• 学术搜索
  • 科研智能体
    • Research Labs
    • AI 阅读
    • AI 文库
    • 深度研究
    • 学者亮点
  • 学术资源
    • AI2000
    • 期刊/会议
    • 学者库
    • 学术API
      MCP&Skill
    • 溯源树
    • 数据集
  • 知识沉淀
    • 学术空间
订阅小程序
旧版功能
aminer vip
开通会员低至0.73元/天
一次搞定AI科研
立即登录
  • English
  • 联系方式
    B

    Birla Institute of Technology and Science, Pilani – Goa Campus

    院校
    287论文总数
    4,272引用总数

    论文量&引用量时间轴

    机构学者

    论文(287)

    年份
    起
    –
    止
    排序
    1Structural Controllability of Bilinear Systems on 𝕊𝔼(n)
    A. Sanand Amita Dilip,Chirayu D. Athalye

    Structural controllability challenges arise from imprecise system modeling and system interconnections in large scale systems. In this paper, we study structural control of bilinear systems on the special Euclidean group. We employ graph theoretic methods to analyze the structural controllability problem for driftless bilinear systems and structural accessibility for bilinear systems with drift. This facilitates the identification of a sparsest pattern necessary for achieving structural controllability and discerning redundant connections. To obtain a graph theoretic characterization of structural controllability and accessibility on the special Euclidean group, we introduce a novel idea of solid and broken edges on graphs; subsequently, we use the notion of transitive closure of graphs.

    2026Mathematics of Control, Signals, and Systems(2026)引用:17
    引用
    AI阅读
    加入学术空间
    2A Comprehensive Dataset for Human Vs. AI Generated Image Detection.
    Rajarshi Roy, Ashhar Aziz, Shashwat Bajpai, Nasrin Imanpour, Gurpreet Singh, Shwetangshu Biswas, Kapil Wanaskar,Parth Patwa,Subhankar Ghosh, Shreyas Dixit, Nilesh Ranjan Pal,Vipula Rawte,

    Multimodal generative AI systems like Stable Diffusion, DALL-E, and MidJourney have fundamentally changed how synthetic images are created. These tools drive innovation but also enable the spread of misleading content, false information, and manipulated media. As generated images become harder to distinguish from photographs, detecting them has become an urgent priority. To combat this challenge, we release MS COCOAI, a novel dataset for AI generated image detection consisting of 96000 real and synthetic datapoints, built using the MS COCO dataset. To generate synthetic images, we use five generators: Stable Diffusion 3, Stable Diffusion 2.1, SDXL, DALL-E 3, and MidJourney v6. Based on the dataset, we propose two tasks: (1) classifying images as real or generated, and (2) identifying which model produced a given synthetic image. The dataset is available at https://huggingface.co/datasets/Rajarshi-Roy-research/Defactify_Image_Dataset.

    2026CoRR(2026)引用:5
    引用
    AI阅读
    加入学术空间
    3Weights or Skills? A Survey of Robot-Learning Techniques: from Action-Predicting Weights to Robots That Write Their Own Skills
    Gaytri Jena, Kapil Wanaskar,Vinija Jain,Aman Chadha, Vasu Sharma, Amitava Das

    Robot learning is splitting into two bets: policies that bake competence into frozen weights (vision-language-action, or VLA, models), and agents that write and refine their own executable skills as code. This survey organises the field around that axis of weights versus skills. Its central analytical contribution is a deep-dive that arranges code-as-policy methods by their degree of self-improvement, from zero-shot program synthesis, through closed-loop self-repair and persistent skill memory, to the sparsely populated cell in which execution feedback, skill memory, and evolutionary search combine into one open-ended loop; only a few very recent systems (for example ASPIRE, ENPIRE, and RoboClaw) occupy that cell. We map the complementary "skills" pole, from unsupervised reinforcement-learning skill discovery to large-language-model skill libraries, and show that the word "skill" is used in at least five distinct senses, of which only the code sense self-improves without gradient updates. We then connect the taxonomy to the emerging skill economy: commercial robot-skill marketplaces now distribute one-tap skills across robots but ship only static playback, which surfaces open problems of adaptation, cross-embodiment portability, provenance, safety verification, composition, and standardisation. This is a deliberately focused survey. Rather than cataloguing the field exhaustively, it examines 77 representative systems across six technique families through one taxonomy and a set of contrast tables, and it supplies operational definitions of the self-improvement mechanisms together with a statement of what each family cannot do.

    2026引用:2
    引用
    AI阅读
    加入学术空间
    4FRACTIONAL-ORDER PREY-PREDATOR MODELS WITH PARAMETER ESTIMATION VIA FRACTIONAL PHYSICS-INFORMED NEURAL NETWORKS (FPINNS)
    Vighnesh V. Alavani, P. Danumjaya, Radmanabhan Seshaiyer

    This article examines the fractional prey-predator model through the use of fractional physics-informed neural networks (fPINNs). The methodology focuses on the implementation of fPINN algorithms to approximate solutions to systems governed by fractional-order differential equations. Furthermore, key parameters of the models, based on Holling's-type functional responses I, II, and II, were estimated with fPINNs. A detailed study is conducted on the impact of data noise, various data sets, and if only one population is available (prey), then how to predict the other population (predator). Our computational experiments indicate that JPINNs are extremely effective, both in parameter estimation and in accurately forecasting prey-predator populations.

    2026JOURNAL OF MACHINE LEARNING FOR MODELING AND COMPUTING(2026)引用:2
    引用
    AI阅读
    加入学术空间
    5Stochastic CHAOS: Why Deterministic Inference Kills, and Distributional Variability is the Heartbeat of Artifical Cognition
    Tanmay Joshi, Shourya Aggarwal, Anusa Saha, Aadi Pandey, Shreyash Dhoot, Vighnesh Rai, Raxit Goswami,Aman Chadha,Vinija Jain,Amitava Das

    Deterministic inference is a comforting ideal in classical software: the same program on the same input should always produce the same output. As large language models move into real-world deployment, this ideal has been imported wholesale into inference stacks. Recent work from the Thinking Machines Lab has presented a detailed analysis of nondeterminism in LLM inference, showing how batch-invariant kernels and deterministic attention can enforce bitwise-identical outputs, positioning deterministic inference as a prerequisite for reproducibility and enterprise reliability. In this paper, we take the opposite stance. We argue that, for LLMs, deterministic inference kills. It kills the ability to model uncertainty, suppresses emergent abilities, collapses reasoning into a single brittle path, and weakens safety alignment by hiding tail risks. LLMs implement conditional distributions over outputs, not fixed functions. Collapsing these distributions to a single canonical completion may appear reassuring, but it systematically conceals properties central to artificial cognition. We instead advocate Stochastic CHAOS, treating distributional variability as a signal to be measured and controlled. Empirically, we show that deterministic inference is systematically misleading. Single-sample deterministic evaluation underestimates both capability and fragility, masking failure probability under paraphrases and noise. Phase-like transitions associated with emergent abilities disappear under greedy decoding. Multi-path reasoning degrades when forced onto deterministic backbones, reducing accuracy and diagnostic insight. Finally, deterministic evaluation underestimates safety risk by hiding rare but dangerous behaviors that appear only under multi-sample evaluation.

    2026CoRR(2026)引用:1
    引用
    AI阅读
    加入学术空间
    立即登录,查看全部 287 篇论文

    合作机构(100)

    Bristol Institute for Transfusion Sciences,NHS Blood and Transplant合作论文 11
    Facebook 公司合作论文 9
    苹果公司合作论文 9
    谷歌合作论文 8
    印度理工学院合作论文 8
    GLA University合作论文 6
    亚马逊合作论文 5
    印度理工学院克哈格普尔分校合作论文 4
    Manipal Academy of Higher Education合作论文 3
    印度理工学院信息技术分部合作论文 3

    机构统计