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 |
|---|---|---|---|---|---|
| Structured Visual Narratives Undermine Safety Alignment in Multimodal Large Language Models Roy Ka-Wei Lee, Rui Yang Tan, Yujia Hu Published: 2026-03-23Area: cs.CRCitations: - Tags: ai-safety, alignment-training, cscr, preprint | 2026-03-23 | cs.CR | ai-safety, alignment-training, cscr, preprint | E5 / R3 (97%) | - |
| Uncertainty-guided Compositional Alignment with Part-to-Whole Semantic Representativeness in Hyperbolic Vision-Language Models Hayeon Kim, Ji Ha Jang, Junghun James Kim, Se Young Chun Published: 2026-03-23Area: cs.CVCitations: - Tags: ai-safety, alignment-training, cscv, preprint | 2026-03-23 | cs.CV | ai-safety, alignment-training, cscv, preprint | E6 / R3 (94%) | - |
| Uncertainty-guided Compositional Alignment with Part-to-Whole Semantic Representativeness in Hyperbolic Vision-Language Models Hayeon Kim, Ji Ha Jang, Junghun James Kim, Se Young Chun Published: 2026-03-23Area: cs.CVCitations: - Tags: ai-safety, alignment-training, cscv, preprint | 2026-03-23 | cs.CV | ai-safety, alignment-training, cscv, preprint | E6 / R3 (94%) | - |
| HyFI: Hyperbolic Feature Interpolation for Brain-Vision Alignment Da-Woon Heo, Heung-Il Suk, Sangmin Jo, Wootaek Jeong Published: 2026-03-24Area: cs.AICitations: - Tags: ai-safety, alignment-training, csai, preprint | 2026-03-24 | cs.AI | ai-safety, alignment-training, csai, preprint | E5 / R3 (99%) | - |
| ImplicitRM: Unbiased Reward Modeling from Implicit Preference Data for LLM alignment Haocheng Yang, Hao Wang, Haoxuan Li, Lei Shen Published: 2026-03-24Area: cs.CLCitations: - Tags: ai-safety, alignment-training, cscl, preprint | 2026-03-24 | cs.CL | ai-safety, alignment-training, cscl, preprint | E5 / R3 (94%) | - |
| Improving Safety Alignment via Balanced Direct Preference Optimization Fangzhou Chen, Mengyang Wang, Qihui Zhu, Ranjie Duan Published: 2026-03-24Area: cs.AICitations: - Tags: ai-safety, alignment-training, csai, preprint | 2026-03-24 | cs.AI | ai-safety, alignment-training, csai, preprint | E6 / R3 (95%) | - |
| KARMA: Knowledge-Action Regularized Multimodal Alignment for Personalized Search at Taobao Dan Ou, Haihong Tang, Liren Yu, Wenming Zhang Published: 2026-03-24Area: cs.IRCitations: - Tags: ai-safety, alignment-training, csir, preprint | 2026-03-24 | cs.IR | ai-safety, alignment-training, csir, preprint | E5 / R3 (95%) | - |
| Probabilistic Geometric Alignment via Bayesian Latent Transport for Domain-Adaptive Foundation Models Aueaphum Aueawatthanaphisut, Kuepon Auewattanapisut Published: 2026-03-24Area: cs.LGCitations: - Tags: ai-safety, alignment-training, cslg, preprint | 2026-03-24 | cs.LG | ai-safety, alignment-training, cslg, preprint | E5 / R3 (94%) | - |
| Probabilistic Geometric Alignment via Bayesian Latent Transport for Domain-Adaptive Foundation Models Kuepon Aueawatthanaphisut Published: 2026-03-24Area: cs.LGCitations: - Tags: ai-safety, alignment-training, cslg, preprint | 2026-03-24 | cs.LG | ai-safety, alignment-training, cslg, preprint | E5 / R3 (95%) | - |
| TDATR: Improving End-to-End Table Recognition via Table Detail-Aware Learning and Cell-Level Visual Alignment Baocai Yin, Bing Yin, Chenyu Liu, Chunxia Qin Published: 2026-03-24Area: cs.CVCitations: - Tags: ai-safety, alignment-training, cscv, preprint | 2026-03-24 | cs.CV | ai-safety, alignment-training, cscv, preprint | E4 / R3 (96%) | - |
| WiFi2Cap: Semantic Action Captioning from Wi-Fi CSI via Limb-Level Semantic Alignment Chu-Yu Huang, Jen-Jee Chen, Tzu-Ti Wei, Yu-Chee Tseng Published: 2026-03-24Area: cs.CVCitations: - Tags: ai-safety, alignment-training, cscv, preprint | 2026-03-24 | cs.CV | ai-safety, alignment-training, cscv, preprint | E5 / R3 (96%) | - |
| Latent Bias Alignment for High-Fidelity Diffusion Inversion in Real-World Image Reconstruction and Manipulation Qifan Liu, Siyi Liu, Weiming Chen, Yijia Wang Published: 2026-03-25Area: cs.CVCitations: - Tags: ai-safety, alignment-training, cscv, preprint | 2026-03-25 | cs.CV | ai-safety, alignment-training, cscv, preprint | E5 / R3 (96%) | - |
| The Alignment Tax: Response Homogenization in Aligned LLMs and Its Implications for Uncertainty Estimation Mingyi Liu Published: 2026-03-25Area: cs.LGCitations: - Tags: ai-safety, alignment-training, cslg, preprint | 2026-03-25 | cs.LG | ai-safety, alignment-training, cslg, preprint | E6 / R3 (96%) | - |
| The Alignment Tax: Response Homogenization in Aligned LLMs and Its Implications for Uncertainty Estimation Mingyi Liu Published: 2026-03-25Area: cs.LGCitations: - Tags: ai-safety, alignment-training, cslg, preprint | 2026-03-25 | cs.LG | ai-safety, alignment-training, cslg, preprint | E5 / R3 (95%) | - |
| CVA: Context-aware Video-text Alignment for Video Temporal Grounding Jiwan Seo, Seunghun Lee, Sungho Moon, Sunghoon Im Published: 2026-03-26Area: cs.LGCitations: - Tags: ai-safety, alignment-training, cslg, preprint | 2026-03-26 | cs.LG | ai-safety, alignment-training, cslg, preprint | E6 / R4 (98%) | - |
| Drive My Way: Preference Alignment of Vision-Language-Action Model for Personalized Driving Hang Qiu, Huaide Jiang, Jiachen Li, Shuaiwu Dong Published: 2026-03-26Area: cs.ROCitations: - Tags: ai-safety, alignment-training, csro, preprint | 2026-03-26 | cs.RO | ai-safety, alignment-training, csro, preprint | E5 / R3 (96%) | - |
| Goodness-of-pronunciation without phoneme time alignment Jeremy H. M. Wong, Nancy F. Chen Published: 2026-03-26Area: cs.CLCitations: - Tags: ai-safety, alignment-training, cscl, preprint | 2026-03-26 | cs.CL | ai-safety, alignment-training, cscl, preprint | E5 / R3 (95%) | - |
| SAVe: Self-Supervised Audio-visual Deepfake Detection Exploiting Visual Artifacts and Audio-visual Misalignment Ammarah Hashmi, Chia-Wen Lin, Hsin-Min Wang, Junichi Yamagishi Published: 2026-03-26Area: cs.CVCitations: - Tags: ai-safety, alignment-training, cscv, preprint | 2026-03-26 | cs.CV | ai-safety, alignment-training, cscv, preprint | E6 / R3 (98%) | - |
| Mimetic Alignment with ASPECT: Evaluation of AI-inferred Personal Profiles Dan Marshall, Denae Ford, Edward Cutrell, Ruoxi Shang Published: 2026-03-27Area: cs.HCCitations: - Tags: ai-safety, alignment-training, cshc, preprint, safety-evaluation | 2026-03-27 | cs.HC | ai-safety, alignment-training, cshc, preprint, safety-evaluation | E4 / R3 (96%) | - |
| A Revealed Preference Framework for AI Alignment Elchin Suleymanov Published: 2026-03-29Area: econ.THCitations: - Tags: ai-safety, alignment-training, econth, preprint | 2026-03-29 | econ.TH | ai-safety, alignment-training, econth, preprint | E4 / R3 (95%) | - |
| LVRPO: Language-Visual Alignment with GRPO for Multimodal Understanding and Generation Shentong Mo, Sukmin Yun Published: 2026-03-29Area: cs.CVCitations: - Tags: ai-safety, alignment-training, cscv, preprint | 2026-03-29 | cs.CV | ai-safety, alignment-training, cscv, preprint | E6 / R3 (96%) | - |
| Beyond Dataset Distillation: Lossless Dataset Concentration via Diffusion-Assisted Distribution Alignment Bing Li, Tongfei Liu, Weiming Hu, Yufan Liu Published: 2026-03-30Area: cs.CVCitations: - Tags: ai-safety, alignment-training, cscv, preprint | 2026-03-30 | cs.CV | ai-safety, alignment-training, cscv, preprint | E5 / R3 (97%) | - |
| AGFT: Alignment-Guided Fine-Tuning for Zero-Shot Adversarial Robustness of Vision-Language Models Xianchao Guan, Yubo Cui, Zheng Zhang, Zijun Xiong Published: 2026-03-31Area: cs.CVCitations: - Tags: adversarial-robustness, ai-safety, alignment-training, cscv, preprint | 2026-03-31 | cs.CV | adversarial-robustness, ai-safety, alignment-training, cscv, preprint | E5 / R3 (95%) | - |
| M-MiniGPT4: Multilingual VLLM Alignment via Translated Data Mohamed Elhoseiny, Seung Hun Han, Youssef Mohamed Published: 2026-03-31Area: cs.CLCitations: - Tags: ai-safety, alignment-training, cscl, preprint | 2026-03-31 | cs.CL | ai-safety, alignment-training, cscl, preprint | E5 / R3 (98%) | - |
| Neural-Assisted in-Motion Self-Heading Alignment Adriano Frutuoso, Felipe O. Silva, Itzik Klein, Zeev Yampolsky Published: 2026-03-31Area: cs.ROCitations: - Tags: ai-safety, alignment-training, csro, preprint | 2026-03-31 | cs.RO | ai-safety, alignment-training, csro, preprint | E5 / R2 (94%) | - |
| RAAP: Retrieval-Augmented Affordance Prediction with Cross-Image Action Alignment He-Yang Xu, Qiyuan Zhuang, Xin-Yang Zhao, Xiu-Shen Wei Published: 2026-03-31Area: cs.ROCitations: - Tags: ai-safety, alignment-training, csro, preprint | 2026-03-31 | cs.RO | ai-safety, alignment-training, csro, preprint | E5 / R4 (94%) | - |
| The Geometry of Compromise: Unlocking Generative Capabilities via Controllable Modality Alignment Hongyuan Liu, Jiaming Liu, Jinxia Guo, Junming Shao Published: 2026-03-31Area: cs.CVCitations: - Tags: ai-safety, alignment-training, cscv, preprint | 2026-03-31 | cs.CV | ai-safety, alignment-training, cscv, preprint | E5 / R3 (96%) | - |
| GRASP: Gradient Realignment via Active Shared Perception for Multi-Agent Collaborative Optimization Sihan Zhou, Tiantian He, Yaqing Hou, Yew-Soon Ong Published: 2026-04-01Area: cs.MACitations: - Tags: ai-safety, alignment-training, csma, preprint | 2026-04-01 | cs.MA | ai-safety, alignment-training, csma, preprint | E5 / R3 (96%) | - |
| UK AISI Alignment Evaluation Case-Study Abby D'Cruz, Alexandra Souly, Jacob Merizian, Robert Kirk Published: 2026-04-01Area: cs.AICitations: - Tags: ai-safety, alignment-training, csai, preprint, safety-evaluation | 2026-04-01 | cs.AI | ai-safety, alignment-training, csai, preprint, safety-evaluation | E6 / R3 (96%) | - |
| Fusion and Alignment Enhancement with Large Language Models for Tail-item Sequential Recommendation Chuang Zhao, Guibing Guo, Yizhou Dang, Zhifu Wei Published: 2026-04-04Area: cs.IRCitations: - Tags: ai-safety, alignment-training, csir, preprint | 2026-04-04 | cs.IR | ai-safety, alignment-training, csir, preprint | E5 / R3 (96%) | - |