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 |
|---|---|---|---|---|---|
| Sparrow: Text-Anchored Window Attention with Visual-Semantic Glimpsing for Speculative Decoding in Video LLMs Dongsheng Li, Libo Zhang, Peng Qiao, Wangyang Hong Published: 2026-02-17Area: cs.CVCitations: 15 Tags: ai-safety, cscv, preprint | 2026-02-17 | cs.CV | ai-safety, cscv, preprint | E8 / R7 (91%) | 15 |
| STAPO: Stabilizing Reinforcement Learning for LLMs by Silencing Rare Spurious Tokens Bo Zhang, Guojian Zhan, Jiang Wu, Jingliang Duan Published: 2026-02-17Area: cs.CLCitations: 30 Tags: ai-safety, cscl, preprint | 2026-02-17 | cs.CL | ai-safety, cscl, preprint | E9 / R6 (93%) | 30 |
| SuperLocalMemory: Privacy-Preserving Multi-Agent Memory with Bayesian Trust Defense Against Memory Poisoning Varun Pratap Bhardwaj Published: 2026-02-17Area: cs.AICitations: 15 Tags: ai-safety, csai, preprint | 2026-02-17 | cs.AI | ai-safety, csai, preprint | E10 / R9 (91%) | 15 |
| The Compute ICE-AGE: Invariant Compute Envelope under Addressable Graph Evolution R. Jay Martin Published: 2026-02-17Area: cs.OSCitations: 1 Tags: ai-safety, csos, preprint | 2026-02-17 | cs.OS | ai-safety, csos, preprint | E8 / R8 (94%) | 1 |
| The Equalizer: Introducing Shape-Gain Decomposition in Neural Audio Codecs Laurent Girin, Samir Sadok, Xavier Alameda-Pineda Published: 2026-02-17Area: cs.SDCitations: - Tags: ai-safety, cssd, preprint | 2026-02-17 | cs.SD | ai-safety, cssd, preprint | E10 / R9 (92%) | - |
| The Geometric Anatomy of Capability Acquisition in Transformers Jayadev Billa Published: 2026-02-17Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-02-17 | cs.LG | ai-safety, cslg, preprint | E8 / R6 (91%) | - |
| The Geometry of Alignment Collapse: When Fine-Tuning Breaks Safety Aleksandra Korolova, Blossom Metevier, Bohdan Turbal, Chung Peng Lee Published: 2026-02-17Area: cs.LGCitations: 65 Tags: ai-safety, alignment-training, cslg, preprint | 2026-02-17 | cs.LG | ai-safety, alignment-training, cslg, preprint | E8 / R8 (95%) | 65 |
| The geometry of online conversations and the causal antecedents of conflictual discourse Carlo Santagiustina, Caterina Cruciani Published: 2026-02-17Area: cs.SICitations: - Tags: ai-safety, cssi, preprint | 2026-02-17 | cs.SI | ai-safety, cssi, preprint | E9 / R6 (90%) | - |
| The Information Geometry of Softmax: Probing and Steering Kiho Park, Todd Nief, Victor Veitch, Yo Joong Choe Published: 2026-02-17Area: cs.LGCitations: 15 Tags: ai-safety, cslg, preprint | 2026-02-17 | cs.LG | ai-safety, cslg, preprint | E10 / R6 (90%) | 15 |
| The Obfuscation Atlas: Mapping Where Honesty Emerges in RLVR with Deception Probes Adam Gleave, Chris Cundy, Mohammad Taufeeque, Stefan Heimersheim Published: 2026-02-17Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-02-17 | cs.LG | ai-safety, cslg, preprint | E10 / R8 (92%) | - |
| This human study did not involve human subjects: Validating LLM simulations as behavioral evidence Aaron Shaw, David Broska, Huaman Sun, Jessica Hullman Published: 2026-02-17Area: cs.AICitations: - Tags: ai-safety, csai, preprint | 2026-02-17 | cs.AI | ai-safety, csai, preprint | E6 / R5 (91%) | - |
| Towards Efficient Constraint Handling in Neural Solvers for Routing Problems Cathy Wu, Jianan Zhou, Jieyi Bi, Jie Zhang Published: 2026-02-17Area: cs.AICitations: 15 Tags: ai-safety, csai, preprint | 2026-02-17 | cs.AI | ai-safety, csai, preprint | E12 / R10 (92%) | 15 |
| Transforming GenAI Policy to Prompting Instruction: An RCT of Scalable Prompting Interventions in a CS1 Course Harsh Kumar, Jessica Wen, John Stamper, Michael Liut Published: 2026-02-17Area: cs.HCCitations: - Tags: ai-safety, cshc, preprint | 2026-02-17 | cs.HC | ai-safety, cshc, preprint | E8 / R6 (92%) | - |
| Uncertainty-Calibrated Spatiotemporal Field Diffusion with Sparse Supervision David Keetae Park, Kevin Valencia, Shinjae Yoo, Xihaier Luo Published: 2026-02-17Area: cs.LGCitations: 15 Tags: ai-safety, cslg, preprint | 2026-02-17 | cs.LG | ai-safety, cslg, preprint | E8 / R7 (91%) | 15 |
| Understanding vs. Generation: Navigating Optimization Dilemma in Multimodal Models Di He, Han Hu, Liwei Wang, Mengde Xu Published: 2026-02-17Area: cs.CVCitations: - Tags: ai-safety, cscv, preprint | 2026-02-17 | cs.CV | ai-safety, cscv, preprint | E8 / R7 (91%) | - |
| Unforgeable Watermarks for Language Models via Robust Signatures Huijia Lin, Kameron Shahabi, Min Jae Song Published: 2026-02-17Area: cs.CRCitations: 40 Tags: ai-safety, cscr, preprint | 2026-02-17 | cs.CR | ai-safety, cscr, preprint | E11 / R9 (92%) | 40 |
| Updating Parametric Knowledge with Context Distillation Retains Post-Training Capabilities Mustafa Omer Gul, Shankar Padmanabhan, Tanya Goyal Published: 2026-02-17Area: cs.CLCitations: 15 Tags: ai-safety, cscl, preprint | 2026-02-17 | cs.CL | ai-safety, cscl, preprint | E10 / R10 (90%) | 15 |
| UrbanVerse: Learning Urban Region Representation Across Cities and Tasks Egemen Tanin, Fengze Sun, Flora D. Salim, Jianzhong Qi Published: 2026-02-17Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-02-17 | cs.LG | ai-safety, cslg, preprint | E10 / R9 (90%) | - |
| Visual Persuasion: What Influences Decisions of Vision-Language Models? Manuel Cherep, Nikhil Singh, Pattie Maes, Pranav M R Published: 2026-02-17Area: cs.CVCitations: - Tags: ai-safety, cscv, preprint | 2026-02-17 | cs.CV | ai-safety, cscv, preprint | E10 / R9 (90%) | - |
| VLM-DEWM: Dynamic External World Model for Verifiable and Resilient Vision-Language Planning in Manufacturing Gang Chen, Guoqin Tang, Ning Ji, Qingxuan Jia Published: 2026-02-17Area: cs.ROCitations: - Tags: ai-safety, csro, preprint | 2026-02-17 | cs.RO | ai-safety, csro, preprint | E9 / R10 (92%) | - |
| What Is Missing: Interpretable Ratings for Large Language Model Outputs Nicholas Stranges, Yimin Yang Published: 2026-02-17Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-02-17 | cs.CL | ai-safety, cscl, preprint | E7 / R5 (92%) | - |
| When Remembering and Planning are Worth it: Navigating under Change J. Brian Burns, Omid Madani, Reza Eghbali, Thomas L. Dean Published: 2026-02-17Area: cs.AICitations: - Tags: ai-safety, csai, preprint | 2026-02-17 | cs.AI | ai-safety, csai, preprint | E10 / R8 (86%) | - |
| World-Model-Augmented Web Agents with Action Correction Juncheng Li, Shengyu Zhang, Tianqing Fang, Xiyun Li Published: 2026-02-17Area: cs.AICitations: 15 Tags: ai-safety, csai, preprint | 2026-02-17 | cs.AI | ai-safety, csai, preprint | E8 / R9 (91%) | 15 |
| X-MAP: eXplainable Misclassification Analysis and Profiling for Spam and Phishing Detection Audun J酶sang, Dian Chen, Dong Hyun Jeong, Feng Chen Published: 2026-02-17Area: cs.AICitations: - Tags: ai-safety, csai, preprint | 2026-02-17 | cs.AI | ai-safety, csai, preprint | E14 / R11 (92%) | - |
| Zombie Agents: Persistent Control of Self-Evolving LLM Agents via Self-Reinforcing Injections Bryan Hooi, Jin Song Dong, Shuo Ji, Xianglin Yang Published: 2026-02-17Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-02-17 | cs.CR | ai-safety, cscr, preprint | E10 / R9 (87%) | - |
| A Contrastive Learning Framework Empowered by Attention-based Feature Adaptation for Street-View Image Classification James Haworth, Qi You, Yitai Cheng, Zichao Zeng Published: 2026-02-18Area: cs.CVCitations: 15 Tags: ai-safety, cscv, preprint | 2026-02-18 | cs.CV | ai-safety, cscv, preprint | E6 / R6 (91%) | 15 |
| AdaptOrch: Task-Adaptive Multi-Agent Orchestration in the Era of LLM Performance Convergence Geunbin Yu Published: 2026-02-18Area: cs.MACitations: - Tags: ai-safety, csma, preprint | 2026-02-18 | cs.MA | ai-safety, csma, preprint | E12 / R10 (92%) | - |
| AgentFixer: From Failure Detection to Fix Recommendations in LLM Agentic Systems Avi Yaeli, Hadar Mulian, Ido Levy, Liane Galanti Published: 2026-02-18Area: cs.AICitations: - Tags: ai-safety, csai, preprint | 2026-02-18 | cs.AI | ai-safety, csai, preprint | E11 / R11 (92%) | - |
| AgentLAB: Benchmarking LLM Agents against Long-Horizon Attacks Jiacheng Liang, Tanqiu Jiang, Ting Wang, Yuhui Wang Published: 2026-02-18Area: cs.AICitations: - Tags: ai-safety, csai, preprint | 2026-02-18 | cs.AI | ai-safety, csai, preprint | E10 / R8 (92%) | - |
| Agent Skill Framework: Perspectives on the Potential of Small to Medium Language Models in Industrial Environments Lama Sleem, Lujun Li, Niccolo Gentile, Radu State Published: 2026-02-18Area: cs.AICitations: - Tags: ai-safety, csai, preprint | 2026-02-18 | cs.AI | ai-safety, csai, preprint | E12 / R8 (90%) | - |