๐ Original Info Title: No Labels, No Problem: Training Visual Reasoners with Multimodal Verifiers ArXiv ID: 2512.08889 Date: 2025-12-09 Authors: Damiano Marsili, Georgia Gkioxari ๐ Abstract Visual reasoning is challenging, requiring both precise โฆ
๐ Original Info Title: Prompt-Based Continual Compositional Zero-Shot Learning ArXiv ID: 2512.09172 Date: 2025-12-09 Authors: Sauda Maryam, Sara Nadeem, Faisal Qureshi, Mohsen Ali ๐ Abstract We tackle continual adaptation of vision-language models to โฆ
๐ Original Info Title: Protein Secondary Structure Prediction Using Transformers ArXiv ID: 2512.08613 Date: 2025-12-09 Authors: Manzi Kevin Maxime ๐ Abstract Predicting protein secondary structures such as alpha helices, beta sheets, and coils from โฆ
๐ Original Info Title: Quantum Decision Transformers (QDT): Synergistic Entanglement and Interference for Offline Reinforcement Learning ArXiv ID: 2512.14726 Date: 2025-12-09 Authors: Abraham Itzhak Weinberg ๐ Abstract Offline reinforcement learning โฆ
๐ Original Info Title: Residual Primitive Fitting of 3D Shapes with SuperFrusta ArXiv ID: 2512.09201 Date: 2025-12-09 Authors: Aditya Ganeshan, Matheus Gadelha, Thibault Groueix, Zhiqin Chen, Siddhartha Chaudhuri, Vladimir Kim, Wang Yifan, Daniel โฆ
๐ Original Info Title: Revisiting the Scaling Properties of Downstream Metrics in Large Language Model Training ArXiv ID: 2512.08894 Date: 2025-12-09 Authors: Jakub Krajewski, Amitis Shidani, Dan Busbridge, Sam Wiseman, Jason Ramapuram ๐ Abstract โฆ
๐ Original Info Title: Semantic Trajectory Generation for Goal-Oriented Spacecraft Rendezvous ArXiv ID: 2512.09111 Date: 2025-12-09 Authors: Yuji Takubo, Arpit Dwivedi, Sukeerth Ramkumar, Luis A. Pabon, Daniele Gammelli, Marco Pavone, Simone DAmico ๐ โฆ
๐ Original Info Title: Siamese-Driven Optimization for Low-Resolution Image Latent Embedding in Image Captioning ArXiv ID: 2512.08873 Date: 2025-12-09 Authors: Jing Jie Tan, Anissa Mokraoui, Ban-Hoe Kwan, Danny Wee-Kiat Ng, Yan-Chai Hum ๐ Abstract โฆ
๐ Original Info Title: SoMe: A Realistic Benchmark for LLM-based Social Media Agents ArXiv ID: 2512.14720 Date: 2025-12-09 Authors: Dizhan Xue, Jing Cui, Shengsheng Qian, Chuanrui Hu, Changsheng Xu ๐ Abstract Intelligent agents powered by large โฆ
๐ Original Info Title: Toward Faithful Retrieval-Augmented Generation with Sparse Autoencoders ArXiv ID: 2512.08892 Date: 2025-12-09 Authors: Guangzhi Xiong, Zhenghao He, Bohan Liu, Sanchit Sinha, Aidong Zhang ๐ Abstract Retrieval-Augmented โฆ
๐ Original Info Title: Towards Lossless Ultimate Vision Token Compression for VLMs ArXiv ID: 2512.09010 Date: 2025-12-09 Authors: Dehua Zheng, Mouxiao Huang, Borui Jiang, Hailin Hu, Xinghao Chen ๐ Abstract Visual language models encounter challenges โฆ
๐ Original Info Title: WOLF: Werewolf-based Observations for LLM Deception and Falsehoods ArXiv ID: 2512.09187 Date: 2025-12-09 Authors: Mrinal Agarwal, Saad Rana, Theo Sundoro, Hermela Berhe, Spencer Kim, Vasu Sharma, Sean OBrien, Kevin Zhu ๐ โฆ
๐ Original Info Title: WonderZoom: Multi-Scale 3D World Generation ArXiv ID: 2512.09164 Date: 2025-12-09 Authors: Jin Cao, Hong-Xing Yu, Jiajun Wu ๐ Abstract Prompt: "The SUV has a shiny chrome bumper." : camera movement : camera zoom-in Figure 1. โฆ
๐ Original Info Title: Attention as Binding: A Vector-Symbolic Perspective on Transformer Reasoning ArXiv ID: 2512.14709 Date: 2025-12-08 Authors: Sahil Rajesh Dhayalkar ๐ Abstract Transformer-based language models display impressive reasoning-like โฆ
๐ Original Info Title: CFD-copilot: leveraging domain-adapted large language model and model context protocol to enhance simulation automation ArXiv ID: 2512.07917 Date: 2025-12-08 Authors: Zhehao Dong, Shanghai Du, Zhen Lu, Yue Yang ๐ Abstract โฆ
๐ Original Info Title: Demo: Generative AI helps Radiotherapy Planning with User Preference ArXiv ID: 2512.08996 Date: 2025-12-08 Authors: Riqiang Gao, Simon Arberet, Martin Kraus, Han Liu, Wilko FAR Verbakel, Dorin Comaniciu, Florin-Cristian Ghesu, โฆ
๐ Original Info Title: Guiding What Not to Generate: Automated Negative Prompting for Text-Image Alignment ArXiv ID: 2512.07702 Date: 2025-12-08 Authors: Sangha Park, Eunji Kim, Yeongtak Oh, Jooyoung Choi, Sungroh Yoon ๐ Abstract Despite substantial โฆ
๐ Original Info Title: Lang3D-XL: Language Embedded 3D Gaussians for Large-scale Scenes ArXiv ID: 2512.07807 Date: 2025-12-08 Authors: Shai Krakovsky, Gal Fiebelman, Sagie Benaim, Hadar Averbuch-Elor ๐ Abstract ๐ Full Content Fig. 1. Language โฆ
๐ Original Info Title: Promoting Fairness in Information Access within Social Networks ArXiv ID: 2512.14711 Date: 2025-12-08 Authors: Changan Liu, Xiaotian Zhou, Ahad N. Zehmakan, Zhongzhi Zhang ๐ Abstract The advent of online social networks has โฆ
๐ Original Info Title: TPA: Next Token Probability Attribution for Detecting Hallucinations in RAG ArXiv ID: 2512.07515 Date: 2025-12-08 Authors: Pengqian Lu, Jie Lu, Anjin Liu, Guangquan Zhang ๐ Abstract Detecting hallucinations in โฆ
๐ Original Info Title: A Comprehensive Study of Supervised Machine Learning Models for Zero-Day Attack Detection: Analyzing Performance on Imbalanced Data ArXiv ID: 2512.07030 Date: 2025-12-07 Authors: Zahra Lotfi, Mostafa Lotfi ๐ Abstract Among the โฆ
๐ Original Info Title: LLM as a Neural Architect: Controlled Generation of Image Captioning Models Under Strict API Contracts ArXiv ID: 2512.14706 Date: 2025-12-07 Authors: Krunal Jesani, Dmitry Ignatov, Radu Timofte ๐ Abstract Neural architecture โฆ
๐ Original Info Title: ProAgent: Harnessing On-Demand Sensory Contexts for Proactive LLM Agent Systems ArXiv ID: 2512.06721 Date: 2025-12-07 Authors: Bufang Yang, Lilin Xu, Liekang Zeng, Yunqi Guo, Siyang Jiang, Wenrui Lu, Kaiwei Liu, Hancheng Xiang, โฆ
๐ Original Info Title: Rethinking Robustness: A New Approach to Evaluating Feature Attribution Methods ArXiv ID: 2512.06665 Date: 2025-12-07 Authors: Panagiota Kiourti, Anu Singh, Preeti Duraipandian, Weichao Zhou, Wenchao Li ๐ Abstract This paper โฆ
๐ Original Info Title: Bayesian Earthquake Location with a Neural Travel-Time Surrogate: Fast, Robust, and Fully Probabilistic Inference in 3-D Media ArXiv ID: 2512.06407 Date: 2025-12-06 Authors: Jinqing Sun, Ziye Yu, Zemin Liu, Lu Li, Chunyu Liu, โฆ
๐ Original Info Title: Convergence of Outputs When Two Large Language Models Interact in a Multi-Agentic Setup ArXiv ID: 2512.06256 Date: 2025-12-06 Authors: Aniruddha Maiti, Satya Nimmagadda, Kartha Veerya Jammuladinne, Niladri Sengupta, Ananya Jana โฆ
๐ Original Info Title: Explainable Fundus Image Curation and Lesion Detection in Diabetic Retinopathy ArXiv ID: 2512.08986 Date: 2025-12-06 Authors: Anca Mihai, Adrian Groza ๐ Abstract Diabetic Retinopathy (DR) affects individuals with long-term โฆ
๐ Original Info Title: Metaphor-based Jailbreaking Attacks on Text-to-Image Models ArXiv ID: 2512.10766 Date: 2025-12-06 Authors: Chenyu Zhang, Yiwen Ma, Lanjun Wang, Wenhui Li, Yi Tu, An-An Liu ๐ Abstract Text-to-image (T2I) models commonly โฆ
๐ Original Info Title: RAG-HAR: Retrieval Augmented Generation-based Human Activity Recognition ArXiv ID: 2512.08984 Date: 2025-12-06 Authors: Nirhoshan Sivaroopan, Hansi Karunarathna, Chamara Madarasingha, Anura Jayasumana, Kanchana Thilakarathna ๐ โฆ
๐ Original Info Title: A Comprehensive Framework for Automated Quality Control in the Automotive Industry ArXiv ID: 2512.05579 Date: 2025-12-05 Authors: Panagiota Moraiti, Panagiotis Giannikos, Athanasios Mastrogeorgiou, Panagiotis Mavridis, Linghao โฆ
๐ Original Info Title: A Fast Anti-Jamming Cognitive Radar Deployment Algorithm Based on Reinforcement Learning ArXiv ID: 2512.05753 Date: 2025-12-05 Authors: Wencheng Cai, Xuchao Gao, Congying Han, Mingqiang Li, Tiande Guo ๐ Abstract The fast โฆ
๐ Original Info Title: Bayesian Active Inference for Intelligent UAV Anti-Jamming and Adaptive Trajectory Planning ArXiv ID: 2512.05711 Date: 2025-12-05 Authors: Ali Krayani, Seyedeh Fatemeh Sadati, Lucio Marcenaro, Carlo Regazzoni ๐ Abstract This โฆ
๐ Original Info Title: Big Tech-Funded AI Papers Have Higher Citation Impact, Greater Insularity, and Larger Recency Bias ArXiv ID: 2512.05714 Date: 2025-12-05 Authors: Max Martin Gnewuch, Jan Philip Wahle, Terry Ruas, Bela Gipp ๐ Abstract Over the โฆ
๐ Original Info Title: ChipMind: Retrieval-Augmented Reasoning for Long-Context Circuit Design Specifications ArXiv ID: 2512.05371 Date: 2025-12-05 Authors: Changwen Xing, SamZaak Wong, Xinlai Wan, Yanfeng Lu, Mengli Zhang, Zebin Ma, Lei Qi, โฆ
๐ Original Info Title: Efficient Text Classification with Conformal In-Context Learning ArXiv ID: 2512.05732 Date: 2025-12-05 Authors: Ippokratis Pantelidis, Korbinian Randl, Aron Henriksson ๐ Abstract Large Language Models (LLMs) demonstrate strong โฆ
๐ Original Info Title: Grounded Multilingual Medical Reasoning for Question Answering with Large Language Models ArXiv ID: 2512.05658 Date: 2025-12-05 Authors: Pietro Ferrazzi, Aitor Soroa, Rodrigo Agerri ๐ Abstract Large Language Models (LLMs) with โฆ
๐ Original Info Title: HiMoE-VLA: Hierarchical Mixture-of-Experts for Generalist Vision-Language-Action Policies ArXiv ID: 2512.05693 Date: 2025-12-05 Authors: Zhiying Du, Bei Liu, Yaobo Liang, Yichao Shen, Haidong Cao, Xiangyu Zheng, Zhiyuan Feng, โฆ
๐ Original Info Title: HSCP: A Two-Stage Spectral Clustering Framework for Resource-Constrained UAV Identification ArXiv ID: 2512.08983 Date: 2025-12-05 Authors: Maoyu Wang, Yao Lu, Bo Zhou, Zhuangzhi Chen, Yun Lin, Qi Xuan, Guan Gui ๐ Abstract With โฆ
๐ Original Info Title: Improving Local Fidelity Through Sampling and Modeling Nonlinearity ArXiv ID: 2512.05556 Date: 2025-12-05 Authors: Sanjeev Shrestha, Rahul Dubey, Hui Liu ๐ Abstract With the increasing complexity of black-box machine learning โฆ
๐ Original Info Title: Interaction Tensor SHAP ArXiv ID: 2512.05338 Date: 2025-12-05 Authors: Hiroki Hasegawa, Yukihiko Okada ๐ Abstract This study proposes Interaction Tensor SHAP (IT-SHAP), a tensor-algebraic formulation of the Shapley-Taylor โฆ
๐ Original Info Title: InverseCrafter: Efficient Video ReCapture as a Latent Domain Inverse Problem ArXiv ID: 2512.05672 Date: 2025-12-05 Authors: Yeobin Hong, Suhyeon Lee, Hyungjin Chung, Jong Chul Ye ๐ Abstract Figure 1 . Representative video on โฆ
๐ Original Info Title: KANFormer for Predicting Fill Probabilities via Survival Analysis in Limit Order Books ArXiv ID: 2512.05734 Date: 2025-12-05 Authors: Jinfeng Zhong, Emmanuel Bacry, Agathe Guilloux, Jean-Franรงois Muzy ๐ Abstract This paper โฆ
๐ Original Info Title: Lyrics Matter: Exploiting the Power of Learnt Representations for Music Popularity Prediction ArXiv ID: 2512.05508 Date: 2025-12-05 Authors: Yash Choudhary, Preeti Rao, Pushpak Bhattacharyya ๐ Abstract Accurately predicting โฆ
๐ Original Info Title: Matching Ranks Over Probability Yields Truly Deep Safety Alignment ArXiv ID: 2512.05518 Date: 2025-12-05 Authors: Jason Vega, Gagandeep Singh ๐ Abstract A frustratingly easy technique known as the prefilling attack has been โฆ
๐ Original Info Title: Mitigating Bias with Words: Inducing Demographic Ambiguity in Face Recognition Templates by Text Encoding ArXiv ID: 2512.08981 Date: 2025-12-05 Authors: Tahar Chettaoui, Naser Damer, Fadi Boutros ๐ Abstract Face recognition โฆ
๐ Original Info Title: Mitigating Self-Preference by Authorship Obfuscation ArXiv ID: 2512.05379 Date: 2025-12-05 Authors: Taslim Mahbub, Shi Feng ๐ Abstract Language models (LMs) judges are widely used to evaluate the quality of LM outputs. Despite โฆ
๐ Original Info Title: Natural Language Summarization Enables Multi-Repository Bug Localization by LLMs in Microservice Architectures ArXiv ID: 2512.05908 Date: 2025-12-05 Authors: Amirkia Rafiei Oskooei, S. Selcan Yukcu, Mehmet Cevheri Bozoglan, โฆ
๐ Original Info Title: NEAT: Neighborhood-Guided, Efficient, Autoregressive Set Transformer for 3D Molecular Generation ArXiv ID: 2512.05844 Date: 2025-12-05 Authors: Daniel Rose, Roxane Axel Jacob, Johannes Kirchmair, Thierry Langer ๐ Abstract โฆ
๐ Original Info Title: On measuring grounding and generalizing grounding problems ArXiv ID: 2512.06205 Date: 2025-12-05 Authors: Daniel Quigley, Eric Maynard ๐ Abstract The symbol grounding problem asks how tokens like cat can be about cats, as โฆ
๐ Original Info Title: Optimizing Medical Question-Answering Systems: A Comparative Study of Fine-Tuned and Zero-Shot Large Language Models with RAG Framework ArXiv ID: 2512.05863 Date: 2025-12-05 Authors: Tasnimul Hassan, Md Faisal Karim, Haziq โฆ
Enter keywords to search articles