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 |
|---|---|---|---|---|---|
| "Dark Triad" Model Organisms of Misalignment: Narrow Fine-Tuning Mirrors Human Antisocial Behavior Fiona Collins, Jonas Kaplan, Roshni Lulla, Sanaya Parekh Published: 2026-03-06Area: cs.CLCitations: - Tags: ai-safety, alignment-training, cscl, preprint | 2026-03-06 | cs.CL | ai-safety, alignment-training, cscl, preprint | E5 / R4 (95%) | - |
| Property-driven Protein Inverse Folding With Multi-Objective Preference Alignment Chence Shi, Jian Tang, Junqi Liu, Xiaoyang Hou Published: 2026-03-06Area: cs.LGCitations: - Tags: ai-safety, alignment-training, cslg, preprint | 2026-03-06 | cs.LG | ai-safety, alignment-training, cslg, preprint | E5 / R3 (96%) | - |
| SAHOO: Safeguarded Alignment for High-Order Optimization Objectives in Recursive Self-Improvement Aman Chadha, Divya Chaudhary, Subramanyam Sahoo, Vinija Jain Published: 2026-03-06Area: cs.AICitations: - Tags: ai-safety, alignment-training, csai, preprint | 2026-03-06 | cs.AI | ai-safety, alignment-training, csai, preprint | E6 / R4 (97%) | - |
| Hit-RAG: Learning to Reason with Long Contexts via Preference Alignment Junming Liu, Shiping Wen, Tingwen Huang, Yuqi Li Published: 2026-03-07Area: cs.CLCitations: - Tags: ai-safety, alignment-training, cscl, preprint | 2026-03-07 | cs.CL | ai-safety, alignment-training, cscl, preprint | E5 / R4 (97%) | - |
| Do Machines Fail Like Humans? A Human-Centred Out-of-Distribution Spectrum for Mapping Error Alignment Binxia Xu, Luke Dickens, Robert M. Mok, Xiaoliang Luo Published: 2026-03-08Area: cs.AICitations: - Tags: ai-safety, alignment-training, csai, preprint | 2026-03-08 | cs.AI | ai-safety, alignment-training, csai, preprint | E6 / R4 (95%) | - |
| Alignment-Aware and Reliability-Gated Multimodal Fusion for Unmanned Aerial Vehicle Detection Across Heterogeneous Thermal-Visual Sensors Amith Khandakar, Balamurugan Balusamy, Ishrat Jahan, M Murugappan Published: 2026-03-09Area: cs.CVCitations: - Tags: ai-safety, alignment-training, cscv, preprint | 2026-03-09 | cs.CV | ai-safety, alignment-training, cscv, preprint | E4 / R3 (96%) | - |
| Alignment-Process-Outcome: Rethinking How AIs and Humans Collaborate Anjun Zhu, Arpit Narechania, Haichang Li Published: 2026-03-09Area: cs.HCCitations: - Tags: ai-safety, alignment-training, cshc, preprint | 2026-03-09 | cs.HC | ai-safety, alignment-training, cshc, preprint | E5 / R4 (93%) | - |
| DARC: Disagreement-Aware Alignment via Risk-Constrained Decoding Jiaxiang Chen, Junfan Li, Langzhang Liang, Mingxi Zou Published: 2026-03-09Area: cs.LGCitations: - Tags: ai-safety, alignment-training, cslg, preprint | 2026-03-09 | cs.LG | ai-safety, alignment-training, cslg, preprint | E5 / R3 (93%) | - |
| Deconstructing Multimodal Mathematical Reasoning: Towards a Unified Perception-Alignment-Reasoning Paradigm Arman Cohan, Chen Zhao, Lisen Dai, Minhao Cheng Published: 2026-03-09Area: cs.AICitations: - Tags: ai-safety, alignment-training, csai, preprint | 2026-03-09 | cs.AI | ai-safety, alignment-training, csai, preprint | E5 / R3 (95%) | - |
| Foley-Flow: Coordinated Video-to-Audio Generation with Masked Audio-Visual Alignment and Dynamic Conditional Flows Shentong Mo, Yibing Song Published: 2026-03-09Area: cs.CVCitations: - Tags: ai-safety, alignment-training, cscv, preprint | 2026-03-09 | cs.CV | ai-safety, alignment-training, cscv, preprint | E5 / R3 (98%) | - |
| Towards Effective and Efficient Graph Alignment without Supervision Lei Zou, Shuai Zheng, Songyang Chen, Youfang Lin Published: 2026-03-09Area: cs.LGCitations: - Tags: ai-safety, alignment-training, cslg, preprint | 2026-03-09 | cs.LG | ai-safety, alignment-training, cslg, preprint | E5 / R3 (95%) | - |
| Visual Self-Fulfilling Alignment: Shaping Safety-Oriented Personas via Threat-Related Images Di Wang, Lijie Hu, Qishun Yang, Shu Yang Published: 2026-03-09Area: cs.CVCitations: - Tags: ai-safety, alignment-training, cscv, preprint | 2026-03-09 | cs.CV | ai-safety, alignment-training, cscv, preprint | E5 / R3 (94%) | - |
| Composed Vision-Language Retrieval for Skin Cancer Case Search via Joint Alignment of Global and Local Representations Chunqi Chang, Dongrun Zhu, Harvey Lui, Jiayue Cai Published: 2026-03-10Area: cs.CVCitations: - Tags: ai-safety, alignment-training, cscv, preprint | 2026-03-10 | cs.CV | ai-safety, alignment-training, cscv, preprint | E5 / R3 (96%) | - |
| Joint Imaging-ROI Representation Learning via Cross-View Contrastive Alignment for Brain Disorder Classification Lifang He, Wei Liang Published: 2026-03-10Area: cs.CVCitations: - Tags: ai-safety, alignment-training, cscv, preprint | 2026-03-10 | cs.CV | ai-safety, alignment-training, cscv, preprint | E5 / R4 (96%) | - |
| LCA: Local Classifier Alignment for Continual Learning Danilo Vasconcellos Vargas, Khoat Than, Tung Tran Published: 2026-03-10Area: cs.AICitations: - Tags: ai-safety, alignment-training, csai, preprint | 2026-03-10 | cs.AI | ai-safety, alignment-training, csai, preprint | E5 / R3 (96%) | - |
| Multi-Stream Perturbation Attack: Breaking Safety Alignment of Thinking LLMs Through Concurrent Task Interference Fan Yang Published: 2026-03-10Area: cs.CRCitations: - Tags: ai-safety, alignment-training, cscr, preprint | 2026-03-10 | cs.CR | ai-safety, alignment-training, cscr, preprint | E6 / R4 (97%) | - |
| SPAARS: Safer RL Policy Alignment through Abstract Exploration and Refined Exploitation of Action Space Aritra Hazra, Swaminathan S K Published: 2026-03-10Area: cs.LGCitations: - Tags: ai-safety, alignment-training, cslg, preprint | 2026-03-10 | cs.LG | ai-safety, alignment-training, cslg, preprint | E6 / R3 (95%) | - |
| Does LLM Alignment Really Need Diversity? An Empirical Study of Adapting RLVR Methods for Moral Reasoning Ceyao Zhang, Junchao Huang, Xiaohan Liu, Xiaoyuan Yi Published: 2026-03-11Area: cs.AICitations: - Tags: ai-safety, alignment-training, csai, preprint | 2026-03-11 | cs.AI | ai-safety, alignment-training, csai, preprint | E5 / R3 (96%) | - |
| Enhancing Value Alignment of LLMs with Multi-agent system and Combinatorial Fusion D. Frank Hsu, Djallel Bouneffouf, Yuanhong Wu Published: 2026-03-11Area: cs.MACitations: - Tags: ai-safety, alignment-training, csma, preprint | 2026-03-11 | cs.MA | ai-safety, alignment-training, csma, preprint | E5 / R4 (94%) | - |
| Learning to Negotiate: Multi-Agent Deliberation for Collective Value Alignment in LLMs Jad Tarifi, Nataliia Babina, Nima Asgharbeygi, Panatchakorn Anantaprayoon Published: 2026-03-11Area: cs.CLCitations: - Tags: ai-safety, alignment-training, cscl, preprint | 2026-03-11 | cs.CL | ai-safety, alignment-training, cscl, preprint | E5 / R3 (94%) | - |
| Deactivating Refusal Triggers: Understanding and Mitigating Overrefusal in Safety Alignment Bocheng Chen, Guangliang Liu, Ramtin Pedarsani, Zhiyu Xue Published: 2026-03-12Area: cs.AICitations: - Tags: ai-safety, alignment-training, csai, preprint | 2026-03-12 | cs.AI | ai-safety, alignment-training, csai, preprint | E5 / R3 (95%) | - |
| DiFlowDubber: Discrete Flow Matching for Automated Video Dubbing via Cross-Modal Alignment and Synchronization Hieu-Nghia Huynh-Nguyen, Jeongsoo Choi, Ngoc-Son Nguyen, Thanh V. T. Tran Published: 2026-03-15Area: cs.CVCitations: - Tags: ai-safety, alignment-training, cscv, preprint | 2026-03-15 | cs.CV | ai-safety, alignment-training, cscv, preprint | E5 / R4 (96%) | - |
| Trust-Region Noise Search for Black-Box Alignment of Diffusion and Flow Models Daniel Cremers, Karnik Ram, Niklas Schweiger Published: 2026-03-15Area: cs.LGCitations: - Tags: ai-safety, alignment-training, cslg, preprint | 2026-03-15 | cs.LG | ai-safety, alignment-training, cslg, preprint | E5 / R3 (95%) | - |
| Are Dilemmas and Conflicts in LLM Alignment Solvable? A View from Priority Graph Bo Li, Eunsol Choi, Qian Wang, Xiang Liu Published: 2026-03-16Area: cs.AICitations: - Tags: ai-safety, alignment-training, csai, preprint | 2026-03-16 | cs.AI | ai-safety, alignment-training, csai, preprint | E4 / R3 (93%) | - |
| Unlocking the Value of Text: Event-Driven Reasoning and Multi-Level Alignment for Time Series Forecasting Bin Yang, Chenjuan Guo, Peng Chen, Siyuan Wang Published: 2026-03-16Area: cs.AICitations: - Tags: ai-safety, alignment-training, csai, preprint | 2026-03-16 | cs.AI | ai-safety, alignment-training, csai, preprint | E6 / R4 (96%) | - |
| A Context Alignment Pre-processor for Enhancing the Coherence of Human-LLM Dialog Ding Wei Published: 2026-03-17Area: cs.AICitations: - Tags: ai-safety, alignment-training, csai, preprint | 2026-03-17 | cs.AI | ai-safety, alignment-training, csai, preprint | E5 / R4 (96%) | - |
| Alignment Makes Language Models Normative, Not Descriptive Eilam Shapira, Moshe Tennenholtz, Roi Reichart Published: 2026-03-17Area: cs.CLCitations: - Tags: ai-safety, alignment-training, cscl, preprint | 2026-03-17 | cs.CL | ai-safety, alignment-training, cscl, preprint | E5 / R3 (94%) | - |
| MOSAIC: Composable Safety Alignment with Modular Control Tokens Hongyu Chen, Jiancheng Dong, Jingyu Peng, Kai Zhang Published: 2026-03-17Area: cs.AICitations: - Tags: ai-safety, alignment-training, csai, preprint | 2026-03-17 | cs.AI | ai-safety, alignment-training, csai, preprint | E5 / R3 (94%) | - |
| Prompt Programming for Cultural Bias and Alignment of Large Language Models Brian Cook, Eric Michalak, Johnny Seales, Maksim Eren Published: 2026-03-17Area: cs.AICitations: - Tags: ai-safety, alignment-training, csai, preprint | 2026-03-17 | cs.AI | ai-safety, alignment-training, csai, preprint | E5 / R3 (96%) | - |
| V-Co: A Closer Look at Visual Representation Alignment via Co-Denoising Chu Wang, Han Lin, Jaemin Cho, Mohit Bansal Published: 2026-03-17Area: cs.CVCitations: - Tags: ai-safety, alignment-training, cscv, preprint | 2026-03-17 | cs.CV | ai-safety, alignment-training, cscv, preprint | E5 / R3 (97%) | - |