Instant research discovery
Search and browse arXiv CS/AI/ML papers, enriched with AI-generated insights.
Generate novel research ideas grounded in real arXiv papers with Brainstorm.
PreviousNext
| Paper | Published | Area | Tags | Intel | Citations |
|---|---|---|---|---|---|
Search and browse arXiv CS/AI/ML papers, enriched with AI-generated insights.
Generate novel research ideas grounded in real arXiv papers with Brainstorm.
| Paper | Published | Area | Tags | Intel | Citations |
|---|---|---|---|---|---|
Search and browse arXiv CS/AI/ML papers, enriched with AI-generated insights.
Generate novel research ideas grounded in real arXiv papers with Brainstorm.
| Paper | Published | Area | Tags | Intel | Citations |
|---|---|---|---|---|---|
| Paper | Published | Area | Tags | Intel | Citations |
|---|---|---|---|---|---|
| When 1+1 Backfires: Rethinking Relevance-Diversity Balancing for Sample-Aware Visual Token Reduction Chenhao Zhou, Difu Feng, Peisong Wen, Qianqian Xu Published: 2026-10-12Area: cs.AICitations: - Tags: ai-safety, csai, preprint | 2026-10-12 | cs.AI | ai-safety, csai, preprint | - | - |
| When a Conceptor Complement Becomes Gain: Operator Geometry and Behavioral Attribution in Language Models R Balamurugan, Shuhul Razdan Published: 2026-10-12Area: cs.AICitations: - Tags: ai-safety, csai, preprint | 2026-10-12 | cs.AI | ai-safety, csai, preprint | - | - |
| When Agent Evaluation Becomes Unreliable: An Empirical Study of Oracle Failures and Configuration-Dependent Measurement in an LLM Agent Benchmark Junjie Chen Published: 2026-10-12Area: cs.SECitations: - Tags: ai-safety, csse, preprint, safety-evaluation | 2026-10-12 | cs.SE | ai-safety, csse, preprint, safety-evaluation | - | - |
| When Agents Talk, Secrets Travel: Topology-Driven Leakage and Recipient-Conditioned Sanitization in Multi-Agent LLM Systems Muhammad Ikram, Sunday Oyinlola Ogundoyin Published: 2026-10-12Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-10-12 | cs.CR | ai-safety, cscr, preprint | - | - |
| When Does Compensating Inherited Quantization Error Help? Mean-Square Guarantees for Layer-Wise Quantization and Their Limits Tianhao Guo Published: 2026-10-12Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-10-12 | cs.LG | ai-safety, cslg, preprint | - | - |
| When Goals Leak Across Relationships: How Cached Goal Representations Shape Cross-Client Decisions Glenn Matlin, Saloni Gupta, S茅bastien Krier Published: 2026-10-12Area: cs.AICitations: - Tags: ai-safety, csai, preprint | 2026-10-12 | cs.AI | ai-safety, csai, preprint | - | - |
| When LLM Agents See a Conflict but Still Proceed: Cross-Domain Dependencies in Network Slicing Marcos Lima Romero, Ricardo Suyama Published: 2026-10-12Area: cs.AICitations: - Tags: ai-safety, csai, preprint | 2026-10-12 | cs.AI | ai-safety, csai, preprint | - | - |
| Where Polanyi Meets Galois: Tacit Knowing as an Algebro-Deterministic Operation, Toward Re-rooting AI-Generated Science Hiroyuki Chuma, Kanji Otsuka, Kodo Yamauchi, Yoichi Sato Published: 2026-10-12Area: cs.NECitations: - Tags: ai-safety, csne, preprint | 2026-10-12 | cs.NE | ai-safety, csne, preprint | - | - |
| Who is the 'I' in AI? Establishing Decentralized Identity and Accountability for Autonomous Agents Ahammod Munim Ramil, Khalid Al Kafi, M. A. Abdullahis Sany, Md Sadek Ferdous Published: 2026-10-12Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-10-12 | cs.CR | ai-safety, cscr, preprint | - | - |
| Why Agentic Workflows Fail: A Taxonomy Derived from Literature and Empirical Data Rami Bahsoon, Tao Chen, Xin Li Published: 2026-10-12Area: cs.SECitations: - Tags: ai-safety, csse, preprint | 2026-10-12 | cs.SE | ai-safety, csse, preprint | - | - |
| WildTrace: Evaluating Training Data Detection in Realistic Large-Scale LLM Post-Training Hengxiang Zhang, Hongxin Wei, Junxian Liu Published: 2026-10-12Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-10-12 | cs.LG | ai-safety, cslg, preprint | - | - |
| World Models Need a Physical Registry: Learning Internal Predictive States for Physically Plausible World Models Jaeseok Jeong, Jianlong Fu, Shinseong Kim, Youngjung Uh Published: 2026-10-12Area: cs.AICitations: - Tags: ai-safety, csai, preprint | 2026-10-12 | cs.AI | ai-safety, csai, preprint | - | - |
| WorldRoPE: Probabilistic World-Centric Rotary Embedding for Multi-View Attention Bohyung Han, Kyujin Lim, Mijeong Kim Published: 2026-10-12Area: cs.CVCitations: - Tags: ai-safety, cscv, preprint | 2026-10-12 | cs.CV | ai-safety, cscv, preprint | - | - |
| World-T3: Test-Time Training as Persistent Memory for Real-Time Video World Models Bartek Rymkowski, Chen Guo, Chenhongyi Yang, Hongbing Hu Published: 2026-10-12Area: cs.CVCitations: - Tags: ai-safety, cscv, preprint | 2026-10-12 | cs.CV | ai-safety, cscv, preprint | - | - |
| XAI-Guided Fourier Domain Generalisation for Pure-Simulation Sim-to-Real Deep Reinforcement Learning Chuyao Wang, Nabil Aouf, Wei Yao, Ziwei Wang Published: 2026-10-12Area: cs.AICitations: - Tags: ai-safety, csai, preprint | 2026-10-12 | cs.AI | ai-safety, csai, preprint | - | - |
| Accuracy and Uncertainty in Machine Deception Detection (Research White Paper) Heng-Sheng Chang Published: 2026-10-11Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-10-11 | cs.LG | ai-safety, cslg, preprint | - | - |
| Across Viewpoints and Time: Trajectory-Generalizable Physical Attacks on World Models and Video Understanding Models Chenqi Kong, Meiwen Ding, Song Xia, Wenhan Yang Published: 2026-10-11Area: cs.CVCitations: - Tags: ai-safety, cscv, preprint | 2026-10-11 | cs.CV | ai-safety, cscv, preprint | - | - |
| ADAPT: Audio-Depth Action Planning with Transition-Aware Rewards for Lights-Out Industrial Navigation Hanning Chen, Jiarui Cui, Lichi Li, Mohsen Imani Published: 2026-10-11Area: cs.AICitations: - Tags: ai-safety, csai, preprint | 2026-10-11 | cs.AI | ai-safety, csai, preprint | - | - |
| Adaptive Look, Flexible Thought: Learning How and How Long to Think in Multimodal Reasoning Boqiang Guo, Chunjin Ye, Kun Xiang, Quanlin Chen Published: 2026-10-11Area: cs.CVCitations: - Tags: ai-safety, cscv, preprint | 2026-10-11 | cs.CV | ai-safety, cscv, preprint | - | - |
| A Decade in a Day: Synthesizing Agent-Native Interfaces from Human-Oriented Software Evolution Alan Wu, Wei Tao, Yiwen Guo Published: 2026-10-11Area: cs.SECitations: - Tags: ai-safety, csse, preprint | 2026-10-11 | cs.SE | ai-safety, csse, preprint | - | - |
| A Decade of PhotoMappers: A Longitudinal Study of Crowdsourced Disaster Photos Geolocalization with Vision-Language Models and Geospatial Reasoning Fabian Deuser, Fan Zhang, Filip Biljecki, Hao Li Published: 2026-10-11Area: cs.AICitations: - Tags: ai-safety, csai, preprint | 2026-10-11 | cs.AI | ai-safety, csai, preprint | - | - |
| Adversarial Detection for Pre-trained Classifiers via Lipschitz-Margin Analysis with Certification Huazhen Yu, Jian Liu, Rui Zhang, Xinle Cao Published: 2026-10-11Area: cs.LGCitations: - Tags: adversarial-robustness, ai-safety, cslg, preprint | 2026-10-11 | cs.LG | adversarial-robustness, ai-safety, cslg, preprint | - | - |
| Agent-Canary-Mas: End-to-End Evaluation of Protocol Risk in Long-Horizon Multi-Agent Systems Bin Zhu, Chao Feng, Le Gai, Peiyang Li Published: 2026-10-11Area: cs.AICitations: - Tags: ai-safety, csai, preprint, safety-evaluation | 2026-10-11 | cs.AI | ai-safety, csai, preprint, safety-evaluation | - | - |
| Agent Sociodrama: Social-Dynamics-Guided Persona Recasting for LLM Agent Teams Jaehong Yoon, Xiaoming Zhang, Yirui Qi Published: 2026-10-11Area: cs.AICitations: - Tags: ai-safety, csai, preprint | 2026-10-11 | cs.AI | ai-safety, csai, preprint | - | - |
| Analyzing the Dynamics of WSBM-based Echo State Networks using InputDSA Huy Mai, Robert Clarke Published: 2026-10-11Area: cs.AICitations: - Tags: ai-safety, csai, preprint | 2026-10-11 | cs.AI | ai-safety, csai, preprint | - | - |
| Anchor-and-Harvest Curriculum: A Fully Unmasked Non-LLM Curriculum for Craftax Hanyi Dong, Jiayu Zhu, Luyuan Li, Yuyuan Shi Published: 2026-10-11Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-10-11 | cs.LG | ai-safety, cslg, preprint | - | - |
| An Explainable System for Offensive Content Detection in Nastaliq Urdu: Corpus Curation, Transformer Benchmarking, and Word-Level Attribution Muhammad Shahid Iqbal Malik Published: 2026-10-11Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-10-11 | cs.CL | ai-safety, cscl, preprint | - | - |
| A Sovereign, Indic-First, Reasoning Model Avinash Benki, Daksh Maan, Nayanjit Sarkar, Parijat Chatterjee Published: 2026-10-11Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-10-11 | cs.CL | ai-safety, cscl, preprint | - | - |
| Attention Sinks in VLMs Are Borrowed, Not Seen Alexander Martin, Andrew Yates, Benjamin Van Durme, Dengjia Zhang Published: 2026-10-11Area: cs.AICitations: - Tags: ai-safety, csai, preprint | 2026-10-11 | cs.AI | ai-safety, csai, preprint | - | - |
| AutoSec-RAN: Specification-Grounded LLM Fine-Tuning for Automated Security Analysis of O-RAN Aly Sabri Abdalla, Anoop Mishra, Joshua Moore, Vuk Marojevic Published: 2026-10-11Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-10-11 | cs.CR | ai-safety, cscr, preprint | - | - |