)., Comment: Accepted by IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI). Journal version of arXiv:2211.09703 (ICCV 2023). Code is available at: https://github.com/LeapLabTHU/EfficientTrain

The properties of the progenitors of gamma-ray bursts (GRBs) and of their environment are encoded in their luminosity function and cosmic formation rate. They are usually recovered from a flux-limited sample based on Lynden-Bell's $c^{-}$ method. However, this method is based on the assumption that the luminosity is independent of the redshift. Observationally, if correlated, people use nonparametric $\tau$ statistical method to remove this correlation through the transformation, $L^{\prime}=L/g(z)$, where $z$ is the burst redshift, and $g(z)=(1+z)^{k}$ parameterizes the underlying luminosity evolution. However, the application of this method to different observations could result in very different luminosity functions. By the means of Monte Carlo simulation, in this paper, we demonstrate that the origin of an observed correlation, measured by the $\tau$ statistical method, is a complex combination of multiple factors when the underlying data are correlated. Thus, in this case, it is difficult to unbiasedly reconstruct the underlying population distribution from a truncated sample, unless the detailed information of the intrinsic correlation is accurately known in advance. In addition, we argue that an intrinsic correlation between luminosity function and formation rate is unlikely eliminated by a misconfigured transformation, and the $g(z)$, derived from a truncated sample with the $\tau$ statistical method, does not necessarily represent its underlying luminosity evolution., Comment: Comments: 8 pages, 8 figures,Accepted for publication in MNRAS

Humans possess the ability to draw on past experiences explicitly when learning new tasks and applying them accordingly. We believe this capacity for self-referencing is especially advantageous for reinforcement learning agents in the unsupervised pretrain-then-finetune setting. During pretraining, an agent's past experiences can be explicitly utilized to mitigate the nonstationarity of intrinsic rewards. In the finetuning phase, referencing historical trajectories prevents the unlearning of valuable exploratory behaviors. Motivated by these benefits, we propose the Self-Reference (SR) approach, an add-on module explicitly designed to leverage historical information and enhance agent performance within the pretrain-finetune paradigm. Our approach achieves state-of-the-art results in terms of Interquartile Mean (IQM) performance and Optimality Gap reduction on the Unsupervised Reinforcement Learning Benchmark for model-free methods, recording an 86% IQM and a 16% Optimality Gap. Additionally, it improves current algorithms by up to 17% IQM and reduces the Optimality Gap by 31%. Beyond performance enhancement, the Self-Reference add-on also increases sample efficiency, a crucial attribute for real-world applications., Comment: Preprint

Large Language Models (LLMs) exhibit impressive reasoning and data augmentation capabilities in various NLP tasks. However, what about small models? In this work, we propose TeacherLM-7.1B, capable of annotating relevant fundamentals, chain of thought, and common mistakes for most NLP samples, which makes annotation more than just an answer, thus allowing other models to learn "why" instead of just "what". The TeacherLM-7.1B model achieved a zero-shot score of 52.3 on MMLU, surpassing most models with over 100B parameters. Even more remarkable is its data augmentation ability. Based on TeacherLM-7.1B, we augmented 58 NLP datasets and taught various student models with different parameters from OPT and BLOOM series in a multi-task setting. The experimental results indicate that the data augmentation provided by TeacherLM has brought significant benefits. We will release the TeacherLM series of models and augmented datasets as open-source., Comment: 5 figures, 15 pages

Open large language models (LLMs) with great performance in various tasks have significantly advanced the development of LLMs. However, they are far inferior to commercial models such as ChatGPT and GPT-4 when acting as agents to tackle complex tasks in the real world. These agent tasks employ LLMs as the central controller responsible for planning, memorization, and tool utilization, necessitating both fine-grained prompting methods and robust LLMs to achieve satisfactory performance. Though many prompting methods have been proposed to complete particular agent tasks, there is lack of research focusing on improving the agent capabilities of LLMs themselves without compromising their general abilities. In this work, we present AgentTuning, a simple and general method to enhance the agent abilities of LLMs while maintaining their general LLM capabilities. We construct AgentInstruct, a lightweight instruction-tuning dataset containing high-quality interaction trajectories. We employ a hybrid instruction-tuning strategy by combining AgentInstruct with open-source instructions from general domains. AgentTuning is used to instruction-tune the Llama 2 series, resulting in AgentLM. Our evaluations show that AgentTuning enables LLMs' agent capabilities without compromising general abilities. The AgentLM-70B is comparable to GPT-3.5-turbo on unseen agent tasks, demonstrating generalized agent capabilities. We open source the AgentInstruct and AgentLM-7B, 13B, and 70B models at https://github.com/THUDM/AgentTuning, serving open and powerful alternatives to commercial LLMs for agent tasks., Comment: 31 pages

The divergence of the Q-value estimation has been a prominent issue in offline RL, where the agent has no access to real dynamics. Traditional beliefs attribute this instability to querying out-of-distribution actions when bootstrapping value targets. Though this issue can be alleviated with policy constraints or conservative Q estimation, a theoretical understanding of the underlying mechanism causing the divergence has been absent. In this work, we aim to thoroughly comprehend this mechanism and attain an improved solution. We first identify a fundamental pattern, self-excitation, as the primary cause of Q-value estimation divergence in offline RL. Then, we propose a novel Self-Excite Eigenvalue Measure (SEEM) metric based on Neural Tangent Kernel (NTK) to measure the evolving property of Q-network at training, which provides an intriguing explanation of the emergence of divergence. For the first time, our theory can reliably decide whether the training will diverge at an early stage, and even predict the order of the growth for the estimated Q-value, the model's norm, and the crashing step when an SGD optimizer is used. The experiments demonstrate perfect alignment with this theoretic analysis. Building on our insights, we propose to resolve divergence from a novel perspective, namely improving the model's architecture for better extrapolating behavior. Through extensive empirical studies, we identify LayerNorm as a good solution to effectively avoid divergence without introducing detrimental bias, leading to superior performance. Experimental results prove that it can still work in some most challenging settings, i.e. using only 1 transitions of the dataset, where all previous methods fail. Moreover, it can be easily plugged into modern offline RL methods and achieve SOTA results on many challenging tasks. We also give unique insights into its effectiveness., Comment: 31 pages, 20 figures

Long-duration GRB~200829A was detected by Fermi-GBM and Swift-BAT/XRT, and then rapidly observed by other ground-based telescopes. It has a weak $\gamma$-ray emission in the very early phase and followed by a bright spiky $\gamma$-ray emission pulse. The radiation spectrum of the very early emission is best fitted by a power-law function with index $\sim -1.7$. However, the bright spiky $\gamma$-ray pulse, especially the time around the peak, exhibits a distinct two-component radiation spectra, i.e., Band function combined with a blackbody radiation spectrum. We infer the photospheric properties and reveal a medium magnetization at photospheric position by adopting the initial size of the outflow as $r_0=10^9$~cm. It implies that Band component in this pulse may be formed during the dissipation of magnetic field. The power-law radiation spectra found in the very early prompt emission may imply the external-shock origination of this phase. Then, we perform Markov Chain Monte Carlo method fitting on the light-curves of this burst, where the jet corresponding to the $\gamma$-ray pulses at around $20$~s is used to refresh the external-shock. It is shown that the light-curves of very early phase and X-ray afterglow after $40$~s, involving the X-ray bump at around $100$~s, can be well modelled in the external-shock scenario. For the obtained initial outflow, we estimate the minimum magnetization factor of the jet based on the fact that the photospheric emission of this jet is missed in the very early phase., Comment: Accepted for publication in Astrophysical Journal

Knowledge about the Lorentz factor and its evolution of relativistic jets in gamma-ray bursts (GRBs) is crucial to understand their physics. An exact value of bulk Lorentz factor can be estimated based on a high-energy spectral cutoff, which may appear in GRBs' prompt emission owing to the absorption of photon-photon pair production. In this work, we focus on the investigation of the bulk Lorentz factor evolution of jets in an individual burst. Based on \textsl{Fermi} observations, we search for the bursts with multiple $\gamma$-ray pulses characterized by a high-energy spectral cutoff, and nine GRBs are obtained. Together with the estimation of the pulse duration and radiation spectrum, the Lorentz factor of jets corresponding to different pulses in an individual GRB are estimated. It is shown that the Lorentz factor of jets in an individual GRB fluctuates within a certain range and without a general trend in these nine GRBs. In addition, the Lorentz factors of the jets in GRBs~130821A, 160509A and 160625B seem to increase with time. We also study the relations among $L_{\rm iso }$, $E_{\rm p,z}$, and $\Gamma$ for the pulses in our sample, which is found to be consistent with that found in previous works., Comment: Accepted for publication in ApJ

It was well known that most of gamma-ray bursts (GRBs) are dominated by positive spectral lags, while a small fraction of GRBs show negative lags. However, Wei et al. firstly identified a well-defined transition from positive lags to negative lags in GRB 160625B, and then got robust limits on possible violation of Lorentz Invariance (LIV) based on the observation. Recently, such a transition has been found in three different emission episodes in \thisgrb by Gunapati et al., which provides us a great opportunity to investigate whether the transition results from LIV-induced observed spectral lags. Our analysis shows that the LIV model can not be compatible with the current observations, whereas, only the spectral evolution induced spectral lags could responsible for the transition. So, spectral evolution can also explain the positive to negative lag in GRB 190530A., Comment: 12 pages, 5 figures, accepted by Astrophysical Journal