๐ Original Info Title: Counterfactual Self-Questioning for Stable Policy Optimization in Language Models ArXiv ID: 2601.00885 Date: 2025-12-31 Authors: Mandar Parab ๐ Abstract Recent advances in language model self-improvement, including โฆ
๐ Original Info Title: Crafting Adversarial Inputs for Large Vision-Language Models Using Black-Box Optimization ArXiv ID: 2601.01747 Date: 2026-01-05 Authors: Jiwei Guan, Haibo Jin, Haohan Wang ๐ Abstract Recent advancements in Large Vision-Language โฆ
๐ Original Info Title: CubeBench: Diagnosing Interactive, Long-Horizon Spatial Reasoning Under Partial Observations ArXiv ID: 2512.23328 Date: 2025-12-29 Authors: Huan-ang Gao, Zikang Zhang, Tianwei Luo, Kaisen Yang, Xinzhe Juan, Jiahao Qiu, Tianxing โฆ
๐ Original Info Title: Cultural Encoding in Large Language Models: The Existence Gap in AI-Mediated Brand Discovery ArXiv ID: 2601.00869 Date: 2025-12-30 Authors: Huang Junyao, Situ Ruimin, Ye Renqin ๐ Abstract As artificial intelligence systems โฆ
๐ Original Info Title: Data Complexity-aware Deep Model Performance Forecasting ArXiv ID: 2601.01383 Date: 2026-01-04 Authors: Yen-Chia Chen, Hsing-Kuo Pao, Hanjuan Huang ๐ Abstract Deep learning models are widely used across computer vision and โฆ
๐ Original Info Title: DeCode: Decoupling Content and Delivery for Medical QA ArXiv ID: 2601.02123 Date: 2026-01-05 Authors: Po-Jen Ko, Chen-Han Tsai, Yu-Shao Peng ๐ Abstract Large language models (LLMs) exhibit strong medical knowledge and can โฆ
๐ Original Info Title: Decoupling Amplitude and Phase Attention in Frequency Domain for RGB-Event based Visual Object Tracking ArXiv ID: 2601.01022 Date: 2026-01-03 Authors: Shiao Wang, Xiao Wang, Haonan Zhao, Jiarui Xu, Bo Jiang, Lin Zhu, Xin Zhao, โฆ
๐ Original Info Title: Deep Delta Learning ArXiv ID: 2601.00417 Date: 2026-01-01 Authors: Yifan Zhang, Yifeng Liu, Mengdi Wang, Quanquan Gu ๐ Abstract The effectiveness of deep residual networks hinges on the identity shortcut connection. While this โฆ
๐ Original Info Title: Deep Learning for Art Market Valuation ArXiv ID: 2512.23078 Date: 2025-12-28 Authors: Jianping Mei, Michael Moses, Jan Waelty, Yucheng Yang ๐ Abstract We study how deep learning can improve valuation in the art market by โฆ
๐ Original Info Title: Deep Networks Learn Deep Hierarchical Models ArXiv ID: 2601.00455 Date: 2026-01-01 Authors: Amit Daniely ๐ Abstract We consider supervised learning with n labels and show that layerwise SGD on residual networks can efficiently โฆ
๐ Original Info Title: DeepInv: A Novel Self-supervised Learning Approach for Fast and Accurate Diffusion Inversion ArXiv ID: 2601.01487 Date: 2026-01-04 Authors: Ziyue Zhang, Luxi Lin, Xiaolin Hu, Chao Chang, HuaiXi Wang, Yiyi Zhou, Rongrong Ji ๐ โฆ
๐ Original Info Title: Defensive M2S: Training Guardrail Models on Compressed Multi-turn Conversations ArXiv ID: 2601.00454 Date: 2026-01-01 Authors: Hyunjun Kim ๐ Abstract Guardrail models are essential for ensuring the safety of Large Language โฆ
๐ Original Info Title: Dรฉjร Q: Open-Ended Evolution of Diverse, Learnable and Verifiable Problems ArXiv ID: 2601.01931 Date: 2026-01-05 Authors: Willem Rรถpke, Samuel Coward, Andrei Lupu, Thomas Foster, Tim Rocktรคschel, Jakob Foerster ๐ Abstract Recent โฆ
๐ Original Info Title: DermaVQA-DAS: Dermatology Assessment Schema (DAS) & Datasets for Closed-Ended Question Answering & Segmentation in Patient-Generated Dermatology Images ArXiv ID: 2512.24340 Date: 2025-12-30 Authors: Wen-wai Yim, Yujuan โฆ
๐ Original Info Title: Device-Native Autonomous Agents for Privacy-Preserving Negotiations ArXiv ID: 2601.00911 Date: 2026-01-01 Authors: Joyjit Roy, Samaresh Kumar Singh ๐ Abstract Automated negotiations in insurance and businessto-business (B2B) โฆ
๐ Original Info Title: Discovering Multi-Scale Semantic Structure in Text Corpora Using Density-Based Trees and LLM Embeddings ArXiv ID: 2512.23471 Date: 2025-12-29 Authors: Thomas Haschka, Joseph Bakarji ๐ Abstract Recent advances in large language โฆ
๐ Original Info Title: Distilled HuBERT for Mobile Speech Emotion Recognition: A Cross-Corpus Validation Study ArXiv ID: 2512.23435 Date: 2025-12-29 Authors: Saifelden M. Ismail ๐ Abstract Speech Emotion Recognition (SER) has significant potential โฆ
๐ Original Info Title: Divergent-Convergent Thinking in Large Language Models for Creative Problem Generation ArXiv ID: 2512.23601 Date: 2025-12-29 Authors: Manh Hung Nguyen, Adish Singla ๐ Abstract Large language models (LLMs) have significant โฆ
๐ Original Info Title: Do Large Language Models Know What They Are Capable Of? ArXiv ID: 2512.24661 Date: 2025-12-31 Authors: Casey O. Barkan, Sid Black, Oliver Sourbut ๐ Abstract We investigate whether large language models (LLMs) can predict โฆ
๐ Original Info Title: DrivingGen: A Comprehensive Benchmark for Generative Video World Models in Autonomous Driving ArXiv ID: 2601.01528 Date: 2026-01-04 Authors: Yang Zhou, Hao Shao, Letian Wang, Zhuofan Zong, Hongsheng Li, Steven L. Waslander ๐ โฆ
๐ Original Info Title: DynaFix: Iterative Automated Program Repair Driven by Execution-Level Dynamic Information ArXiv ID: 2512.24635 Date: 2025-12-31 Authors: Zhili Huang, Ling Xu, Chao Liu, Weifeng Sun, Xu Zhang, Yan Lei, Meng Yan, Hongyu Zhang ๐ โฆ
๐ Original Info Title: Dynamic Large Concept Models: Latent Reasoning in an Adaptive Semantic Space ArXiv ID: 2512.24617 Date: 2025-12-31 Authors: Xingwei Qu, Shaowen Wang, Zihao Huang, Kai Hua, Fan Yin, Rui-Jie Zhu, Jundong Zhou, Qiyang Min, Zihao โฆ
๐ Original Info Title: EgoGrasp: World-Space Hand-Object Interaction Estimation from Egocentric Videos ArXiv ID: 2601.01050 Date: 2026-01-03 Authors: Hongming Fu, Wenjia Wang, Xiaozhen Qiao, Shuo Yang, Zheng Liu, Bo Zhao ๐ Abstract We propose โฆ
๐ Original Info Title: Emergent Introspective Awareness in Large Language Models ArXiv ID: 2601.01828 Date: 2026-01-05 Authors: Jack Lindsey ๐ Abstract We investigate whether large language models can introspect on their internal states. It is โฆ
๐ Original Info Title: Enabling Physical AI at the Edge: Hardware-Accelerated Recovery of System Dynamics ArXiv ID: 2512.23767 Date: 2025-12-29 Authors: Bin Xu, Ayan Banerjee, Sandeep Gupta ๐ Abstract Physical AI at the edge-enabling autonomous โฆ
๐ Original Info Title: Enhancing Histopathological Image Classification via Integrated HOG and Deep Features with Robust Noise Performance ArXiv ID: 2601.01056 Date: 2026-01-03 Authors: Ifeanyi Ezuma, Ugochukwu Ugwu ๐ Abstract The era of digital โฆ
๐ Original Info Title: Enhancing LLM Planning Capabilities through Intrinsic Self-Critique ArXiv ID: 2512.24103 Date: 2025-12-30 Authors: Bernd Bohnet, Pierre-Alexandre Kamienny, Hanie Sedghi, Dilan Gorur, Pranjal Awasthi, Aaron Parisi, Kevin โฆ
๐ Original Info Title: Enhancing Temporal Awareness in LLMs for Temporal Point Processes ArXiv ID: 2601.00845 Date: 2025-12-29 Authors: Lili Chen, Wensheng Gan, Shuang Liang, Philip S. Yu ๐ Abstract Temporal point processes (TPPs) are crucial for โฆ
๐ Original Info Title: Enriching Historical Records: An OCR and AI-Driven Approach for Database Integration ArXiv ID: 2512.23710 Date: 2025-11-17 Authors: Zahra Abedi, Richard M. K. van Dijk, Gijs Wijnholds, Tessa Verhoef ๐ Abstract This research โฆ
๐ Original Info Title: Entropy-Adaptive Fine-Tuning: Resolving Confident Conflicts to Mitigate Forgetting ArXiv ID: 2601.02151 Date: 2026-01-05 Authors: Muxi Diao, Lele Yang, Wuxuan Gong, Yutong Zhang, Zhonghao Yan, Yufei Han, Kongming Liang, Weiran โฆ
๐ Original Info Title: Entropy-Aware Speculative Decoding Toward Improved LLM Reasoning ArXiv ID: 2512.23765 Date: 2025-12-29 Authors: Tiancheng Su, Meicong Zhang, Guoxiu He ๐ Abstract Speculative decoding (SD) accelerates large language model (LLM) โฆ
๐ Original Info Title: Evaluating Feature Dependent Noise in Preference-based Reinforcement Learning ArXiv ID: 2601.01904 Date: 2026-01-05 Authors: Yuxuan Li, Harshith Reddy Kethireddy, Srijita Das ๐ Abstract Learning from Preferences in โฆ
๐ Original Info Title: Evaluating the Impact of Compression Techniques on the Robustness of CNNs under Natural Corruptions ArXiv ID: 2512.24971 Date: 2025-12-31 Authors: Itallo Patrick Castro Alves Da Silva, Emanuel Adler Medeiros Pereira, Erick de โฆ
๐ Original Info Title: Evolving, Not Training: Zero-Shot Reasoning Segmentation via Evolutionary Prompting ArXiv ID: 2512.24702 Date: 2025-12-31 Authors: Kai Ye, Xiaotong You, Jianghang Lin, Jiayi Ji, Pingyang Dai, Liujuan Cao ๐ Abstract Reasoning โฆ
๐ Original Info Title: Explaining Why Things Go Where They Go: Interpretable Constructs of Human Organizational Preferences ArXiv ID: 2512.24829 Date: 2025-12-31 Authors: Emmanuel Fashae, Michael Burke, Leimin Tian, Lingheng Meng, Pamela โฆ
๐ Original Info Title: Explicit Abstention Knobs for Predictable Reliability in Video Question Answering ArXiv ID: 2601.00138 Date: 2025-12-31 Authors: Jorge Ortiz ๐ Abstract High-stakes deployment of vision-language models (VLMs) requires selective โฆ
๐ Original Info Title: Exploring Approaches for Detecting Memorization of Recommender System Data in Large Language Models ArXiv ID: 2601.02002 Date: 2026-01-05 Authors: Antonio Colacicco, Vito Guida, Dario Di Palma, Fedelucio Narducci, Tommaso Di โฆ
๐ Original Info Title: Exploring Diversity, Novelty, and Popularity Bias in ChatGPTs Recommendations ArXiv ID: 2601.01997 Date: 2026-01-05 Authors: Dario Di Palma, Giovanni Maria Biancofiore, Vito Walter Anelli, Fedelucio Narducci, Tommaso Di Noia ๐ โฆ
๐ Original Info Title: Exploring the Performance of Large Language Models on Subjective Span Identification Tasks ArXiv ID: 2601.00736 Date: 2026-01-02 Authors: Alphaeus Dmonte, Roland Oruche, Tharindu Ranasinghe, Marcos Zampieri, Prasad Calyam ๐ โฆ
๐ Original Info Title: Exposing Hidden Interfaces: LLM-Guided Type Inference for Reverse Engineering macOS Private Frameworks ArXiv ID: 2601.01673 Date: 2026-01-04 Authors: Arina Kharlamova, Youcheng Sun, Ting Yu ๐ Abstract Private macOS frameworks โฆ
๐ Original Info Title: Factorized Learning for Temporally Grounded Video-Language Models ArXiv ID: 2512.24097 Date: 2025-12-30 Authors: Wenzheng Zeng, Difei Gao, Mike Zheng Shou, Hwee Tou Ng ๐ Abstract Evidence grounding What did I put in the rack? โฆ
๐ Original Info Title: FALCON: Few-Shot Adversarial Learning for Cross-Domain Medical Image Segmentation ArXiv ID: 2601.01687 Date: 2026-01-04 Authors: Abdur R. Fayjie, Pankhi Kashyap, Jutika Borah, Patrick Vandewalle ๐ Abstract Precise delineation โฆ
๐ Original Info Title: FastV-RAG: Towards Fast and Fine-Grained Video QA with Retrieval-Augmented Generation ArXiv ID: 2601.01513 Date: 2026-01-04 Authors: Gen Li, Peiyu Liu ๐ Abstract Vision-Language Models (VLMs) excel at visual reasoning but still โฆ
๐ Original Info Title: FedSCAM (Federated Sharpness-Aware Minimization with Clustered Aggregation and Modulation): Scam-resistant SAM for Robust Federated Optimization in Heterogeneous Environments ArXiv ID: 2601.00853 Date: 2025-12-29 Authors: โฆ
๐ Original Info Title: FlashInfer-Bench: Building the Virtuous Cycle for AI-driven LLM Systems ArXiv ID: 2601.00227 Date: 2026-01-01 Authors: Shanli Xing, Yiyan Zhai, Alexander Jiang, Yixin Dong, Yong Wu, Zihao Ye, Charlie Ruan, Yingyi Huang, Yineng โฆ
๐ Original Info Title: ForCM: Forest Cover Mapping from Multispectral Sentinel-2 Image by Integrating Deep Learning with Object-Based Image Analysis ArXiv ID: 2512.23196 Date: 2025-12-29 Authors: Maisha Haque, Israt Jahan Ayshi, Sadaf M. Anis, Nahian โฆ
๐ Original Info Title: FormationEval, an open multiple-choice benchmark for petroleum geoscience ArXiv ID: 2601.02158 Date: 2026-01-05 Authors: Almaz Ermilov ๐ Abstract This paper presents FormationEval, an open multiple-choice question benchmark for โฆ
๐ Original Info Title: Generating Diverse TSP Tours via a Combination of Graph Pointer Network and Dispersion ArXiv ID: 2601.01132 Date: 2026-01-03 Authors: Hao-Tsung Yang, Ssu-Yuan Lo, Kuan-Lun Chen, Ching-Kai Wang ๐ Abstract We address the Diverse โฆ
๐ Original Info Title: Geometric and Dynamic Scaling in Deep Transformers ArXiv ID: 2601.01014 Date: 2026-01-03 Authors: Haoran Su, Chenyu You ๐ Abstract Scaling Transformer architectures to extreme depth often leads to rank collapse: representations โฆ
๐ Original Info Title: Geometric Regularization in Mixture-of-Experts: The Disconnect Between Weights and Activations ArXiv ID: 2601.00457 Date: 2026-01-01 Authors: Hyunjun Kim ๐ Abstract Mixture-of-Experts (MoE) models achieve efficiency through โฆ
Enter keywords to search articles