Showing 1–50 of 68 results for author: Bao, T

Enhancing Scientific Named Entity Recognition via Large Language Models: A Type-driven Multi-task Learning Approach

Authors: Tong Bao, Yi Zhao, Heng Zhang, Chengzhi Zhang

Abstract: Scientific named entity recognition (SciNER) plays a crucial role in information extraction and knowledge discovery from scientific texts. Recently, large language models (LLMs) have demonstrated the capacity to achieve competitive SciNER performance with minimal human effort. Existing research highlights the importance of incorporating candidate entity type information for accurate entity recogni… ▽ More Scientific named entity recognition (SciNER) plays a crucial role in information extraction and knowledge discovery from scientific texts. Recently, large language models (LLMs) have demonstrated the capacity to achieve competitive SciNER performance with minimal human effort. Existing research highlights the importance of incorporating candidate entity type information for accurate entity recognition and classification by LLMs. However, when too many candidate entity types are provided in the prompt, LLMs struggle to accurately recognize and label entities in scientific texts, where entity types are more complex than in general domains. To address this challenge, we propose TdSciNER, a type-driven approach that effectively leverages entity type information to enhance SciNER performance. In TdSciNER, we first design an entity type filter model to identify the most likely entity types present in a given sentence. Subsequently, we introduce an auxiliary multi-class entity typing task within a multi-task learning framework alongside SciNER to obtain richer contextual representations. Then, we develop a novel demonstration selection strategy based on sentence similarity and entity type diversity to activate the in-context learning capabilities of LLMs, thereby improving entity recognition accuracy across diverse scientific domains. Experiments on three datasets demonstrate that our method achieves performance comparable to fully supervised models. Further analysis validates that each entity type-driven component in TdSciNER contributes to the improvement of SciNER performance. This work provides valuable insights for future advancements in SciNER and broader information extraction tasks in scientific text mining. △ Less

Submitted 14 August, 2026; v1 submitted 9 August, 2026; originally announced August 2026.

Journal ref: Expert Systems With Applications, 2026

Developing and Validating the Spanish Version of the Large Language Models Dependency Scale (LLM-D12-SP)

Authors: Tran Gia Bao, Mo El-Haj, Sameha Al-Shakhsi, Antonio Garcia-Cabot, Raian Ali, Ala Yankouskaya

Abstract: There is a growing need for reliable and culturally validated instruments to assess psychological dependency on large language models (LLMs), particularly as LLMs are increasingly used for task execution, decision-making, and communication in organizational and work-related settings. This need is especially relevant for Spanish-speaking populations, where LLM adoption is rapidly expanding, yet val… ▽ More There is a growing need for reliable and culturally validated instruments to assess psychological dependency on large language models (LLMs), particularly as LLMs are increasingly used for task execution, decision-making, and communication in organizational and work-related settings. This need is especially relevant for Spanish-speaking populations, where LLM adoption is rapidly expanding, yet validated psychometric tools remain scarce. The present study reports the first validation of the Spanish version of the Large Language Model Dependency Scale (LLM-D12-SP), extending prior validations conducted in English- and Arabic-speaking samples. The LLM-D12 is a two-dimensional instrument assessing Instrumental Dependency (reliance on LLMs for performing tasks and supporting decisions) and Relationship Dependency (psychological reliance on LLMs for companionship and social interaction). A total of 386 Spanish-speaking participants (M = 28.0 years, SD = 6.1; 55% male) completed the LLM-D12-SP. Confirmatory factor analysis supported the original two-factor structure. The scale demonstrated good internal consistency (Cronbach's alpha = 0.89 total; 0.86 Instrumental; 0.85 Relationship). Discriminant validity analyses indicated that the two subscales represent related but distinct constructs. External validation showed that both dependency dimensions were positively associated with internet addiction and perceived trustworthiness of LLMs, while showing weak or no association with need for cognition. Together with prior English and Arabic validations, these findings establish cross-linguistic support for the scale's structure and provide a psychometrically sound tool for investigating psychological aspects of LLM use in organizational contexts. △ Less

Submitted 24 July, 2026; originally announced July 2026.

Comments: 32 pages

Journal ref: Discover Psychology 2026

SeedSmith: LLM-Driven Seed Synthesis for Directed Fuzzing

Authors: Junmin Zhu, Siyu Liu, Jie Hu, Fabio Gritti, Ati Priya Bajaj, Hulin Wang, Wenbo Guo, Tiffany Bao, Christopher Kruegel, Giovanni Vigna

Abstract: Directed fuzzing steers fuzzers toward user-defined sink functions to identify vulnerabilities, but it frequently fails to trigger crashes even after long campaigns. We identify two challenges that prevent directed fuzzers from exposing crashes: incomplete static analysis of indirect calls, which leaves reachable paths invisible to distance-based guidance, and lack of semantic guidance for crash p… ▽ More Directed fuzzing steers fuzzers toward user-defined sink functions to identify vulnerabilities, but it frequently fails to trigger crashes even after long campaigns. We identify two challenges that prevent directed fuzzers from exposing crashes: incomplete static analysis of indirect calls, which leaves reachable paths invisible to distance-based guidance, and lack of semantic guidance for crash preconditions, which blind mutation cannot satisfy within practical time budgets. A natural intervention point is the initial seed corpus: seeds that encode the right control-flow path and satisfy key crash preconditions shift fuzzing from blind exploration to local refinement. Existing seed generation approaches address neither: grammar-based and format-driven methods produce structurally valid inputs with no sink awareness, while LLM-based methods either lack sink targeting or inherit static analysis limitations through one-shot prompting. We present SeedSmith, an agentic LLM pipeline that replicates a security analyst's workflow: starting from a sink, it iteratively explores the codebase, resolves indirect calls, identifies crash preconditions, and synthesizes concrete inputs that satisfy them. Because SeedSmith operates as a seed generation front-end, its seeds are fuzzer-agnostic and improve any downstream mutation-based fuzzer without modification. On Magma, fuzzers using SeedSmith seeds achieve geometric mean crash-time speedups of 11.51 times (AFL++) to 14.66 times (AFLGo) over default seeds. On ARVO, SeedSmith enables fuzzers to trigger 16 previously unreachable bugs spanning 10 projects with diverse input formats. △ Less

Submitted 14 July, 2026; v1 submitted 9 July, 2026; originally announced July 2026.

ACM Class: D.2.5

GeoGS-SLAM: Geometry-Only Gaussian Splatting for Dense Monocular SLAM

Authors: Lipu Zhou, Yaoyun Kang, Junxiang Pang, Shengkai Sun, Tingting Bao, Kehan Wang

Abstract: Dense visual SLAM is a fundamental problem in robotics. Recent advances in 3DGS have demonstrated its potential for dense SLAM. Existing 3DGS frameworks focus on both appearance and geometry modeling. However, scene geometry is typically more critical for SLAM than novel view synthesis because downstream robotic tasks, such as navigation and obstacle avoidance, rely primarily on accurate spatial g… ▽ More Dense visual SLAM is a fundamental problem in robotics. Recent advances in 3DGS have demonstrated its potential for dense SLAM. Existing 3DGS frameworks focus on both appearance and geometry modeling. However, scene geometry is typically more critical for SLAM than novel view synthesis because downstream robotic tasks, such as navigation and obstacle avoidance, rely primarily on accurate spatial geometry rather than photorealistic rendering. This observation raises a natural question: Is it feasible for 3DGS to perform 3D reconstruction without scene appearance modeling? Motivated by this, we propose Geometry-only Gaussian Splatting (GeoGS), which directly reconstructs scene geometry, and further present GeoGS-SLAM, a dense visual SLAM system built upon this representation. Specifically, GeoGS retains only spatial parameters to reduce the number of per-primitive parameters by over 80%. In contrast to existing 3DGS methods, GeoGS focuses solely on geometric reconstruction, which significantly reduces the number of Gaussian primitives, accelerates geometric convergence, and enhances robustness to illumination variations. In addition, we present an effective training framework that optimizes the Gaussian primitives via single-view and multi-view geometric and photometric supervision, and speeds up geometry convergence with a local-plane driven initialization that better aligns primitives with local structures. Furthermore, we introduce a map update strategy for loop closure that globally transforms the Gaussian map to align it with the corrected pose estimates, thereby preventing map tearing caused by inconsistent per-viewpoint pose corrections in existing methods. Extensive experiments on synthetic and real-world benchmarks demonstrate that our method outperforms SOTA methods in terms of online mapping efficiency and geometric reconstruction quality. △ Less

Submitted 8 July, 2026; originally announced July 2026.

ARVO: Atlas of Reproducible Vulnerabilities for Open-Source Software

Authors: Xiang Mei, Jordi Del Castillo, Pulkit Singh Singaria, Haoran Xi, Abdelouahab Benchikh, Tiffany Bao, Ruoyu Wang, Yan Shoshitaishvili, Adam Doupé, Hammond Pearce, Brendan Dolan-Gavitt

Abstract: Achieving reproducibility, quantity, and diversity in vulnerability datasets has long been viewed as an inherent three-way trade-off, where improving one dimension often comes at the cost of the others. In practice, reproducibility has been the dimension most often neglected. This has limited what can be automatically extracted from historical bug datasets, and has reduced their utility for downst… ▽ More Achieving reproducibility, quantity, and diversity in vulnerability datasets has long been viewed as an inherent three-way trade-off, where improving one dimension often comes at the cost of the others. In practice, reproducibility has been the dimension most often neglected. This has limited what can be automatically extracted from historical bug datasets, and has reduced their utility for downstream security research. In this work, we propose a method to produce a new security dataset which ensures reproducibility for diverse vulnerabilities at scale by identifying the key obstacles to large-scale bug reproduction and addressing them with general solutions. Using this method, we introduce full reproducibility to the largest open source software vulnerability dataset (OSS-Fuzz) and construct the ARVO dataset (an Atlas of Reproducible Vulnerabilities in Open-source software). ARVO is a large-scale dataset consisting of over 6,100 real-world vulnerabilities across 311 projects. Focusing on reproducibility, ARVO differs from existing datasets by providing each vulnerability in a form that can be consistently rebuilt, triggered, and analyzed across versions. Reproducibility also enables automatic identification of the corresponding patch for each vulnerability and supports direct interaction with vulnerabilities after code changes, capabilities that existing large-scale datasets do not provide. In our evaluation, ARVO successfully reproduces 81% of vulnerabilities and achieves 89.4% accuracy on the located patches. We also discuss ARVO's influence on both upstream practices and downstream security research. △ Less

Submitted 18 June, 2026; v1 submitted 15 June, 2026; originally announced June 2026.

Comments: I found my co-author has already submitted one (arXiv:2408.02153)

Root-Cause-Driven Automated Vulnerability Repair

Authors: Hulin Wang, Zion Leonahenahe Basque, Jie Hu, Ati Priya Bajaj, Yibo Liu, Samuel Zhu, Giorgi Kobakhia, Nikhil Chapre, Will Rosenberg, Siddharth Mishra, Aditya Maheshbhai Gabani, Moritz Schloegel, Adam Doupé, Yan Shoshitaishvili, Ruoyu Wang, Tiffany Bao

Abstract: Recent LLM-based systems have made automated vulnerability repair increasingly practical, but two challenges remain. First, without strong signals about where a bug originates, repair agents drift toward shallow edits that silence the observed failure while leaving the underlying defect unresolved. Second, finding the root cause for bugs is hard: even developers familiar with the codebase frequent… ▽ More Recent LLM-based systems have made automated vulnerability repair increasingly practical, but two challenges remain. First, without strong signals about where a bug originates, repair agents drift toward shallow edits that silence the observed failure while leaving the underlying defect unresolved. Second, finding the root cause for bugs is hard: even developers familiar with the codebase frequently produce fixes that address symptoms rather than the root cause, and LLM-based agents, operating with noisier context and less program understanding, are no exception. We present Kumushi, a root-cause-driven patching agent that addresses both challenges by combining diversified dynamic fault localization with evidence-weighted ranking to focus the LLM on the code most relevant to the defect. To rigorously measure whether Kumushi produces genuinely better patches, we also introduce a two-tier patch quality metric that pairs automated oracle validation with structured expert assessment of patches. Evaluated on 178 C/C++ vulnerabilities, Kumushi substantially outperforms prior specialized repair agents under automated evaluation while matching a frontier commercial coding agent. Expert assessment then reveals differences that oracles cannot: Kumushi produces more root-cause fixes and fewer superficial patches, and is preferred in the majority of decisive pairwise comparisons. Together, these results demonstrate that progress in automated vulnerability repair requires not only stronger patching systems, but also richer evaluation methods capable of distinguishing genuine fixes from oracle-passing ones. △ Less

Submitted 5 May, 2026; originally announced May 2026.

Comments: Under submission

Generating Synthetic Malware Samples Using Generative AI

Authors: Tiffany Bao, Kylie Trousil, Quang Duy Tran, Fabio Di Troia, Younghee Park

Abstract: Malware attacks have a significant negative impact on organizations of varied scales in the field of cybersecurity. Recently, malware researchers have increasingly turned to machine learning techniques to combat sophisticated obfuscation methods used in malware. However, collecting a diverse set of malware samples with various obfuscation techniques is challenging and often takes years, especially… ▽ More Malware attacks have a significant negative impact on organizations of varied scales in the field of cybersecurity. Recently, malware researchers have increasingly turned to machine learning techniques to combat sophisticated obfuscation methods used in malware. However, collecting a diverse set of malware samples with various obfuscation techniques is challenging and often takes years, especially for newly developed malware. This issue is further compounded by a well-known limitation of machine learning models: their poor performance when training data is scarce. In this paper, we propose a new system for generating synthetic malware samples to augment imbalanced malware dataset. Our approach decomposes malware binary samples into mnemonic opcode sequences, leveraging natural language processing to extract contextual meaning behind malware opcode features to aid the learning of generative AI (GenAI) employed in this paper, Generative Adversarial Networks (GAN), Wasserstein Generative Adversarial Networks with Gradient Penalty (WGAN-GP), and a modified Diffusion model. The experiment results show that augmenting training data with Diffusion-based synthetic data significantly improves classification performance for minor classes by up to 60% on average. This enhancement ultimately leads to an overall malware classification performance of 96%, an 8% improvement. These findings demonstrate the high quality and fidelity of the synthetic data, its robustness, and its potential applications in malware analysis. Specifically, synthetic malware data proves effective in improving the classification of minor malware classes and detection rates, even though the size of known malware data is significantly small. △ Less

Submitted 23 April, 2026; originally announced April 2026.

Comments: 12 pages, 8 figures. This paper has been published in IEEE Access, available at this URL: https://ieeexplore.ieee.org/document/10947040

Journal ref: IEEE Access, vol. 13, pp. 59725-59736, 2025

Impact of large language models on peer review opinions from a fine-grained perspective: Evidence from top conference proceedings in AI

Authors: Wenqing Wu, Chengzhi Zhang, Yi Zhao, Tong Bao

Abstract: With the rapid advancement of Large Language Models (LLMs), the academic community has faced unprecedented disruptions, particularly in the realm of academic communication. The primary function of peer review is improving the quality of academic manuscripts, such as clarity, originality and other evaluation aspects. Although prior studies suggest that LLMs are beginning to influence peer review, i… ▽ More With the rapid advancement of Large Language Models (LLMs), the academic community has faced unprecedented disruptions, particularly in the realm of academic communication. The primary function of peer review is improving the quality of academic manuscripts, such as clarity, originality and other evaluation aspects. Although prior studies suggest that LLMs are beginning to influence peer review, it remains unclear whether they are altering its core evaluative functions. Moreover, the extent to which LLMs affect the linguistic form, evaluative focus, and recommendation-related signals of peer-review reports has yet to be systematically examined. In this study, we examine the changes in peer review reports for academic articles following the emergence of LLMs, emphasizing variations at fine-grained level. Specifically, we investigate linguistic features such as the length and complexity of words and sentences in review comments, while also automatically annotating the evaluation aspects of individual review sentences. We also use a maximum likelihood estimation method, previously established, to identify review reports that potentially have modified or generated by LLMs. Finally, we assess the impact of evaluation aspects mentioned in LLM-assisted review reports on the informativeness of recommendation for paper decision-making. The results indicate that following the emergence of LLMs, peer review texts have become longer and more fluent, with increased emphasis on summaries and surface-level clarity, as well as more standardized linguistic patterns, particularly reviewers with lower confidence score. At the same time, attention to deeper evaluative dimensions, such as originality, replicability, and nuanced critical reasoning, has declined. △ Less

Submitted 21 April, 2026; originally announced April 2026.

Comments: Scientometrics

Beyond Single-Dimension Novelty: How Combinations of Theory, Method, and Results-based Novelty Shape Scientific Impact

Authors: Yi Zhao, Yang Chenggang, Yuzhuo Wang, Tong Bao, Zhang Heng, Chengzhi Zhang

Abstract: Scientific novelty drives advances at the research frontier, yet it is also associated with heightened uncertainty and potential resistance from incumbent paradigms, leading to complex patterns of scientific impact. Prior studies have primarily ex-amined the relationship between a single dimension of novelty -- such as theoreti-cal, methodological, or results-based novelty -- and scientific impact… ▽ More Scientific novelty drives advances at the research frontier, yet it is also associated with heightened uncertainty and potential resistance from incumbent paradigms, leading to complex patterns of scientific impact. Prior studies have primarily ex-amined the relationship between a single dimension of novelty -- such as theoreti-cal, methodological, or results-based novelty -- and scientific impact. However, because scientific novelty is inherently multidimensional, focusing on isolated dimensions may obscure how different types of novelty jointly shape impact. Consequently, we know little about how combinations of novelty types influence scientific impact. To this end, we draw on a dataset of 15,322 articles published in Nature Communications. Using the DeepSeek-V3 model, we classify articles into three novelty dimensions based on the content of their Introduction sections: theoretical novelty, methodological novelty, and results-based novelty. These dimensions may coexist within the same article, forming distinct novelty configura-tions. Scientific impact is measured using five-year citation counts and indicators of whether an article belongs to the top 1% or top 10% highly cited papers. Descriptive results indicate that results-based novelty alone and the simultaneous presence of all three novelty types are the dominant configurations in the sample. Regression results further show that articles with results-based novelty only re-ceive significantly more citations and are more likely to rank among the top 1% and top 10% highly cited papers than articles exhibiting all three novelty types. These findings advance our understanding of how multidimensional novelty configurations shape knowledge diffusion. △ Less

Submitted 14 April, 2026; originally announced April 2026.

Comments: AII-EEKE 2026

SimMOF: AI agent for Automated MOF Simulations

Authors: Jaewoong Lee, Taeun Bae, Jihan Kim

Abstract: Metal-organic frameworks (MOFs) offer a vast design space, and as such, computational simulations play a critical role in predicting their structural and physicochemical properties. However, MOF simulations remain difficult to access because reliable analysis require expert decisions for workflow construction, parameter selection, tool interoperability, and the preparation of computational ready s… ▽ More Metal-organic frameworks (MOFs) offer a vast design space, and as such, computational simulations play a critical role in predicting their structural and physicochemical properties. However, MOF simulations remain difficult to access because reliable analysis require expert decisions for workflow construction, parameter selection, tool interoperability, and the preparation of computational ready structures. Here, we introduce SimMOF, a large language model based multi agent framework that automates end-to-end MOF simulation workflows from natural language queries. SimMOF translates user requests into dependency aware plans, generates runnable inputs, orchestrates multiple agents to execute simulations, and summarizes results with analysis aligned to the user query. Through representative case studies, we show that SimMOF enables adaptive and cognitively autonomous workflows that reflect the iterative and decision driven behavior of human researchers and as such provides a scalable foundation for data driven MOF research. △ Less

Submitted 6 August, 2026; v1 submitted 30 March, 2026; originally announced March 2026.

Comments: 42 pages, 7 figures, 3 tables

ChemCLIP: Bridging Organic and Inorganic Anticancer Compounds Through Contrastive Learning

Authors: Mohamad Koohi-Moghadam, Hongzhe Sun, Hongyan Li, Kyongtae Tyler Bae

Abstract: The discovery of anticancer therapeutics has traditionally treated organic small molecules and metal-based coordination complexes as separate chemical domains, limiting knowledge transfer despite their shared biological objectives. This disparity is particularly pronounced in available data, with extensive screening databases for organic compounds compared to only a few thousand characterized meta… ▽ More The discovery of anticancer therapeutics has traditionally treated organic small molecules and metal-based coordination complexes as separate chemical domains, limiting knowledge transfer despite their shared biological objectives. This disparity is particularly pronounced in available data, with extensive screening databases for organic compounds compared to only a few thousand characterized metal complexes. Here, we introduce ChemCLIP, a dual-encoder contrastive learning framework that bridges this organic-inorganic divide by learning unified representations based on shared anticancer activities rather than structural similarity. We compiled complementary datasets comprising 44,854 unique organic compounds and 5,164 unique metal complexes, standardized across 60 cancer cell lines. By training parallel encoders with activity-aware hard negative mining, we mapped structurally distinct compounds into a shared 256-dimensional embedding space where biologically similar compounds cluster together regardless of chemical class. We systematically evaluated four molecular encoding strategies: Morgan fingerprints, ChemBERTa, MolFormer, and Chemprop, through quantitative alignment metrics, embedding visualizations, and downstream classification tasks. Morgan fingerprints achieved superior performance with an average alignment ratio of 0.899 and downstream classification AUCs of 0.859 (inorganic) and 0.817 (organic). This work establishes contrastive learning as an effective strategy for unifying disparate chemical domains and provides empirical guidance for encoder selection in multi-modal chemistry applications, with implications extending beyond anticancer drug discovery to any scenario requiring cross-domain chemical knowledge transfer. △ Less

Submitted 30 March, 2026; originally announced March 2026.

Comments: 15 pages

ReDiffuse: Rotation Equivariant Diffusion Model for Multi-focus Image Fusion

Authors: Bo Li, Tingting Bao, Lingling Zhang, Weiping Fu, Yaxian Wang, Jun Liu

Abstract: Diffusion models have achieved impressive performance on multi-focus image fusion (MFIF). However, a key challenge in applying diffusion models to the ill-posed MFIF problem is that defocus blur can make common symmetric geometric structures (e.g., textures and edges) appear warped and deformed, often leading to unexpected artifacts in the fused images. Therefore, embedding rotation equivariance i… ▽ More Diffusion models have achieved impressive performance on multi-focus image fusion (MFIF). However, a key challenge in applying diffusion models to the ill-posed MFIF problem is that defocus blur can make common symmetric geometric structures (e.g., textures and edges) appear warped and deformed, often leading to unexpected artifacts in the fused images. Therefore, embedding rotation equivariance into diffusion networks is essential, as it enables the fusion results to faithfully preserve the original orientation and structural consistency of geometric patterns underlying the input images. Motivated by this, we propose ReDiffuse, a rotation-equivariant diffusion model for MFIF. Specifically, we carefully construct the basic diffusion architectures to achieve end-to-end rotation equivariance. We also provide a rigorous theoretical analysis to evaluate its intrinsic equivariance error, demonstrating the validity of embedding equivariance structures. ReDiffuse is comprehensively evaluated against various MFIF methods across four datasets (Lytro, MFFW, MFI-WHU, and Road-MF). Results demonstrate that ReDiffuse achieves competitive performance, with improvements of 0.28-6.64\% across six evaluation metrics. The code is available at https://github.com/MorvanLi/ReDiffuse. △ Less

Submitted 22 March, 2026; originally announced March 2026.

Comments: 10 pages, 9 figures

Pushan: Trace-Free Deobfuscation of Virtualization-Obfuscated Binaries

Authors: Ashwin Sudhir, Zion Leonahenahe Basque, Wil Gibbs, Ati Priya Bajaj, Pulkit Singh Singaria, Mitchell Zakocs, Jie Hu, Moritz Schloegel, Tiffany Bao, Adam Doupe, Yan Shoshitaishvili, Ruoyu Wang

Abstract: In the ever-evolving battle against malware, binary obfuscation techniques are a formidable barrier to effective analysis by both human security analysts and automated systems. In particular, virtualization or VM-based obfuscation is one of the strongest protection mechanisms that evade automated analysis. Despite widespread use of virtualization, existing automated deobfuscation techniques suffer… ▽ More In the ever-evolving battle against malware, binary obfuscation techniques are a formidable barrier to effective analysis by both human security analysts and automated systems. In particular, virtualization or VM-based obfuscation is one of the strongest protection mechanisms that evade automated analysis. Despite widespread use of virtualization, existing automated deobfuscation techniques suffer from three major drawbacks. First, they only work on execution traces, which prevents them from recovering all logic in an obfuscated binary. Second, they depend on dynamic symbolic execution, which is expensive and does not scale in practice. Third, they cannot generate "well-formed" code, which prevents existing binary decompilers from generating human-friendly output. This paper introduces PUSHAN, a novel and generic technique for deobfuscating virtualization-obfuscated binaries while overcoming the limitations of existing techniques. PUSHAN is trace-free and avoids path-constraint accumulation by using VPC-sensitive, constraint-free symbolic emulation to recover a complete CFG of the virtualized function. It is the first approach that also decompiles the protected code into high-quality C pseudocode to enable effective analysis. Crucially, PUSHAN circumvents reliance on path satisfiability, a known NP-hard problem that hampers scalability. We evaluate PUSHAN on more than 1,000 binaries, including targets protected by academic state of the art (Tigress) and commercial-strength obfuscators VMProtect and Themida. PUSHAN successfully deobfuscates these binaries, retrieves their complete CFGs, and decompiles them to C pseudocode. We further demonstrate applicability by analyzing a previously unanalyzed VMProtect-obfuscated malware sample from VirusTotal, where our decompiled output enables LLM-assisted code simplification, reuse, and program understanding. △ Less

Submitted 18 March, 2026; originally announced March 2026.

Multimodal Protein Language Models for Enzyme Kinetic Parameters: From Substrate Recognition to Conformational Adaptation

Authors: Fei Wang, Xinye Zheng, Kun Li, Yanyan Wei, Yuxin Liu, Ganpeng Hu, Tong Bao, Jingwen Yang

Abstract: Predicting enzyme kinetic parameters quantifies how efficiently an enzyme catalyzes a specific substrate under defined biochemical conditions. Canonical parameters such as the turnover number ($k_\text{cat}$), Michaelis constant ($K_\text{m}$), and inhibition constant ($K_\text{i}$) depend jointly on the enzyme sequence, the substrate chemistry, and the conformational adaptation of the active site… ▽ More Predicting enzyme kinetic parameters quantifies how efficiently an enzyme catalyzes a specific substrate under defined biochemical conditions. Canonical parameters such as the turnover number ($k_\text{cat}$), Michaelis constant ($K_\text{m}$), and inhibition constant ($K_\text{i}$) depend jointly on the enzyme sequence, the substrate chemistry, and the conformational adaptation of the active site during binding. Many learning pipelines simplify this process to a static compatibility problem between the enzyme and substrate, fusing their representations through shallow operations and regressing a single value. Such formulations overlook the staged nature of catalysis, which involves both substrate recognition and conformational adaptation. In this regard, we reformulate kinetic prediction as a staged multimodal conditional modeling problem and introduce the Enzyme-Reaction Bridging Adapter (ERBA), which injects cross-modal information via fine-tuning into Protein Language Models (PLMs) while preserving their biochemical priors. ERBA performs conditioning in two stages: Molecular Recognition Cross-Attention (MRCA) first injects substrate information into the enzyme representation to capture specificity; Geometry-aware Mixture-of-Experts (G-MoE) then integrates active-site structure and routes samples to pocket-specialized experts to reflect induced fit. To maintain semantic fidelity, Enzyme-Substrate Distribution Alignment (ESDA) enforces distributional consistency within the PLM manifold in a reproducing kernel Hilbert space. Experiments across three kinetic endpoints and multiple PLM backbones, ERBA delivers consistent gains and stronger out-of-distribution performance compared with sequence-only and shallow-fusion baselines, offering a biologically grounded route to scalable kinetic prediction and a foundation for adding cofactors, mutations, and time-resolved structural cues. △ Less

Submitted 23 April, 2026; v1 submitted 13 March, 2026; originally announced March 2026.

Comments: Accepted by CVPR 2026

Best of Both Worlds: Multimodal Reasoning and Generation via Unified Discrete Flow Matching

Authors: Onkar Susladkar, Tushar Prakash, Gayatri Deshmukh, Kiet A. Nguyen, Jiaxun Zhang, Adheesh Juvekar, Tianshu Bao, Lin Chai, Sparsh Mittal, Inderjit S Dhillon, Ismini Lourentzou

Abstract: We propose UniDFlow, a unified discrete flow-matching framework for multimodal understanding, generation, and editing. It decouples understanding and generation via task-specific low-rank adapters, avoiding objective interference and representation entanglement, while a novel reference-based multimodal preference alignment optimizes relative outcomes under identical conditioning, improving faithfu… ▽ More We propose UniDFlow, a unified discrete flow-matching framework for multimodal understanding, generation, and editing. It decouples understanding and generation via task-specific low-rank adapters, avoiding objective interference and representation entanglement, while a novel reference-based multimodal preference alignment optimizes relative outcomes under identical conditioning, improving faithfulness and controllability without large-scale retraining. UniDFlpw achieves SOTA performance across eight benchmarks and exhibits strong zero-shot generalization to tasks including inpainting, in-context image generation, reference-based editing, and compositional generation, despite no explicit task-specific training. △ Less

Submitted 2 June, 2026; v1 submitted 12 February, 2026; originally announced February 2026.

MedTextWeaver: Procedural Knowledge Evolution in Agentic Medical Text Editing

Authors: Ziyan Xiao, Yinghao Zhu, Liang Peng, Kyongtae T Bae, Lequan Yu

Abstract: Medical text editing is essential for improving communication among diverse stakeholders in clinical settings. However, adapting LLM agents to this task remains challenging because expert supervision is often sparse, fragmented, and distributed across interacting quality dimensions. We identify that direct accumulation or retrieval of individual feedback is insufficient for effective adaptation, a… ▽ More Medical text editing is essential for improving communication among diverse stakeholders in clinical settings. However, adapting LLM agents to this task remains challenging because expert supervision is often sparse, fragmented, and distributed across interacting quality dimensions. We identify that direct accumulation or retrieval of individual feedback is insufficient for effective adaptation, as fragmented evaluations do not directly translate into a coherent understanding of medical text quality. Based on this observation, we propose MedTextWeaver, a training-free framework that transforms fragmented evaluative evidence into global quality principles and actionable procedural knowledge for medical text editing. Across three clinical text datasets and a real-world validation experiment, MedTextWeaver consistently improves performance over strong LLM baselines and existing memory-based adaptation approaches. Further analysis demonstrates that the learned knowledge enables more effective adaptation under limited supervision while providing an explicit and interpretable interface between expert evaluations and LLM editing behavior. △ Less

Submitted 2 August, 2026; v1 submitted 31 January, 2026; originally announced February 2026.

Controllable Diffusion-Based Lesion Inpainting for Scalable Histopathology Data Augmentation

Authors: Mohamad Koohi-Moghadam, Mohammad-Ali Nikouei Mahani, Rex K. H. Au-Yeung, Raymond Yu O, Monalyn Marabi, Piyapharom Intarawichian, Fabian Z. X. Lean, Andrew Ferguson, Kyongtae Tyler Bae

Abstract: Expert-annotated training data remains the critical bottleneck for AI in histopathology, particularly for rare pathologies where even dozens of cases may be unavailable. While data augmentation offers a solution, existing methods fail to generate sufficiently realistic lesion morphologies that preserve tissue-specific architectures. Here we present PathoGen, a diffusion-based generative model enab… ▽ More Expert-annotated training data remains the critical bottleneck for AI in histopathology, particularly for rare pathologies where even dozens of cases may be unavailable. While data augmentation offers a solution, existing methods fail to generate sufficiently realistic lesion morphologies that preserve tissue-specific architectures. Here we present PathoGen, a diffusion-based generative model enabling controllable, high-fidelity lesion inpainting into benign histopathology images. We validate PathoGen across four datasets representing kidney, skin, breast, and prostate pathology. Quantitative assessment confirms PathoGen outperforms state-of-the-art baselines in image fidelity and distributional similarity. Evaluation by six expert pathologists revealed that synthetic images by PathoGen were only marginally distinguished from real tissue image slightly above chance (57.75% accuracy), demonstrating strong perceptual realism of PathoGen-generated lesions. PathoGen achieved the highest win rate (35.4%) when pathologists ranked generation quality against all baselines. Crucially, augmenting training sets with PathoGen-synthesized lesions improves segmentation Dice scores by up to 0.18 compared to traditional augmentations, with maximum benefit in data-scarce regimes. By simultaneously generating realistic morphology and pixel-level annotations, PathoGen effectively addresses both data scarcity and annotation cost, two critical bottlenecks in computational pathology development. △ Less

Submitted 1 July, 2026; v1 submitted 12 January, 2026; originally announced January 2026.

Comments: 19 pages, 5 figures, 1 Table

CSF: Contrastive Semantic Features for Direct Multilingual Sign Language Generation

Authors: Tran Sy Bao

Abstract: Sign language translation systems typically require English as an intermediary language, creating barriers for non-English speakers in the global deaf community. We present Canonical Semantic Form (CSF), a language-agnostic semantic representation framework that enables direct translation from any source language to sign language without English mediation. CSF decomposes utterances into nine unive… ▽ More Sign language translation systems typically require English as an intermediary language, creating barriers for non-English speakers in the global deaf community. We present Canonical Semantic Form (CSF), a language-agnostic semantic representation framework that enables direct translation from any source language to sign language without English mediation. CSF decomposes utterances into nine universal semantic slots: event, intent, time, condition, agent, object, location, purpose, and modifier. A key contribution is our comprehensive condition taxonomy comprising 35 condition types across eight semantic categories, enabling nuanced representation of conditional expressions common in everyday communication. We train a lightweight transformer-based extractor (0.74 MB) that achieves 99.03% average slot extraction accuracy across four typologically diverse languages: English, Vietnamese, Japanese, and French. The model demonstrates particularly strong performance on condition classification (99.4% accuracy) despite the 35-class complexity. With inference latency of 3.02ms on CPU, our approach enables real-time sign language generation in browser-based applications. We release our code, trained models, and multilingual dataset to support further research in accessible sign language technology. △ Less

Submitted 5 January, 2026; originally announced January 2026.

Comments: 9 pages, 8 tables, code available at https://github.com/transybao1393/csf-sign-language

A gradient descent algorithm for computing circle patterns

Authors: Te Ba, Ze Zhou

Abstract: This paper presents a new algorithm for generating planar circle patterns. The algorithm employs gradient descent and conjugate gradient method to compute circle radii and centers separately. Compared with existing algorithms, the proposed method is more efficient in computing centers of circles and is applicable for realizing circle patterns with possible obtuse overlap angles. This paper presents a new algorithm for generating planar circle patterns. The algorithm employs gradient descent and conjugate gradient method to compute circle radii and centers separately. Compared with existing algorithms, the proposed method is more efficient in computing centers of circles and is applicable for realizing circle patterns with possible obtuse overlap angles. △ Less

Submitted 11 December, 2025; originally announced December 2025.

Comments: 7 pages, 1 figure

MSC Class: 52C26; 68U05; 65D18

ENACT: Evaluating Embodied Cognition with World Modeling of Egocentric Interaction

Authors: Qineng Wang, Wenlong Huang, Yu Zhou, Hang Yin, Tianwei Bao, Jianwen Lyu, Weiyu Liu, Ruohan Zhang, Jiajun Wu, Li Fei-Fei, Manling Li

Abstract: Embodied cognition argues that intelligence arises from sensorimotor interaction rather than passive observation. It raises an intriguing question: do modern vision-language models (VLMs), trained largely in a disembodied manner, exhibit signs of embodied cognition? We introduce ENACT, a benchmark that casts evaluation of embodied cognition as world modeling from egocentric interaction in a visual… ▽ More Embodied cognition argues that intelligence arises from sensorimotor interaction rather than passive observation. It raises an intriguing question: do modern vision-language models (VLMs), trained largely in a disembodied manner, exhibit signs of embodied cognition? We introduce ENACT, a benchmark that casts evaluation of embodied cognition as world modeling from egocentric interaction in a visual question answering (VQA) format. Framed as a partially observable Markov decision process (POMDP) whose actions are scene graph changes, ENACT comprises two complementary sequence reordering tasks: forward world modeling (reorder shuffled observations given actions) and inverse world modeling (reorder shuffled actions given observations). While conceptually simple, solving these tasks implicitly demands capabilities central to embodied cognition-affordance recognition, action-effect reasoning, embodied awareness, and interactive, long-horizon memory from partially observable egocentric input, while avoiding low-level image synthesis that could confound the evaluation. We provide a scalable pipeline that synthesizes QA pairs from robotics simulation (BEHAVIOR) and evaluates models on 8,972 QA pairs spanning long-horizon home-scale activities. Experiments reveal a performance gap between frontier VLMs and humans that widens with interaction horizon. Models consistently perform better on the inverse task than the forward one and exhibit anthropocentric biases, including a preference for right-handed actions and degradation when camera intrinsics or viewpoints deviate from human vision. Website at https://enact-embodied-cognition.github.io/. △ Less

Submitted 25 November, 2025; originally announced November 2025.

Comments: Preprint version

EGMOF: Efficient Generation of Metal-Organic Frameworks Using a Hybrid Diffusion-Transformer Architecture

Authors: Seunghee Han, Yeonghun Kang, Taeun Bae, Junho Kim, Younghun Kim, Varinia Bernales, Alan Aspuru-Guzik, Jihan Kim

Abstract: Designing materials with targeted properties remains challenging due to the vastness of chemical space and the scarcity of property-labeled data. While recent advances in generative models offer a promising way for inverse design, most approaches require large datasets and must be retrained for every new target property. Here, we introduce the EGMOF (Efficient Generation of MOFs), a hybrid diffusi… ▽ More Designing materials with targeted properties remains challenging due to the vastness of chemical space and the scarcity of property-labeled data. While recent advances in generative models offer a promising way for inverse design, most approaches require large datasets and must be retrained for every new target property. Here, we introduce the EGMOF (Efficient Generation of MOFs), a hybrid diffusion-transformer framework that overcomes these limitations through a modular, descriptor-mediated workflow. EGMOF decomposes inverse design into two steps: (1) a one-dimensional diffusion model (Prop2Desc) that maps desired properties to chemically meaningful descriptors followed by (2) a transformer model (Desc2MOF) that generates structures from these descriptors. This modular hybrid design enables minimal retraining and maintains high accuracy even under small-data conditions. On a hydrogen uptake dataset, EGMOF achieved over 94% validity and 91% hit rate, representing significant improvements of up to 39% in validity and 29% in hit rate compared to existing methods, while remaining effective with only 1,000 training samples. Moreover, our model successfully performed conditional generation across 29 diverse property datasets, including CoREMOF, QMOF, and text-mined experimental datasets, whereas previous models have not. This work presents a data-efficient, generalizable approach to the inverse design of diverse MOFs and highlights the potential of modular inverse design workflows for broader materials discovery. △ Less

Submitted 19 April, 2026; v1 submitted 4 November, 2025; originally announced November 2025.

Fluidity Index: Next-Generation Super-intelligence Benchmarks

Authors: Eric Ngoiya, Tianshu Bao

Abstract: This paper introduces the Fluidity Index (FI) to quantify model adaptability in dynamic, scaling environments. The benchmark evaluates response accuracy based on deviations in initial, current, and future environment states, assessing context switching and continuity. We distinguish between closed-ended and open-ended benchmarks, prioritizing closed-loop open-ended real-world benchmarks to test ad… ▽ More This paper introduces the Fluidity Index (FI) to quantify model adaptability in dynamic, scaling environments. The benchmark evaluates response accuracy based on deviations in initial, current, and future environment states, assessing context switching and continuity. We distinguish between closed-ended and open-ended benchmarks, prioritizing closed-loop open-ended real-world benchmarks to test adaptability. The approach measures a model's ability to understand, predict, and adjust to state changes in scaling environments. A truly super-intelligent model should exhibit at least second-order adaptability, enabling self-sustained computation through digital replenishment for optimal fluidity. △ Less

Submitted 23 October, 2025; originally announced October 2025.

Comments: 12

A co-evolving agentic AI system for medical imaging analysis

Authors: Songhao Li, Jonathan Xu, Tiancheng Bao, Yuxuan Liu, Yuchen Liu, Yihang Liu, Lilin Wang, Wenhui Lei, Sheng Wang, Yinuo Xu, Yan Cui, Jialu Yao, Shunsuke Koga, Zhi Huang

Abstract: Agentic AI is rapidly advancing in healthcare and biomedical research. However, in medical image analysis, their performance and adoption remain limited due to the lack of a robust ecosystem, insufficient toolsets, and the absence of real-time interactive expert feedback. Here we present "TissueLab", a co-evolving agentic AI system that allows researchers to ask direct questions, automatically pla… ▽ More Agentic AI is rapidly advancing in healthcare and biomedical research. However, in medical image analysis, their performance and adoption remain limited due to the lack of a robust ecosystem, insufficient toolsets, and the absence of real-time interactive expert feedback. Here we present "TissueLab", a co-evolving agentic AI system that allows researchers to ask direct questions, automatically plan and generate explainable workflows, and conduct real-time analyses where experts can visualize intermediate results and refine them. TissueLab integrates tool factories across pathology, radiology, and spatial omics domains. By standardizing inputs, outputs, and capabilities of diverse tools, the system determines when and how to invoke them to address research and clinical questions. Across diverse tasks with clinically meaningful quantifications that inform staging, prognosis, and treatment planning, TissueLab achieves state-of-the-art performance compared with end-to-end vision-language models (VLMs) and other agentic AI systems such as GPT-5. Moreover, TissueLab continuously learns from clinicians, evolving toward improved classifiers and more effective decision strategies. With active learning, it delivers accurate results in unseen disease contexts within minutes, without requiring massive datasets or prolonged retraining. Released as a sustainable open-source ecosystem, TissueLab aims to accelerate computational research and translational adoption in medical imaging while establishing a foundation for the next generation of medical AI. △ Less

Submitted 24 September, 2025; originally announced September 2025.

Neurodynamics-Driven Coupled Neural P Systems for Multi-Focus Image Fusion

Authors: Bo Li, Yunkuo Lei, Tingting Bao, Hang Yan, Yaxian Wang, Weiping Fu, Lingling Zhang, Jun Liu

Abstract: Multi-focus image fusion (MFIF) is a crucial technique in image processing, with a key challenge being the generation of decision maps with precise boundaries. However, traditional methods based on heuristic rules and deep learning methods with black-box mechanisms are difficult to generate high-quality decision maps. To overcome this challenge, we introduce neurodynamics-driven coupled neural P (… ▽ More Multi-focus image fusion (MFIF) is a crucial technique in image processing, with a key challenge being the generation of decision maps with precise boundaries. However, traditional methods based on heuristic rules and deep learning methods with black-box mechanisms are difficult to generate high-quality decision maps. To overcome this challenge, we introduce neurodynamics-driven coupled neural P (CNP) systems, which are third-generation neural computation models inspired by spiking mechanisms, to enhance the accuracy of decision maps. Specifically, we first conduct an in-depth analysis of the model's neurodynamics to identify the constraints between the network parameters and the input signals. This solid analysis avoids abnormal continuous firing of neurons and ensures the model accurately distinguishes between focused and unfocused regions, generating high-quality decision maps for MFIF. Based on this analysis, we propose a Neurodynamics-Driven CNP Fusion model (ND-CNPFuse) tailored for the challenging MFIF task. Unlike current ideas of decision map generation, ND-CNPFuse distinguishes between focused and unfocused regions by mapping the source image into interpretable spike matrices. By comparing the number of spikes, an accurate decision map can be generated directly without any post-processing. Extensive experimental results show that ND-CNPFuse achieves new state-of-the-art performance on four classical MFIF datasets, including Lytro, MFFW, MFI-WHU, and Real-MFF. The code is available at https://github.com/MorvanLi/ND-CNPFuse. △ Less

Submitted 13 March, 2026; v1 submitted 22 September, 2025; originally announced September 2025.

Comments: Accepted by CVPR2026

xOffense: An Autonomous Multi-Agent Framework for Penetration Testing with Domain-Adapted Large Language Models

Authors: Phung Duc Luong, Le Tran Gia Bao, Nguyen Vu Khai Tam, Dong Huu Nguyen Khoa, Nguyen Huu Quyen, Van-Hau Pham, Phan The Duy

Abstract: This work introduces xOffense, an AI-driven, multi-agent penetration testing framework that shifts the process from labor-intensive, expert-driven manual efforts to fully automated, machine-executable workflows capable of scaling seamlessly with computational infrastructure. At its core, xOffense leverages a fine-tuned, mid-scale open-source LLM (Qwen3-32B) to drive reasoning and decision-making i… ▽ More This work introduces xOffense, an AI-driven, multi-agent penetration testing framework that shifts the process from labor-intensive, expert-driven manual efforts to fully automated, machine-executable workflows capable of scaling seamlessly with computational infrastructure. At its core, xOffense leverages a fine-tuned, mid-scale open-source LLM (Qwen3-32B) to drive reasoning and decision-making in penetration testing. The framework assigns specialized agents to reconnaissance, vulnerability scanning, and exploitation, with an orchestration layer ensuring seamless coordination across phases. Fine-tuning on Chain-of-Thought penetration testing data further enables the model to generate precise tool commands and perform consistent multi-step reasoning. We evaluate xOffense on two rigorous benchmarks: AutoPenBench and AI-Pentest-Benchmark. The results demonstrate that xOffense consistently outperforms contemporary methods, achieving a sub-task completion rate of 79.17%, decisively surpassing leading systems such as VulnBot and PentestGPT. These findings highlight the potential of domain-adapted mid-scale LLMs, when embedded within structured multi-agent orchestration, to deliver superior, cost-efficient, and reproducible solutions for autonomous penetration testing. △ Less

Submitted 27 April, 2026; v1 submitted 16 September, 2025; originally announced September 2025.

Comments: 17 pages, 4 figures

Guiding Noisy Label Conditional Diffusion Models with Score-based Discriminator Correction

Authors: Dat Nguyen Cong, Hieu Tran Bao, Hoang Thanh-Tung

Abstract: Diffusion models have gained prominence as state-of-the-art techniques for synthesizing images and videos, particularly due to their ability to scale effectively with large datasets. Recent studies have uncovered that these extensive datasets often contain mistakes from manual labeling processes. However, the extent to which such errors compromise the generative capabilities and controllability of… ▽ More Diffusion models have gained prominence as state-of-the-art techniques for synthesizing images and videos, particularly due to their ability to scale effectively with large datasets. Recent studies have uncovered that these extensive datasets often contain mistakes from manual labeling processes. However, the extent to which such errors compromise the generative capabilities and controllability of diffusion models is not well studied. This paper introduces Score-based Discriminator Correction (SBDC), a guidance technique for aligning noisy pre-trained conditional diffusion models. The guidance is built on discriminator training using adversarial loss, drawing on prior noise detection techniques to assess the authenticity of each sample. We further show that limiting the usage of our guidance to the early phase of the generation process leads to better performance. Our method is computationally efficient, only marginally increases inference time, and does not require retraining diffusion models. Experiments on different noise settings demonstrate the superiority of our method over previous state-of-the-art methods. △ Less

Submitted 27 August, 2025; originally announced August 2025.

Comments: 21 pages, 16 figures

SurveyGen: Quality-Aware Scientific Survey Generation with Large Language Models

Authors: Tong Bao, Mir Tafseer Nayeem, Davood Rafiei, Chengzhi Zhang

Abstract: Automatic survey generation has emerged as a key task in scientific document processing. While large language models (LLMs) have shown promise in generating survey texts, the lack of standardized evaluation datasets critically hampers rigorous assessment of their performance against human-written surveys. In this work, we present SurveyGen, a large-scale dataset comprising over 4,200 human-written… ▽ More Automatic survey generation has emerged as a key task in scientific document processing. While large language models (LLMs) have shown promise in generating survey texts, the lack of standardized evaluation datasets critically hampers rigorous assessment of their performance against human-written surveys. In this work, we present SurveyGen, a large-scale dataset comprising over 4,200 human-written surveys across diverse scientific domains, along with 242,143 cited references and extensive quality-related metadata for both the surveys and the cited papers. Leveraging this resource, we build QUAL-SG, a novel quality-aware framework for survey generation that enhances the standard Retrieval-Augmented Generation (RAG) pipeline by incorporating quality-aware indicators into literature retrieval to assess and select higher-quality source papers. Using this dataset and framework, we systematically evaluate state-of-the-art LLMs under varying levels of human involvement - from fully automatic generation to human-guided writing. Experimental results and human evaluations show that while semi-automatic pipelines can achieve partially competitive outcomes, fully automatic survey generation still suffers from low citation quality and limited critical analysis. △ Less

Submitted 25 August, 2025; originally announced August 2025.

Journal ref: EMNLP2025

SC4ANM: Identifying Optimal Section Combinations for Automated Novelty Prediction in Academic Papers

Authors: Wenqing Wu, Chengzhi Zhang, Tong Bao, Yi Zhao

Abstract: Novelty is a core component of academic papers, and there are multiple perspectives on the assessment of novelty. Existing methods often focus on word or entity combinations, which provide limited insights. The content related to a paper's novelty is typically distributed across different core sections, e.g., Introduction, Methodology and Results. Therefore, exploring the optimal combination of se… ▽ More Novelty is a core component of academic papers, and there are multiple perspectives on the assessment of novelty. Existing methods often focus on word or entity combinations, which provide limited insights. The content related to a paper's novelty is typically distributed across different core sections, e.g., Introduction, Methodology and Results. Therefore, exploring the optimal combination of sections for evaluating the novelty of a paper is important for advancing automated novelty assessment. In this paper, we utilize different combinations of sections from academic papers as inputs to drive language models to predict novelty scores. We then analyze the results to determine the optimal section combinations for novelty score prediction. We first employ natural language processing techniques to identify the sectional structure of academic papers, categorizing them into introduction, methods, results, and discussion (IMRaD). Subsequently, we used different combinations of these sections (e.g., introduction and methods) as inputs for pretrained language models (PLMs) and large language models (LLMs), employing novelty scores provided by human expert reviewers as ground truth labels to obtain prediction results. The results indicate that using introduction, results and discussion is most appropriate for assessing the novelty of a paper, while the use of the entire text does not yield significant results. Furthermore, based on the results of the PLMs and LLMs, the introduction and results appear to be the most important section for the task of novelty score prediction. The code and dataset for this paper can be accessed at https://github.com/njust-winchy/SC4ANM. △ Less

Submitted 22 May, 2025; originally announced May 2025.

Journal ref: Expert Systems With Applications, 2025

Enhancing Abstractive Summarization of Scientific Papers Using Structure Information

Authors: Tong Bao, Heng Zhang, Chengzhi Zhang

Abstract: Abstractive summarization of scientific papers has always been a research focus, yet existing methods face two main challenges. First, most summarization models rely on Encoder-Decoder architectures that treat papers as sequences of words, thus fail to fully capture the structured information inherent in scientific papers. Second, existing research often use keyword mapping or feature engineering… ▽ More Abstractive summarization of scientific papers has always been a research focus, yet existing methods face two main challenges. First, most summarization models rely on Encoder-Decoder architectures that treat papers as sequences of words, thus fail to fully capture the structured information inherent in scientific papers. Second, existing research often use keyword mapping or feature engineering to identify the structural information, but these methods struggle with the structural flexibility of scientific papers and lack robustness across different disciplines. To address these challenges, we propose a two-stage abstractive summarization framework that leverages automatic recognition of structural functions within scientific papers. In the first stage, we standardize chapter titles from numerous scientific papers and construct a large-scale dataset for structural function recognition. A classifier is then trained to automatically identify the key structural components (e.g., Background, Methods, Results, Discussion), which provides a foundation for generating more balanced summaries. In the second stage, we employ Longformer to capture rich contextual relationships across sections and generating context-aware summaries. Experiments conducted on two domain-specific scientific paper summarization datasets demonstrate that our method outperforms advanced baselines, and generates more comprehensive summaries. The code and dataset can be accessed at https://github.com/tongbao96/code-for-SFR-AS. △ Less

Submitted 20 May, 2025; originally announced May 2025.

Journal ref: Expert Systems with Applications, 2025

Adaptive Inference-Time Scaling via Cyclic Diffusion Search

Authors: Gyubin Lee, Truong Nhat Nguyen Bao, Jaesik Yoon, Dongwoo Lee, Minsu Kim, Yoshua Bengio, Sungjin Ahn

Abstract: Diffusion models have demonstrated strong generative capabilities across domains ranging from image synthesis to complex reasoning tasks. However, most inference-time scaling methods rely on fixed denoising schedules, limiting their ability to allocate computation based on instance difficulty or task-specific demands adaptively. We introduce the challenge of adaptive inference-time scaling-dynamic… ▽ More Diffusion models have demonstrated strong generative capabilities across domains ranging from image synthesis to complex reasoning tasks. However, most inference-time scaling methods rely on fixed denoising schedules, limiting their ability to allocate computation based on instance difficulty or task-specific demands adaptively. We introduce the challenge of adaptive inference-time scaling-dynamically adjusting computational effort during inference-and propose Adaptive Bi-directional Cyclic Diffusion (ABCD), a flexible, search-based inference framework. ABCD refines outputs through bi-directional diffusion cycles while adaptively controlling exploration depth and termination. It comprises three components: Cyclic Diffusion Search, Automatic Exploration-Exploitation Balancing, and Adaptive Thinking Time. Experiments show that ABCD improves performance across diverse tasks while maintaining computational efficiency. △ Less

Submitted 24 October, 2025; v1 submitted 20 May, 2025; originally announced May 2025.

Examining Linguistic Shifts in Academic Writing Before and After the Launch of ChatGPT: A Study on Preprint Papers

Authors: Tong Bao, Yi Zhao, Jin Mao, Chengzhi Zhang

Abstract: Large Language Models (LLMs), such as ChatGPT, have prompted academic concerns about their impact on academic writing. Existing studies have primarily examined LLM usage in academic writing through quantitative approaches, such as word frequency statistics and probability-based analyses. However, few have systematically examined the potential impact of LLMs on the linguistic characteristics of aca… ▽ More Large Language Models (LLMs), such as ChatGPT, have prompted academic concerns about their impact on academic writing. Existing studies have primarily examined LLM usage in academic writing through quantitative approaches, such as word frequency statistics and probability-based analyses. However, few have systematically examined the potential impact of LLMs on the linguistic characteristics of academic writing. To address this gap, we conducted a large-scale analysis across 823,798 abstracts published in last decade from arXiv dataset. Through the linguistic analysis of features such as the frequency of LLM-preferred words, lexical complexity, syntactic complexity, cohesion, readability and sentiment, the results indicate a significant increase in the proportion of LLM-preferred words in abstracts, revealing the widespread influence of LLMs on academic writing. Additionally, we observed an increase in lexical complexity and sentiment in the abstracts, but a decrease in syntactic complexity, suggesting that LLMs introduce more new vocabulary and simplify sentence structure. However, the significant decrease in cohesion and readability indicates that abstracts have fewer connecting words and are becoming more difficult to read. Moreover, our analysis reveals that scholars with weaker English proficiency were more likely to use the LLMs for academic writing, and focused on improving the overall logic and fluency of the abstracts. Finally, at discipline level, we found that scholars in Computer Science showed more pronounced changes in writing style, while the changes in Mathematics were minimal. △ Less

Submitted 17 May, 2025; originally announced May 2025.

MSC Class: 68T50 ACM Class: I.2.7

Journal ref: Scientometrics,2025

Safeguarding AI in Medical Imaging: Post-Hoc Out-of-Distribution Detection with Normalizing Flows

Authors: Dariush Lotfi, Mohammad-Ali Nikouei Mahani, Mohamad Koohi-Moghadam, Kyongtae Ty Bae

Abstract: In AI-driven medical imaging, the failure to detect out-of-distribution (OOD) data poses a severe risk to clinical reliability, potentially leading to critical diagnostic errors. Current OOD detection methods often demand impractical retraining or modifications to pre-trained models, hindering their adoption in regulated clinical environments. To address this challenge, we propose a post-hoc norma… ▽ More In AI-driven medical imaging, the failure to detect out-of-distribution (OOD) data poses a severe risk to clinical reliability, potentially leading to critical diagnostic errors. Current OOD detection methods often demand impractical retraining or modifications to pre-trained models, hindering their adoption in regulated clinical environments. To address this challenge, we propose a post-hoc normalizing flow-based approach that seamlessly integrates with existing pre-trained models without altering their weights. We evaluate the approach on our in-house-curated MedOOD dataset, designed to capture clinically relevant distribution shifts, and on the MedMNIST benchmark. The proposed method achieves an AUROC of 84.61% on MedOOD, outperforming ViM (80.65%) and MDS (80.87%), and reaches 93.8% AUROC on MedMNIST, surpassing ViM (88.08%) and ReAct (87.05%). This combination of strong performance and post-hoc integration capability makes our approach a practical and effective safeguard for clinical imaging workflows. The model and code to build OOD datasets are publicly accessible at https://github.com/dlotfi/MedOODFlow. △ Less

Submitted 17 November, 2025; v1 submitted 17 February, 2025; originally announced February 2025.

Learning to Stop Overthinking at Test Time

Authors: Hieu Tran Bao, Nguyen Cong Dat, Nguyen Duc Anh, Hoang Thanh-Tung

Abstract: Test time scaling is currently one of the most active research areas that shows promise after training time scaling has reached its limits. Deep-thinking (DT) models are a class of recurrent models that can perform easy-to-hard generalization by assigning more compute to harder test samples. However, due to their inability to determine the complexity of a test sample, DT models have to use a large… ▽ More Test time scaling is currently one of the most active research areas that shows promise after training time scaling has reached its limits. Deep-thinking (DT) models are a class of recurrent models that can perform easy-to-hard generalization by assigning more compute to harder test samples. However, due to their inability to determine the complexity of a test sample, DT models have to use a large amount of computation for both easy and hard test samples. Excessive test time computation is wasteful and can cause the ``overthinking'' problem where more test time computation leads to worse results. In this paper, we introduce a test time training method for determining the optimal amount of computation needed for each sample during test time. We also propose Conv-LiGRU, a novel recurrent architecture for efficient and robust visual reasoning. Extensive experiments demonstrate that Conv-LiGRU is more stable than DT, effectively mitigates the ``overthinking'' phenomenon, and achieves superior accuracy. △ Less

Submitted 17 February, 2025; v1 submitted 15 February, 2025; originally announced February 2025.

ZeroBP: Learning Position-Aware Correspondence for Zero-shot 6D Pose Estimation in Bin-Picking

Authors: Jianqiu Chen, Zikun Zhou, Xin Li, Ye Zheng, Tianpeng Bao, Zhenyu He

Abstract: Bin-picking is a practical and challenging robotic manipulation task, where accurate 6D pose estimation plays a pivotal role. The workpieces in bin-picking are typically textureless and randomly stacked in a bin, which poses a significant challenge to 6D pose estimation. Existing solutions are typically learning-based methods, which require object-specific training. Their efficiency of practical d… ▽ More Bin-picking is a practical and challenging robotic manipulation task, where accurate 6D pose estimation plays a pivotal role. The workpieces in bin-picking are typically textureless and randomly stacked in a bin, which poses a significant challenge to 6D pose estimation. Existing solutions are typically learning-based methods, which require object-specific training. Their efficiency of practical deployment for novel workpieces is highly limited by data collection and model retraining. Zero-shot 6D pose estimation is a potential approach to address the issue of deployment efficiency. Nevertheless, existing zero-shot 6D pose estimation methods are designed to leverage feature matching to establish point-to-point correspondences for pose estimation, which is less effective for workpieces with textureless appearances and ambiguous local regions. In this paper, we propose ZeroBP, a zero-shot pose estimation framework designed specifically for the bin-picking task. ZeroBP learns Position-Aware Correspondence (PAC) between the scene instance and its CAD model, leveraging both local features and global positions to resolve the mismatch issue caused by ambiguous regions with similar shapes and appearances. Extensive experiments on the ROBI dataset demonstrate that ZeroBP outperforms state-of-the-art zero-shot pose estimation methods, achieving an improvement of 9.1% in average recall of correct poses. △ Less

Submitted 2 February, 2025; originally announced February 2025.

Comments: ICRA 2025

Vietnamese Legal Information Retrieval in Question-Answering System

Authors: Thiem Nguyen Ba, Vinh Doan The, Tung Pham Quang, Toan Tran Van

Abstract: In the modern era of rapidly increasing data volumes, accurately retrieving and recommending relevant documents has become crucial in enhancing the reliability of Question Answering (QA) systems. Recently, Retrieval Augmented Generation (RAG) has gained significant recognition for enhancing the capabilities of large language models (LLMs) by mitigating hallucination issues in QA systems, which is… ▽ More In the modern era of rapidly increasing data volumes, accurately retrieving and recommending relevant documents has become crucial in enhancing the reliability of Question Answering (QA) systems. Recently, Retrieval Augmented Generation (RAG) has gained significant recognition for enhancing the capabilities of large language models (LLMs) by mitigating hallucination issues in QA systems, which is particularly beneficial in the legal domain. Various methods, such as semantic search using dense vector embeddings or a combination of multiple techniques to improve results before feeding them to LLMs, have been proposed. However, these methods often fall short when applied to the Vietnamese language due to several challenges, namely inefficient Vietnamese data processing leading to excessive token length or overly simplistic ensemble techniques that lead to instability and limited improvement. Moreover, a critical issue often overlooked is the ordering of final relevant documents which are used as reference to ensure the accuracy of the answers provided by LLMs. In this report, we introduce our three main modifications taken to address these challenges. First, we explore various practical approaches to data processing to overcome the limitations of the embedding model. Additionally, we enhance Reciprocal Rank Fusion by normalizing order to combine results from keyword and vector searches effectively. We also meticulously re-rank the source pieces of information used by LLMs with Active Retrieval to improve user experience when refining the information generated. In our opinion, this technique can also be considered as a new re-ranking method that might be used in place of the traditional cross encoder. Finally, we integrate these techniques into a comprehensive QA system, significantly improving its performance and reliability △ Less

Submitted 4 September, 2024; originally announced September 2024.

Comments: 7 pages

AutoPET III Challenge: PET/CT Semantic Segmentation

Authors: Reza Safdari, Mohammad Koohi-Moghaddam, Kyongtae Tyler Bae

Abstract: In this study, we implemented a two-stage deep learning-based approach to segment lesions in PET/CT images for the AutoPET III challenge. The first stage utilized a DynUNet model for coarse segmentation, identifying broad regions of interest. The second stage refined this segmentation using an ensemble of SwinUNETR, SegResNet, and UNet models. Preprocessing involved resampling images to a common r… ▽ More In this study, we implemented a two-stage deep learning-based approach to segment lesions in PET/CT images for the AutoPET III challenge. The first stage utilized a DynUNet model for coarse segmentation, identifying broad regions of interest. The second stage refined this segmentation using an ensemble of SwinUNETR, SegResNet, and UNet models. Preprocessing involved resampling images to a common resolution and normalization, while data augmentation techniques such as affine transformations and intensity adjustments were applied to enhance model generalization. The dataset was split into 80% training and 20% validation, excluding healthy cases. This method leverages multi-stage segmentation and model ensembling to achieve precise lesion segmentation, aiming to improve robustness and overall performance. △ Less

Submitted 19 September, 2024; originally announced September 2024.

ARVO: Atlas of Reproducible Vulnerabilities for Open-Source Software

Authors: Xiang Mei, Jordi Del Castillo, Pulkit Singh Singaria, Haoran Xi, Abdelouahab Benchikh, Tiffany Bao, Ruoyu Wang, Yan Shoshitaishvili, Adam Doupé, Hammond Pearce, Brendan Dolan-Gavitt

Abstract: Achieving reproducibility, quantity, and diversity in vulnerability datasets has long been viewed as an inherent three-way trade-off, where improving one dimension often comes at the cost of the others. In practice, reproducibility has been the dimension most often neglected. This has limited what can be automatically extracted from historical bug datasets, and has reduced their utility for downst… ▽ More Achieving reproducibility, quantity, and diversity in vulnerability datasets has long been viewed as an inherent three-way trade-off, where improving one dimension often comes at the cost of the others. In practice, reproducibility has been the dimension most often neglected. This has limited what can be automatically extracted from historical bug datasets, and has reduced their utility for downstream security research. In this work, we propose a method to produce a new security dataset which ensures reproducibility for diverse vulnerabilities at scale by identifying the key obstacles to large-scale bug reproduction and addressing them with general solutions. Using this method, we introduce full reproducibility to the largest open source software vulnerability dataset (OSS-Fuzz) and construct the ARVO dataset (an Atlas of Reproducible Vulnerabilities in Open-source software). ARVO is a large-scale dataset consisting of over 6,100 real-world vulnerabilities across 311 projects. Focusing on reproducibility, ARVO differs from existing datasets by providing each vulnerability in a form that can be consistently rebuilt, triggered, and analyzed across versions. Reproducibility also enables automatic identification of the corresponding patch for each vulnerability and supports direct interaction with vulnerabilities after code changes, capabilities that existing large-scale datasets do not provide. In our evaluation, ARVO successfully reproduces 81% of vulnerabilities and achieves 89.4% accuracy on the located patches. We also discuss ARVO's influence on both upstream practices and downstream security research. △ Less

Submitted 18 June, 2026; v1 submitted 4 August, 2024; originally announced August 2024.

Comments: Accepted at IEEE European Symposium on Security and Privacy (EuroS&P) 2026

Investigating shocking events in the Ethereum stablecoin ecosystem through temporal multilayer graph structure

Authors: Cheick Tidiane Ba, Richard G. Clegg, Ben A. Steer, Matteo Zignani

Abstract: In the dynamic landscape of the Web, we are witnessing the emergence of the Web3 paradigm, which dictates that platforms should rely on blockchain technology and cryptocurrencies to sustain themselves and their profitability. Cryptocurrencies are characterised by high market volatility and susceptibility to substantial crashes, issues that require temporal analysis methodologies able to tackle the… ▽ More In the dynamic landscape of the Web, we are witnessing the emergence of the Web3 paradigm, which dictates that platforms should rely on blockchain technology and cryptocurrencies to sustain themselves and their profitability. Cryptocurrencies are characterised by high market volatility and susceptibility to substantial crashes, issues that require temporal analysis methodologies able to tackle the high temporal resolution, heterogeneity and scale of blockchain data. While existing research attempts to analyse crash events, fundamental questions persist regarding the optimal time scale for analysis, differentiation between long-term and short-term trends, and the identification and characterisation of shock events within these decentralised systems. This paper addresses these issues by examining cryptocurrencies traded on the Ethereum blockchain, with a spotlight on the crash of the stablecoin TerraUSD and the currency LUNA designed to stabilise it. Utilising complex network analysis and a multi-layer temporal graph allows the study of the correlations between the layers representing the currencies and system evolution across diverse time scales. The investigation sheds light on the strong interconnections among stablecoins pre-crash and the significant post-crash transformations. We identify anomalous signals before, during, and after the collapse, emphasising their impact on graph structure metrics and user movement across layers. This paper pioneers temporal, cross-chain graph analysis to explore a cryptocurrency collapse. It emphasises the importance of temporal analysis for studies on web-derived data and how graph-based analysis can enhance traditional econometric results. Overall, this research carries implications beyond its field, for example for regulatory agencies aiming to safeguard users from shocks and monitor investment risks for citizens and clients. △ Less

Submitted 19 March, 2025; v1 submitted 15 July, 2024; originally announced July 2024.

Comments: To appear Transactions on Web

Journal ref: ACM Transactions on Web 2025

Take a Step Further: Understanding Page Spray in Linux Kernel Exploitation

Authors: Ziyi Guo, Dang K Le, Zhenpeng Lin, Kyle Zeng, Ruoyu Wang, Tiffany Bao, Yan Shoshitaishvili, Adam Doupé, Xinyu Xing

Abstract: Recently, a novel method known as Page Spray emerges, focusing on page-level exploitation for kernel vulnerabilities. Despite the advantages it offers in terms of exploitability, stability, and compatibility, comprehensive research on Page Spray remains scarce. Questions regarding its root causes, exploitation model, comparative benefits over other exploitation techniques, and possible mitigation… ▽ More Recently, a novel method known as Page Spray emerges, focusing on page-level exploitation for kernel vulnerabilities. Despite the advantages it offers in terms of exploitability, stability, and compatibility, comprehensive research on Page Spray remains scarce. Questions regarding its root causes, exploitation model, comparative benefits over other exploitation techniques, and possible mitigation strategies have largely remained unanswered. In this paper, we conduct a systematic investigation into Page Spray, providing an in-depth understanding of this exploitation technique. We introduce a comprehensive exploit model termed the \sys model, elucidating its fundamental principles. Additionally, we conduct a thorough analysis of the root causes underlying Page Spray occurrences within the Linux Kernel. We design an analyzer based on the Page Spray analysis model to identify Page Spray callsites. Subsequently, we evaluate the stability, exploitability, and compatibility of Page Spray through meticulously designed experiments. Finally, we propose mitigation principles for addressing Page Spray and introduce our own lightweight mitigation approach. This research aims to assist security researchers and developers in gaining insights into Page Spray, ultimately enhancing our collective understanding of this emerging exploitation technique and making improvements to the community. △ Less

Submitted 8 November, 2024; v1 submitted 3 June, 2024; originally announced June 2024.

Comments: Published on 33rd USENIX Security Symposium (USENIX Security 24), see https://www.usenix.org/conference/usenixsecurity24/presentation/guo-ziyi

Graph Out-of-Distribution Generalization via Causal Intervention

Authors: Qitian Wu, Fan Nie, Chenxiao Yang, Tianyi Bao, Junchi Yan

Abstract: Out-of-distribution (OOD) generalization has gained increasing attentions for learning on graphs, as graph neural networks (GNNs) often exhibit performance degradation with distribution shifts. The challenge is that distribution shifts on graphs involve intricate interconnections between nodes, and the environment labels are often absent in data. In this paper, we adopt a bottom-up data-generative… ▽ More Out-of-distribution (OOD) generalization has gained increasing attentions for learning on graphs, as graph neural networks (GNNs) often exhibit performance degradation with distribution shifts. The challenge is that distribution shifts on graphs involve intricate interconnections between nodes, and the environment labels are often absent in data. In this paper, we adopt a bottom-up data-generative perspective and reveal a key observation through causal analysis: the crux of GNNs' failure in OOD generalization lies in the latent confounding bias from the environment. The latter misguides the model to leverage environment-sensitive correlations between ego-graph features and target nodes' labels, resulting in undesirable generalization on new unseen nodes. Built upon this analysis, we introduce a conceptually simple yet principled approach for training robust GNNs under node-level distribution shifts, without prior knowledge of environment labels. Our method resorts to a new learning objective derived from causal inference that coordinates an environment estimator and a mixture-of-expert GNN predictor. The new approach can counteract the confounding bias in training data and facilitate learning generalizable predictive relations. Extensive experiment demonstrates that our model can effectively enhance generalization with various types of distribution shifts and yield up to 27.4\% accuracy improvement over state-of-the-arts on graph OOD generalization benchmarks. Source codes are available at https://github.com/fannie1208/CaNet. △ Less

Submitted 16 August, 2024; v1 submitted 18 February, 2024; originally announced February 2024.

Comments: Accepted by the research paper track of The Web Conference (WWW) 2024. The codes are available at https://github.com/fannie1208/CaNet

Insights and caveats from mining local and global temporal motifs in cryptocurrency transaction networks

Authors: Naomi A. Arnold, Peijie Zhong, Cheick Tidiane Ba, Ben Steer, Raul Mondragon, Felix Cuadrado, Renaud Lambiotte, Richard G. Clegg

Abstract: Distributed ledger technologies have opened up a wealth of fine-grained transaction data from cryptocurrencies like Bitcoin and Ethereum. This allows research into problems like anomaly detection, anti-money laundering, pattern mining and activity clustering (where data from traditional currencies is rarely available). The formalism of temporal networks offers a natural way of representing this da… ▽ More Distributed ledger technologies have opened up a wealth of fine-grained transaction data from cryptocurrencies like Bitcoin and Ethereum. This allows research into problems like anomaly detection, anti-money laundering, pattern mining and activity clustering (where data from traditional currencies is rarely available). The formalism of temporal networks offers a natural way of representing this data and offers access to a wealth of metrics and models. However, the large scale of the data presents a challenge using standard graph analysis techniques. We use temporal motifs to analyse two Bitcoin datasets and one NFT dataset, using sequences of three transactions and up to three users. We show that the commonly used technique of simply counting temporal motifs over all users and all time can give misleading conclusions. Here we also study the motifs contributed by each user and discover that the motif distribution is heavy-tailed and that the key players have diverse motif signatures. We study the motifs that occur in different time periods and find events and anomalous activity that cannot be seen just by a count on the whole dataset. Studying motif completion time reveals dynamics driven by human behaviour as well as algorithmic behaviour. △ Less

Submitted 4 October, 2024; v1 submitted 14 February, 2024; originally announced February 2024.

Exploring the Limits of ChatGPT in Software Security Applications

Authors: Fangzhou Wu, Qingzhao Zhang, Ati Priya Bajaj, Tiffany Bao, Ning Zhang, Ruoyu "Fish" Wang, Chaowei Xiao

Abstract: Large language models (LLMs) have undergone rapid evolution and achieved remarkable results in recent times. OpenAI's ChatGPT, backed by GPT-3.5 or GPT-4, has gained instant popularity due to its strong capability across a wide range of tasks, including natural language tasks, coding, mathematics, and engaging conversations. However, the impacts and limits of such LLMs in system security domain ar… ▽ More Large language models (LLMs) have undergone rapid evolution and achieved remarkable results in recent times. OpenAI's ChatGPT, backed by GPT-3.5 or GPT-4, has gained instant popularity due to its strong capability across a wide range of tasks, including natural language tasks, coding, mathematics, and engaging conversations. However, the impacts and limits of such LLMs in system security domain are less explored. In this paper, we delve into the limits of LLMs (i.e., ChatGPT) in seven software security applications including vulnerability detection/repair, debugging, debloating, decompilation, patching, root cause analysis, symbolic execution, and fuzzing. Our exploration reveals that ChatGPT not only excels at generating code, which is the conventional application of language models, but also demonstrates strong capability in understanding user-provided commands in natural languages, reasoning about control and data flows within programs, generating complex data structures, and even decompiling assembly code. Notably, GPT-4 showcases significant improvements over GPT-3.5 in most security tasks. Also, certain limitations of ChatGPT in security-related tasks are identified, such as its constrained ability to process long code contexts. △ Less

Submitted 7 December, 2023; originally announced December 2023.

STF: Spatial Temporal Fusion for Trajectory Prediction

Authors: Pengqian Han, Jiamou Liu, Tianzhe Bao, Yifei Wang

Abstract: Trajectory prediction is a challenging task that aims to predict the future trajectory of vehicles or pedestrians over a short time horizon based on their historical positions. The main reason is that the trajectory is a kind of complex data, including spatial and temporal information, which is crucial for accurate prediction. Intuitively, the more information the model can capture, the more preci… ▽ More Trajectory prediction is a challenging task that aims to predict the future trajectory of vehicles or pedestrians over a short time horizon based on their historical positions. The main reason is that the trajectory is a kind of complex data, including spatial and temporal information, which is crucial for accurate prediction. Intuitively, the more information the model can capture, the more precise the future trajectory can be predicted. However, previous works based on deep learning methods processed spatial and temporal information separately, leading to inadequate spatial information capture, which means they failed to capture the complete spatial information. Therefore, it is of significance to capture information more fully and effectively on vehicle interactions. In this study, we introduced an integrated 3D graph that incorporates both spatial and temporal edges. Based on this, we proposed the integrated 3D graph, which considers the cross-time interaction information. In specific, we design a Spatial-Temporal Fusion (STF) model including Multi-layer perceptions (MLP) and Graph Attention (GAT) to capture the spatial and temporal information historical trajectories simultaneously on the 3D graph. Our experiment on the ApolloScape Trajectory Datasets shows that the proposed STF outperforms several baseline methods, especially on the long-time-horizon trajectory prediction. △ Less

Submitted 16 July, 2025; v1 submitted 29 November, 2023; originally announced November 2023.

Comments: 6 pages, 6 figures

TPTU-v2: Boosting Task Planning and Tool Usage of Large Language Model-based Agents in Real-world Systems

Authors: Yilun Kong, Jingqing Ruan, Yihong Chen, Bin Zhang, Tianpeng Bao, Shiwei Shi, Guoqing Du, Xiaoru Hu, Hangyu Mao, Ziyue Li, Xingyu Zeng, Rui Zhao

Abstract: Large Language Models (LLMs) have demonstrated proficiency in addressing tasks that necessitate a combination of task planning and the usage of external tools that require a blend of task planning and the utilization of external tools, such as APIs. However, real-world complex systems present three prevalent challenges concerning task planning and tool usage: (1) The real system usually has a vast… ▽ More Large Language Models (LLMs) have demonstrated proficiency in addressing tasks that necessitate a combination of task planning and the usage of external tools that require a blend of task planning and the utilization of external tools, such as APIs. However, real-world complex systems present three prevalent challenges concerning task planning and tool usage: (1) The real system usually has a vast array of APIs, so it is impossible to feed the descriptions of all APIs to the prompt of LLMs as the token length is limited; (2) the real system is designed for handling complex tasks, and the base LLMs can hardly plan a correct sub-task order and API-calling order for such tasks; (3) Similar semantics and functionalities among APIs in real systems create challenges for both LLMs and even humans in distinguishing between them. In response, this paper introduces a comprehensive framework aimed at enhancing the Task Planning and Tool Usage (TPTU) abilities of LLM-based agents operating within real-world systems. Our framework comprises three key components designed to address these challenges: (1) the API Retriever selects the most pertinent APIs for the user task among the extensive array available; (2) LLM Finetuner tunes a base LLM so that the finetuned LLM can be more capable for task planning and API calling; (3) the Demo Selector adaptively retrieves different demonstrations related to hard-to-distinguish APIs, which is further used for in-context learning to boost the final performance. We validate our methods using a real-world commercial system as well as an open-sourced academic dataset, and the outcomes clearly showcase the efficacy of each individual component as well as the integrated framework. △ Less

Submitted 19 November, 2023; originally announced November 2023.

TPTU: Large Language Model-based AI Agents for Task Planning and Tool Usage

Authors: Jingqing Ruan, Yihong Chen, Bin Zhang, Zhiwei Xu, Tianpeng Bao, Guoqing Du, Shiwei Shi, Hangyu Mao, Ziyue Li, Xingyu Zeng, Rui Zhao

Abstract: With recent advancements in natural language processing, Large Language Models (LLMs) have emerged as powerful tools for various real-world applications. Despite their prowess, the intrinsic generative abilities of LLMs may prove insufficient for handling complex tasks which necessitate a combination of task planning and the usage of external tools. In this paper, we first propose a structured fra… ▽ More With recent advancements in natural language processing, Large Language Models (LLMs) have emerged as powerful tools for various real-world applications. Despite their prowess, the intrinsic generative abilities of LLMs may prove insufficient for handling complex tasks which necessitate a combination of task planning and the usage of external tools. In this paper, we first propose a structured framework tailored for LLM-based AI Agents and discuss the crucial capabilities necessary for tackling intricate problems. Within this framework, we design two distinct types of agents (i.e., one-step agent and sequential agent) to execute the inference process. Subsequently, we instantiate the framework using various LLMs and evaluate their Task Planning and Tool Usage (TPTU) abilities on typical tasks. By highlighting key findings and challenges, our goal is to provide a helpful resource for researchers and practitioners to leverage the power of LLMs in their AI applications. Our study emphasizes the substantial potential of these models, while also identifying areas that need more investigation and improvement. △ Less

Submitted 29 December, 2025; v1 submitted 7 August, 2023; originally announced August 2023.

Comments: Accepted in NeurIPS-2023 Workshop on Foundation Models for Decision Making

Raphtory: The temporal graph engine for Rust and Python

Authors: Ben Steer, Naomi Arnold, Cheick Tidiane Ba, Renaud Lambiotte, Haaroon Yousaf, Lucas Jeub, Fabian Murariu, Shivam Kapoor, Pedro Rico, Rachel Chan, Louis Chan, James Alford, Richard G. Clegg, Felix Cuadrado, Matthew Russell Barnes, Peijie Zhong, John N. Pougué Biyong, Alhamza Alnaimi

Abstract: Raphtory is a platform for building and analysing temporal networks. The library includes methods for creating networks from a variety of data sources; algorithms to explore their structure and evolution; and an extensible GraphQL server for deployment of applications built on top. Raphtory's core engine is built in Rust, for efficiency, with Python interfaces, for ease of use. Raphtory is develop… ▽ More Raphtory is a platform for building and analysing temporal networks. The library includes methods for creating networks from a variety of data sources; algorithms to explore their structure and evolution; and an extensible GraphQL server for deployment of applications built on top. Raphtory's core engine is built in Rust, for efficiency, with Python interfaces, for ease of use. Raphtory is developed by network scientists, with a background in Physics, Applied Mathematics, Engineering and Computer Science, for use across academia and industry. △ Less

Submitted 3 January, 2024; v1 submitted 28 June, 2023; originally announced June 2023.

Balancing Logit Variation for Long-tailed Semantic Segmentation

Authors: Yuchao Wang, Jingjing Fei, Haochen Wang, Wei Li, Tianpeng Bao, Liwei Wu, Rui Zhao, Yujun Shen

Abstract: Semantic segmentation usually suffers from a long-tail data distribution. Due to the imbalanced number of samples across categories, the features of those tail classes may get squeezed into a narrow area in the feature space. Towards a balanced feature distribution, we introduce category-wise variation into the network predictions in the training phase such that an instance is no longer projected… ▽ More Semantic segmentation usually suffers from a long-tail data distribution. Due to the imbalanced number of samples across categories, the features of those tail classes may get squeezed into a narrow area in the feature space. Towards a balanced feature distribution, we introduce category-wise variation into the network predictions in the training phase such that an instance is no longer projected to a feature point, but a small region instead. Such a perturbation is highly dependent on the category scale, which appears as assigning smaller variation to head classes and larger variation to tail classes. In this way, we manage to close the gap between the feature areas of different categories, resulting in a more balanced representation. It is noteworthy that the introduced variation is discarded at the inference stage to facilitate a confident prediction. Although with an embarrassingly simple implementation, our method manifests itself in strong generalizability to various datasets and task settings. Extensive experiments suggest that our plug-in design lends itself well to a range of state-of-the-art approaches and boosts the performance on top of them. △ Less

Submitted 3 June, 2023; originally announced June 2023.

ZeroPose: CAD-Prompted Zero-shot Object 6D Pose Estimation in Cluttered Scenes

Authors: Jianqiu Chen, Zikun Zhou, Mingshan Sun, Tianpeng Bao, Rui Zhao, Liwei Wu, Zhenyu He

Abstract: Many robotics and industry applications have a high demand for the capability to estimate the 6D pose of novel objects from the cluttered scene. However, existing classic pose estimation methods are object-specific, which can only handle the specific objects seen during training. When applied to a novel object, these methods necessitate a cumbersome onboarding process, which involves extensive dat… ▽ More Many robotics and industry applications have a high demand for the capability to estimate the 6D pose of novel objects from the cluttered scene. However, existing classic pose estimation methods are object-specific, which can only handle the specific objects seen during training. When applied to a novel object, these methods necessitate a cumbersome onboarding process, which involves extensive dataset preparation and model retraining. The extensive duration and resource consumption of onboarding limit their practicality in real-world applications. In this paper, we introduce ZeroPose, a novel zero-shot framework that performs pose estimation following a Discovery-Orientation-Registration (DOR) inference pipeline. This framework generalizes to novel objects without requiring model retraining. Given the CAD model of a novel object, ZeroPose enables in seconds onboarding time to extract visual and geometric embeddings from the CAD model as a prompt. With the prompting of the above embeddings, DOR can discover all related instances and estimate their 6D poses without additional human interaction or presupposing scene conditions. Compared with existing zero-shot methods solved by the render-and-compare paradigm, the DOR pipeline formulates the object pose estimation into a feature-matching problem, which avoids time-consuming online rendering and improves efficiency. Experimental results on the seven datasets show that ZeroPose as a zero-shot method achieves comparable performance with object-specific training methods and outperforms the state-of-the-art zero-shot method with 50x inference speed improvement. △ Less

Submitted 29 September, 2024; v1 submitted 29 May, 2023; originally announced May 2023.

Low Complexity Detection of Spatial Modulation Aided OTFS in Doubly-Selective Channels

Authors: Zeping Sui, Hongming Zhang, Yu Xin, Tong Bao, Lie-Liang Yang, Lajos Hanzo

Abstract: A spatial modulation-aided orthogonal time frequency space (SM-OTFS) scheme is proposed for high-Doppler scenarios, which relies on a low-complexity distance-based detection algorithm. We first derive the delay-Doppler (DD) domain input-output relationship of our SM-OTFS system by exploiting an SM mapper, followed by characterizing the doubly-selective channels considered. Then we propose a distan… ▽ More A spatial modulation-aided orthogonal time frequency space (SM-OTFS) scheme is proposed for high-Doppler scenarios, which relies on a low-complexity distance-based detection algorithm. We first derive the delay-Doppler (DD) domain input-output relationship of our SM-OTFS system by exploiting an SM mapper, followed by characterizing the doubly-selective channels considered. Then we propose a distance-based ordering subspace check detector (DOSCD) exploiting the \emph{a priori} information of the transmit symbol vector. Moreover, we derive the discrete-input continuous-output memoryless channel (DCMC) capacity of the system. Finally, our simulation results demonstrate that the proposed SM-OTFS system outperforms the conventional single-input-multiple-output (SIMO)-OTFS system, and that the DOSCD conceived is capable of striking an attractive bit error ratio (BER) vs. complexity trade-off. △ Less

Submitted 17 May, 2023; originally announced May 2023.

Reconstructing Turbulent Flows Using Physics-Aware Spatio-Temporal Dynamics and Test-Time Refinement

Authors: Shengyu Chen, Tianshu Bao, Peyman Givi, Can Zheng, Xiaowei Jia

Abstract: Simulating turbulence is critical for many societally important applications in aerospace engineering, environmental science, the energy industry, and biomedicine. Large eddy simulation (LES) has been widely used as an alternative to direct numerical simulation (DNS) for simulating turbulent flows due to its reduced computational cost. However, LES is unable to capture all of the scales of turbule… ▽ More Simulating turbulence is critical for many societally important applications in aerospace engineering, environmental science, the energy industry, and biomedicine. Large eddy simulation (LES) has been widely used as an alternative to direct numerical simulation (DNS) for simulating turbulent flows due to its reduced computational cost. However, LES is unable to capture all of the scales of turbulent transport accurately. Reconstructing DNS from low-resolution LES is critical for many scientific and engineering disciplines, but it poses many challenges to existing super-resolution methods due to the spatio-temporal complexity of turbulent flows. In this work, we propose a new physics-guided neural network for reconstructing the sequential DNS from low-resolution LES data. The proposed method leverages the partial differential equation that underlies the flow dynamics in the design of spatio-temporal model architecture. A degradation-based refinement method is also developed to enforce physical constraints and further reduce the accumulated reconstruction errors over long periods. The results on two different types of turbulent flow data confirm the superiority of the proposed method in reconstructing the high-resolution DNS data and preserving the physical characteristics of flow transport. △ Less

Submitted 12 December, 2023; v1 submitted 24 April, 2023; originally announced April 2023.

Comments: 19 pages