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 |
|---|---|---|---|---|---|
| Via Negativa for AI Alignment: Why Negative Constraints Are Structurally Superior to Positive Preferences Quan Cheng Published: 2026-03-17Area: cs.AICitations: - Tags: ai-safety, alignment-training, csai, preprint | 2026-03-17 | cs.AI | ai-safety, alignment-training, csai, preprint | E6 / R3 (96%) | - |
| Contrastive Reasoning Alignment: Reinforcement Learning from Hidden Representations Binghui Wang, Haozheng Luo, Jiahao Yu, Yan Chen Published: 2026-03-18Area: cs.AICitations: - Tags: ai-safety, alignment-training, csai, preprint | 2026-03-18 | cs.AI | ai-safety, alignment-training, csai, preprint | E6 / R4 (96%) | - |
| Detection Is Cheap, Routing Is Learned: Why Refusal-Based Alignment Evaluation Fails Gregory N. Frank Published: 2026-03-18Area: cs.LGCitations: - Tags: ai-safety, alignment-training, cslg, preprint, safety-evaluation | 2026-03-18 | cs.LG | ai-safety, alignment-training, cslg, preprint, safety-evaluation | E8 / R4 (98%) | - |
| Interpretable Cross-Domain Few-Shot Learning with Rectified Target-Domain Local Alignment Ruixuan Li, Yaze Zhao, Yixiong Zou, Yuhua Li Published: 2026-03-18Area: cs.CVCitations: - Tags: ai-safety, alignment-training, cscv, preprint | 2026-03-18 | cs.CV | ai-safety, alignment-training, cscv, preprint | E5 / R4 (95%) | - |
| Interpretable Cross-Domain Few-Shot Learning with Rectified Target-Domain Local Alignment Ruixuan Li, Yaze Zhao, Yixiong Zou, Yuhua Li Published: 2026-03-18Area: cs.CVCitations: - Tags: ai-safety, alignment-training, cscv, preprint | 2026-03-18 | cs.CV | ai-safety, alignment-training, cscv, preprint | E34 / R27 (96%) | - |
| MALLES: A Multi-agent LLMs-based Economic Sandbox with Consumer Preference Alignment Xiaotie Deng, Yiran Liu, Yusen Wu Published: 2026-03-18Area: cs.AICitations: - Tags: ai-safety, alignment-training, csai, preprint | 2026-03-18 | cs.AI | ai-safety, alignment-training, csai, preprint | E5 / R4 (94%) | - |
| VC-Soup: Value-Consistency Guided Multi-Value Alignment for Large Language Models Han Wu, Hefei Xu, Le Wu, Meng Wang Published: 2026-03-18Area: cs.LGCitations: - Tags: ai-safety, alignment-training, cslg, preprint | 2026-03-18 | cs.LG | ai-safety, alignment-training, cslg, preprint | E5 / R3 (96%) | - |
| Evaluating 5W3H Structured Prompting for Intent Alignment in Human-AI Interaction Peng Gang Published: 2026-03-19Area: cs.AICitations: - Tags: ai-safety, alignment-training, csai, preprint | 2026-03-19 | cs.AI | ai-safety, alignment-training, csai, preprint | E6 / R3 (97%) | - |
| Expert Personas Improve LLM Alignment but Damage Accuracy: Bootstrapping Intent-Based Persona Routing with PRISM Jesse Thomason, Mohammad Rostami, Zizhao Hu Published: 2026-03-19Area: cs.AICitations: - Tags: ai-safety, alignment-training, csai, preprint | 2026-03-19 | cs.AI | ai-safety, alignment-training, csai, preprint | E5 / R3 (96%) | - |
| Secure Linear Alignment of Large Language Models Matt Gorbett, Suman Jana Published: 2026-03-19Area: cs.AICitations: - Tags: ai-safety, alignment-training, csai, preprint | 2026-03-19 | cs.AI | ai-safety, alignment-training, csai, preprint | E50 / R31 (95%) | - |
| Secure Linear Alignment of Large Language Models Matt Gorbett, Suman Jana Published: 2026-03-19Area: cs.AICitations: - Tags: ai-safety, alignment-training, csai, preprint | 2026-03-19 | cs.AI | ai-safety, alignment-training, csai, preprint | E5 / R3 (96%) | - |
| TARo: Token-level Adaptive Routing for LLM Test-time Alignment Arushi Rai, Dipesh Tamboli, Hanqing Zeng, Lizhu Zhang Published: 2026-03-19Area: cs.CLCitations: - Tags: ai-safety, alignment-training, cscl, preprint | 2026-03-19 | cs.CL | ai-safety, alignment-training, cscl, preprint | E6 / R3 (96%) | - |
| The Causal Impact of Tool Affordance on Safety Alignment in LLM Agents Barry L. Bentley, Fiona Carroll, Shasha Yu Published: 2026-03-19Area: cs.SECitations: - Tags: ai-safety, alignment-training, csse, preprint | 2026-03-19 | cs.SE | ai-safety, alignment-training, csse, preprint | E29 / R24 (95%) | - |
| Dual-Domain Representation Alignment: Bridging 2D and 3D Vision via Geometry-Aware Architecture Search Haoyu Zhang, Qiqi Liu, Ran Cheng, Rui Wang Published: 2026-03-20Area: cs.CVCitations: - Tags: ai-safety, alignment-training, cscv, preprint | 2026-03-20 | cs.CV | ai-safety, alignment-training, cscv, preprint | E5 / R4 (94%) | - |
| Enhancing Alignment for Unified Multimodal Models via Semantically-Grounded Supervision Dongbo Min, Hyesong Choi, Jiyeong Kim, Uiwon Hwang Published: 2026-03-20Area: cs.CVCitations: - Tags: ai-safety, alignment-training, cscv, preprint | 2026-03-20 | cs.CV | ai-safety, alignment-training, cscv, preprint | E5 / R3 (95%) | - |
| HiPath: Hierarchical Vision-Language Alignment for Structured Pathology Report Prediction Anbang Wang, Guang Yang, Jiawei Luo, Liwei Hu Published: 2026-03-20Area: cs.CVCitations: - Tags: ai-safety, alignment-training, cscv, preprint | 2026-03-20 | cs.CV | ai-safety, alignment-training, cscv, preprint | E6 / R5 (96%) | - |
| LoD-Loc v3: Generalized Aerial Localization in Dense Cities using Instance Silhouette Alignment Juelin Zhu, Kun Yang, Maojun Zhang, Shen Yan Published: 2026-03-20Area: cs.CVCitations: - Tags: ai-safety, alignment-training, cscv, preprint | 2026-03-20 | cs.CV | ai-safety, alignment-training, cscv, preprint | E5 / R3 (96%) | - |
| LoD-Loc v3: Generalized Aerial Localization in Dense Cities using Instance Silhouette Alignment Juelin Zhu, Kun Yang, Maojun Zhang, Shen Yan Published: 2026-03-20Area: cs.CVCitations: - Tags: ai-safety, alignment-training, cscv, preprint | 2026-03-20 | cs.CV | ai-safety, alignment-training, cscv, preprint | E5 / R3 (97%) | - |
| Spectral Alignment in Forward-Backward Representations via Temporal Abstraction Abhinav Valada, Hao Zhu, Iman Nematollahi, Jasper Hoffmann Published: 2026-03-20Area: cs.LGCitations: - Tags: ai-safety, alignment-training, cslg, preprint | 2026-03-20 | cs.LG | ai-safety, alignment-training, cslg, preprint | E35 / R24 (93%) | - |
| Spectral Alignment in Forward-Backward Representations via Temporal Abstraction Abhinav Valada, Hao Zhu, Iman Nematollahi, Jasper Hoffmann Published: 2026-03-20Area: cs.LGCitations: - Tags: ai-safety, alignment-training, cslg, preprint | 2026-03-20 | cs.LG | ai-safety, alignment-training, cslg, preprint | E5 / R4 (96%) | - |
| Alignment Whack-a-Mole : Finetuning Activates Verbatim Recall of Copyrighted Books in Large Language Models Jane C. Ginsburg, Niloofar Mireshghallah, Tuhin Chakrabarty, Xinyue Liu Published: 2026-03-21Area: cs.CLCitations: - Tags: ai-safety, alignment-training, cscl, preprint | 2026-03-21 | cs.CL | ai-safety, alignment-training, cscl, preprint | E5 / R3 (94%) | - |
| Alignment Whack-a-Mole : Finetuning Activates Verbatim Recall of Copyrighted Books in Large Language Models Jane C. Ginsburg, Niloofar Mireshghallah, Tuhin Chakrabarty, Xinyue Liu Published: 2026-03-21Area: cs.CLCitations: - Tags: ai-safety, alignment-training, cscl, preprint | 2026-03-21 | cs.CL | ai-safety, alignment-training, cscl, preprint | E5 / R2 (96%) | - |
| Aggregation Alignment for Federated Learning with Mixture-of-Experts under Data Heterogeneity Haonan An, Qianru Wang, Xianhao Chen, Yiqin Deng Published: 2026-03-22Area: cs.LGCitations: - Tags: ai-safety, alignment-training, cslg, preprint | 2026-03-22 | cs.LG | ai-safety, alignment-training, cslg, preprint | E4 / R2 (96%) | - |
| Behavioural feasible set: Value alignment constraints on AI decision support Taejin Park Published: 2026-03-22Area: cs.AICitations: - Tags: ai-safety, alignment-training, csai, preprint | 2026-03-22 | cs.AI | ai-safety, alignment-training, csai, preprint | E5 / R3 (94%) | - |
| RoboAlign: Learning Test-Time Reasoning for Language-Action Alignment in Vision-Language-Action Models Dongyoung Kim, Huiwon Jang, Jaehyung Kim, Jinwoo Shin Published: 2026-03-22Area: cs.AICitations: - Tags: ai-safety, alignment-training, csai, preprint | 2026-03-22 | cs.AI | ai-safety, alignment-training, csai, preprint | E7 / R4 (97%) | - |
| SpatialFly: Geometry-Guided Representation Alignment for UAV Vision-and-Language Navigation in Urban Environments Bin Xu, Hanfang Liang, Hongwei Duan, Jinyuan Liu Published: 2026-03-22Area: cs.CVCitations: - Tags: ai-safety, alignment-training, cscv, preprint | 2026-03-22 | cs.CV | ai-safety, alignment-training, cscv, preprint | E5 / R3 (96%) | - |
| A Framework for Closed-Loop Robotic Assembly, Alignment and Self-Recovery of Precision Optical Systems Caio Silva, Marin Solja膷i膰, Sachin Vaidya, Sajib Biswas Shuvo Published: 2026-03-23Area: cs.ROCitations: - Tags: ai-safety, alignment-training, csro, preprint | 2026-03-23 | cs.RO | ai-safety, alignment-training, csro, preprint | E5 / R3 (96%) | - |
| DSPA: Dynamic SAE Steering for Data-Efficient Preference Alignment Aashiq Muhamed, James Wedgwood, Mona T. Diab, Virginia Smith Published: 2026-03-23Area: cs.LGCitations: - Tags: ai-safety, alignment-training, cslg, preprint | 2026-03-23 | cs.LG | ai-safety, alignment-training, cslg, preprint | E6 / R3 (97%) | - |
| MCLR: Improving Conditional Modeling in Visual Generative Models via Inter-Class Likelihood-Ratio Maximization and Establishing the Equivalence between Classifier-Free Guidance and Alignment Objectives Jeffrey A. Fessler, Qing Qu, Rongrong Wang, Xiang Li Published: 2026-03-23Area: cs.LGCitations: - Tags: ai-safety, alignment-training, cslg, preprint | 2026-03-23 | cs.LG | ai-safety, alignment-training, cslg, preprint | E6 / R3 (96%) | - |
| Stabilizing Iterative Self-Training with Verified Reasoning via Symbolic Recursive Self-Alignment Xinyu Zhang Published: 2026-03-23Area: cs.AICitations: - Tags: ai-safety, alignment-training, csai, preprint | 2026-03-23 | cs.AI | ai-safety, alignment-training, csai, preprint | E5 / R4 (98%) | - |