arXiv subjects

Gang Liu

Publications and source records attributed to Gang Liu.

At least 73 records · Page 4Linked to original sources

arXiv2025

LongCat-Flash Technical Report

We introduce LongCat-Flash, a 560-billion-parameter Mixture-of-Experts (MoE) language model designed for both computational efficiency and advanced agentic capabilities. Stemming from the need for scalable efficiency, LongCat-Flash adopts two novel designs: (a) Zero-computation Experts, which enables dynamic computational budget allocation and activates 18.6B-31.3B (27B on average) per token depending on contextual demands, optimizing resource usage. (b) Shortcut-connected MoE, which enlarges the computation-communication overlap window, demonstrating notable gains in inference efficiency and throughput compared to models of a comparable scale. We develop a comprehensive scaling framework for large models that combines hyperparameter transfer, model-growth initialization, a multi-pronged stability suite, and deterministic computation to achieve stable and reproducible training. Notably, leveraging the synergy among scalable architectural design and infrastructure efforts, we complete model training on more than 20 trillion tokens within 30 days, while achieving over 100 tokens per second (TPS) for inference at a cost of \$0.70 per million output tokens. To cultivate LongCat-Flash towards agentic intelligence, we conduct a large-scale pre-training on optimized mixtures, followed by targeted mid- and post-training on reasoning, code, and instructions, with further augmentation from synthetic data and tool use tasks. Comprehensive evaluations demonstrate that, as a non-thinking foundation model, LongCat-Flash delivers highly competitive performance among other leading models, with exceptional strengths in agentic tasks. The model checkpoint of LongCat-Flash is open-sourced to foster community research. LongCat Chat: https://longcat.ai Hugging Face: https://huggingface.co/meituan-longcat GitHub: https://github.com/meituan-longcat

cs.CL↗

arXiv2025

ShieldMMU: Detecting and Defending against Controlled-Channel Attacks in Shielding Memory System

Intel SGX and hypervisors isolate non-privileged programs from other software, ensuring confidentiality and integrity. However, side-channel attacks continue to threaten Intel SGX's security, enabling malicious OS to manipulate PTE present bits, induce page faults, and steal memory access traces. Despite extensive research, existing defenses focus on detection or rely on impractical solutions. This paper presents ShieldMMU, a comprehensive solution for mitigating controlled channel attacks, balancing compatibility, performance, and usability. Leveraging a Merkle Tree-inspired Defense Tree (DD-Tree), ShieldMMU protects PTE integrity by detecting, locating, and restoring attacked PTEs. It identifies MMU page table lookup events and side-channel attacks, promptly restoring PTE parameters to prevent page fault traps and ensure secure non-privileged application operation within SGX. Our experiments confirm ShieldMMU's enhanced security and acceptable latency performance.

cs.CR↗

arXiv2025

Lattice distortions and non-sluggish diffusion in BCC refractory high entropy alloys

Refractory high-entropy alloys (RHEAs) have emerged as promising candidates for extreme high-temperature applications, for example, in next-generation turbines and nuclear reactors. In such applications, atomic diffusion critically governs essential properties including creep resistance and microstructural stability. The present study systematically investigates impurity diffusion of Co, Mn, and Zn in single phase (BCC solid solution) HfTiZrNbTa and HfTiZrNbV RHEAs applying the radiotracer technique. A neutron total scattering technique is used to evaluate the pair distribution functions and element-specific lattice distortions in these alloys. \textit{Ab initio}-based calculations give access to lattice distortions and solubilities of the impurities under investigation, including the impact of short-range order. The diffusion results are discussed in relation to calculated substitutional and interstitial solution energies, local lattice distortions, and short-range order effects. Co diffusion is found to be dominated by the interstitial mechanism, exhibiting fast diffusion. These findings reveal important structure-property relationships between local atomic environments and diffusion kinetics in BCC RHEAs, providing critical insights for designing alloys with enhanced high-temperature performance through targeted control of impurity diffusion processes.

cond-mat.mtrl-sci↗

arXiv2025

Is-NeRF: In-scattering Neural Radiance Field for Blurred Images

Neural Radiance Fields (NeRF) has gained significant attention for its prominent implicit 3D representation and realistic novel view synthesis capabilities. Available works unexceptionally employ straight-line volume rendering, which struggles to handle sophisticated lightpath scenarios and introduces geometric ambiguities during training, particularly evident when processing motion-blurred images. To address these challenges, this work proposes a novel deblur neural radiance field, Is-NeRF, featuring explicit lightpath modeling in real-world environments. By unifying six common light propagation phenomena through an in-scattering representation, we establish a new scattering-aware volume rendering pipeline adaptable to complex lightpaths. Additionally, we introduce an adaptive learning strategy that enables autonomous determining of scattering directions and sampling intervals to capture finer object details. The proposed network jointly optimizes NeRF parameters, scattering parameters, and camera motions to recover fine-grained scene representations from blurry images. Comprehensive evaluations demonstrate that it effectively handles complex real-world scenarios, outperforming state-of-the-art approaches in generating high-fidelity images with accurate geometric details.

cs.GR↗

arXiv2025

Magnon cat states in a cavity-magnon-qubit system via two-magnon driving and dissipation

We propose an efficient method for dissipative generation of magnonic cat states in a cavity-magnon-qubit hybrid system by exploiting a two-magnon driving and dissipation mechanism. When both the magnon and qubit are driven, a coherent nonlinear two-magnon interaction is induced, wherein the qubit and the magnon mode exchange energy through magnon pairs. The dissipation of the qubit is exploited to steer the magnon mode into a quantum superposition of distinct coherent states, where the magnon mode evolves into either an even or odd cat state, depending on the parity of the magnon initial state. For the case where the magnon initial state is a superposition state, e.g., of $\ket{0}$ and $\ket{1}$, the magnon mode can evolve into a weighted mixture of the even and odd cat states. We also find that magnon squeezed states may emerge during the short-time evolution, showcasing the capability of our mechanism in preparing diverse magnon non-classical states. Magnonic cat and squeezed states are macroscopic quantum states and find applications in macroscopic quantum studies and quantum sensing, e.g., in the dark matter search using ferromagnetic axion haloscopes.

quant-ph↗

arXiv2025

Unsupervised deep learning model for fast energy layer pre-selection of delivery-efficient proton arc therapy plan optimization of nasopharyngeal carcinoma

Proton arc therapy (PAT) is an emerging and promising modality in radiotherapy, offering improved dose distribution and treatment robustness over intensity-modulated proton therapy. Yet, identifying the optimal energy layer (EL) sequence remains challenging due to the intensive computational demand and prolonged treatment delivery time. This study proposes an unsupervised deep learning model for fast EL pre-selection that minimizes EL switch (ELS) time while maintaining high plan quality. We introduce a novel data representation method, spot-count representation, which encodes the number of proton spots intersecting the target and organs at risk (OAR) in a matrix structured by sorted gantry angles and energy layers. This representation serves as the input of an U-Net style architecture, SPArc_dl, which is trained using a tri-objective function: maximizing spot-counts on target, minimizing spot-counts on OAR, and reducing ELS time. The model is evaluated on 35 nasopharyngeal cancer cases, and its performance is compared to SPArc_particle_swarm (SPArc_ps). SPArc_dl produces EL pre-selection that significantly improves both plan quality and delivery efficiency. Compared to SPArc_ps, it enhances the conformity index by 0.1 (p<0.01), reduces the homogeneity index by 0.71 (p<0.01), lowers the brainstem mean dose by 0.25 (p<0.01), and shortens the ELS time by 37.2% (p < 0.01). The results unintentionally reveal employing unchanged ELS is more time-wise efficient than descended ELS. SPArc_dl's inference time is within 1 second. However, SPArc_dl plan demonstrates limitation in robustness. The proposed spot-count representation lays a foundation for incorporating unsupervised deep learning approaches into EL pre-selection task. SPArc_dl is a fast tool for generating high-quality PAT plans by strategically pre-selecting EL to reduce delivery time while maintaining excellent dosimetric performance.

physics.med-ph↗

arXiv2025

ALScope: A Unified Toolkit for Deep Active Learning

Deep Active Learning (DAL) reduces annotation costs by selecting the most informative unlabeled samples during training. As real-world applications become more complex, challenges stemming from distribution shifts (e.g., open-set recognition) and data imbalance have gained increasing attention, prompting the development of numerous DAL algorithms. However, the lack of a unified platform has hindered fair and systematic evaluation under diverse conditions. Therefore, we present a new DAL platform ALScope for classification tasks, integrating 10 datasets from computer vision (CV) and natural language processing (NLP), and 21 representative DAL algorithms, including both classical baselines and recent approaches designed to handle challenges such as distribution shifts and data imbalance. This platform supports flexible configuration of key experimental factors, ranging from algorithm and dataset choices to task-specific factors like out-of-distribution (OOD) sample ratio, and class imbalance ratio, enabling comprehensive and realistic evaluation. We conduct extensive experiments on this platform under various settings. Our findings show that: (1) DAL algorithms' performance varies significantly across domains and task settings; (2) in non-standard scenarios such as imbalanced and open-set settings, DAL algorithms show room for improvement and require further investigation; and (3) some algorithms achieve good performance, but require significantly longer selection time.

cs.LG↗

arXiv2025

On the dynamics of Halley's method

In this article, we study the global dynamics of Halley's method applied to complex polynomials. Specifically, we analyze the structure and connectivity of the Julia set of this method. The convergence behavior, symmetry properties, and topological features of the corresponding Fatou and Julia sets are studied for various classes of polynomials, including unicritical, cubic, and quartic polynomials with non-trivial symmetry groups. In particular, we prove that the Halley's method $H_p$ is convergent, its Julia set is connected, the immediate basins are unbounded and the symmetry group of it coincides with that of the polynomial whenever $p$ belongs to one of the above classes. We further extend our results to a broader class of polynomials. It is shown that the immediate basin of the Halley's method $H_p$ corresponding to a root of $p$ can be bounded. We also make some remarks on the dynamics of the Halley's method applied to a cubic polynomial in general.

math.DS↗

arXiv2025

Minimum-Weight Half-Plane Hitting Set

Given a set $P$ of $n$ weighted points and a set $H$ of $n$ half-planes in the plane, the hitting set problem is to compute a subset $P'$ of points from $P$ such that each half-plane contains at least one point from $P'$ and the total weight of the points in $P'$ is minimized. The previous best algorithm solves the problem in $O(n^{7/2}\log^2 n)$ time. In this paper, we present a new algorithm with runtime $O(n^{5/2}\log^2 n)$.

cs.CG↗

arXiv2025

Smartphone-integrated RPA-CRISPR-Cas12a Detection System with Microneedle Sampling for Point-of-Care Diagnosis of Potato Late Blight in Early Stage

Potato late blight, caused by the oomycete pathogen Phytophthora infestans, is one of the most devastating diseases affecting potato crops in the history. Although conventional detection methods of plant diseases such as PCR and LAMP are highly sensitive and specific, they rely on bulky and expensive laboratory equipment and involve complex operations, making them impracticable for point-of care diagnosis in the field. Here in this study, we report a portable RPA-CRISPR based diagnosis system for plant disease, integrating smartphone for acquisition and analysis of fluorescent images. A polyvinyl alcohol (PVA) microneedle patch was employed for sample extraction on the plant leaves within one minute, the DNA extraction efficiency achieved 56 ug/mg, which is approximately 3 times to the traditional CTAB methods (18 ug/mg). The system of RPA-CRISPR-Cas12a isothermal assay was established to specifically target P. infestans with no cross-reactivity observed against closely-related species (P. sojae, P. capsici). The system demonstrated a detection limit of 2 pg/uL for P. infestans genomic DNA, offering sensitivity comparable to that of benchtop laboratory equipment. The system demonstrates the early-stage diagnosis capability by achieving a approximately 80% and 100% detection rate on the third and fourth day post-inoculation respectively, before visible symptoms observed on the leaves. The smartphone-based "sample-to-result" system decouples the limitations of traditional methods that rely heavily on specialized equipment, offering a promising way for early-stage plant disease detection and control in the field.

q-bio.QM↗

arXiv2025

Foundation Molecular Grammar: Multi-Modal Foundation Models Induce Interpretable Molecular Graph Languages

Recent data-efficient molecular generation approaches exploit graph grammars to introduce interpretability into the generative models. However, grammar learning therein relies on expert annotation or unreliable heuristics for algorithmic inference. We propose Foundation Molecular Grammar (FMG), which leverages multi-modal foundation models (MMFMs) to induce an interpretable molecular language. By exploiting the chemical knowledge of an MMFM, FMG renders molecules as images, describes them as text, and aligns information across modalities using prompt learning. FMG can be used as a drop-in replacement for the prior grammar learning approaches in molecular generation and property prediction. We show that FMG not only excels in synthesizability, diversity, and data efficiency but also offers built-in chemical interpretability for automated molecular discovery workflows. Code is available at https://github.com/shiningsunnyday/induction.

cs.AI↗

arXiv2025

Directed Graph Grammars for Sequence-based Learning

Directed acyclic graphs (DAGs) are a class of graphs commonly used in practice, with examples that include electronic circuits, Bayesian networks, and neural architectures. While many effective encoders exist for DAGs, it remains challenging to decode them in a principled manner, because the nodes of a DAG can have many different topological orders. In this work, we propose a grammar-based approach to constructing a principled, compact and equivalent sequential representation of a DAG. Specifically, we view a graph as derivations over an unambiguous grammar, where the DAG corresponds to a unique sequence of production rules. Equivalently, the procedure to construct such a description can be viewed as a lossless compression of the data. Such a representation has many uses, including building a generative model for graph generation, learning a latent space for property prediction, and leveraging the sequence representational continuity for Bayesian Optimization over structured data. Code is available at https://github.com/shiningsunnyday/induction.

cs.LG↗

arXiv2025

Improve Multi-Modal Embedding Learning via Explicit Hard Negative Gradient Amplifying

With the rapid advancement of multi-modal large language models (MLLMs) in recent years, the foundational Contrastive Language-Image Pretraining (CLIP) framework has been successfully extended to MLLMs, enabling more powerful and universal multi-modal embeddings for a wide range of retrieval tasks. Despite these developments, the core contrastive learning paradigm remains largely unchanged from CLIP-style models to MLLMs. Within this framework, the effective mining of hard negative samples continues to be a critical factor for enhancing performance. Prior works have introduced both offline and online strategies for hard negative mining to improve the efficiency of contrastive learning. While these approaches have led to improved multi-modal embeddings, the specific contribution of each hard negative sample to the learning process has not been thoroughly investigated. In this work, we conduct a detailed analysis of the gradients of the info-NCE loss with respect to the query, positive, and negative samples, elucidating the role of hard negatives in updating model parameters. Building upon this analysis, we propose to explicitly amplify the gradients associated with hard negative samples, thereby encouraging the model to learn more discriminative embeddings. Our multi-modal embedding model, trained with the proposed Explicit Gradient Amplifier and based on the LLaVA-OneVision-7B architecture, achieves state-of-the-art performance on the MMEB benchmark compared to previous methods utilizing the same MLLM backbone. Furthermore, when integrated with our self-developed MLLM, QQMM, our approach attains the top rank on the MMEB leaderboard. Code and models are released on https://github.com/QQ-MM/QQMM-embed.

cs.CV↗

arXiv2025

FLTG: Byzantine-Robust Federated Learning via Angle-Based Defense and Non-IID-Aware Weighting

Byzantine attacks during model aggregation in Federated Learning (FL) threaten training integrity by manipulating malicious clients' updates. Existing methods struggle with limited robustness under high malicious client ratios and sensitivity to non-i.i.d. data, leading to degraded accuracy. To address this, we propose FLTG, a novel aggregation algorithm integrating angle-based defense and dynamic reference selection. FLTG first filters clients via ReLU-clipped cosine similarity, leveraging a server-side clean dataset to exclude misaligned updates. It then dynamically selects a reference client based on the prior global model to mitigate non-i.i.d. bias, assigns aggregation weights inversely proportional to angular deviations, and normalizes update magnitudes to suppress malicious scaling. Evaluations across datasets of varying complexity under five classic attacks demonstrate FLTG's superiority over state-of-the-art methods under extreme bias scenarios and sustains robustness with a higher proportion(over 50%) of malicious clients.

cs.CR↗

arXiv2025

MolTextNet: A Two-Million Molecule-Text Dataset for Multimodal Molecular Learning

Small molecules are essential to drug discovery, and graph-language models hold promise for learning molecular properties and functions from text. However, existing molecule-text datasets are limited in scale and informativeness, restricting the training of generalizable multimodal models. We present MolTextNet, a dataset of 2.5 million high-quality molecule-text pairs designed to overcome these limitations. To construct it, we propose a synthetic text generation pipeline that integrates structural features, computed properties, bioactivity data, and synthetic complexity. Using GPT-4o-mini, we create structured descriptions for 2.5 million molecules from ChEMBL35, with text over 10 times longer than prior datasets. MolTextNet supports diverse downstream tasks, including property prediction and structure retrieval. Pretraining CLIP-style models with Graph Neural Networks and ModernBERT on MolTextNet yields improved performance, highlighting its potential for advancing foundational multimodal modeling in molecular science. Our dataset is available at https://huggingface.co/datasets/liuganghuggingface/moltextnet.

q-bio.BM↗

arXiv2025

Critique Before Thinking: Mitigating Hallucination through Rationale-Augmented Instruction Tuning

Despite significant advancements in multimodal reasoning tasks, existing Large Vision-Language Models (LVLMs) are prone to producing visually ungrounded responses when interpreting associated images. In contrast, when humans embark on learning new knowledge, they often rely on a set of fundamental pre-study principles: reviewing outlines to grasp core concepts, summarizing key points to guide their focus and enhance understanding. However, such preparatory actions are notably absent in the current instruction tuning processes. This paper presents Re-Critic, an easily scalable rationale-augmented framework designed to incorporate fundamental rules and chain-of-thought (CoT) as a bridge to enhance reasoning abilities. Specifically, Re-Critic develops a visual rationale synthesizer that scalably augments raw instructions with rationale explanation. To probe more contextually grounded responses, Re-Critic employs an in-context self-critic mechanism to select response pairs for preference tuning. Experiments demonstrate that models fine-tuned with our rationale-augmented dataset yield gains that extend beyond hallucination-specific tasks to broader multimodal reasoning tasks.

cs.CV↗

arXiv2025

Innovative Thinking, Infinite Humor: Humor Research of Large Language Models through Structured Thought Leaps

Humor is previously regarded as a gift exclusive to humans for the following reasons. Humor is a culturally nuanced aspect of human language, presenting challenges for its understanding and generation. Humor generation necessitates a multi-hop reasoning process, with each hop founded on proper rationales. Although many studies, such as those related to GPT-o1, focus on logical reasoning with reflection and correction, they still fall short in humor generation. Due to the sparsity of the knowledge graph in creative thinking, it is arduous to achieve multi-hop reasoning. Consequently, in this paper, we propose a more robust framework for addressing the humor reasoning task, named LoL. LoL aims to inject external information to mitigate the sparsity of the knowledge graph, thereby enabling multi-hop reasoning. In the first stage of LoL, we put forward an automatic instruction-evolution method to incorporate the deeper and broader thinking processes underlying humor. Judgment-oriented instructions are devised to enhance the model's judgment capability, dynamically supplementing and updating the sparse knowledge graph. Subsequently, through reinforcement learning, the reasoning logic for each online-generated response is extracted using GPT-4o. In this process, external knowledge is re-introduced to aid the model in logical reasoning and the learning of human preferences. Finally, experimental results indicate that the combination of these two processes can enhance both the model's judgment ability and its generative capacity. These findings deepen our comprehension of the creative capabilities of large language models (LLMs) and offer approaches to boost LLMs' creative abilities for cross-domain innovative applications.

cs.AI↗

arXiv2025

Cross-Frame OTFS Parameter Estimation Based On Chinese Remainder Theorem

Orthogonal time-frequency space (OTFS) is a potential waveform for integrated sensing and communications (ISAC) systems because it can manage communication and sensing metrics in one unified domain, and has better performance in high mobility scenarios. In practice, a target might come from far distance or with ultra-high speed. However, the max unambiguous range and max tolerable velocity of OTFS-ISAC system is limited by the unambiguous round-trip delay and Doppler shift, which are related to OTFS frame, i.e., time slots and subcarrier spacing, respectively. To enlarge the sensing range, a novel OTFS cross-frame ranging and velocity estimation model as well as its corresponding method based on the Chinese remainder theorem (CRT) are proposed in this paper. By designing co-prime numbers of subcarriers and time slots in different subframes, the difference in the responses of the subframes for a target can be used to estimate the distance and velocity of an out-of-range target. Several frame structures are further designed for specific sensing scenarios, such as target with ultra-high speed or at far distance. Simulation results show that the proposed method can achieve significantly better performance in NMSE compared with the classic sensing methods under the condition of same time and frequency resources.

eess.SP↗