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 |
|---|---|---|---|---|---|
| HARC: Coupling Harmfulness and Refusal Directions for Robust Safety Alignment Fangzhao Wu, Shei Pern Chua Published: 2026-07-01Area: cs.AICitations: - Tags: ai-safety, alignment-training, csai, preprint | 2026-07-01 | cs.AI | ai-safety, alignment-training, csai, preprint | E9 / R6 (96%) | - |
| MEPA: Multi-Scale Representation Alignment for Visual Autoregressive Modeling with Mixture of Experts Jie Hu, Kun Cheng, Lei Yu, Nannan Wang Published: 2026-07-01Area: cs.CVCitations: - Tags: ai-safety, alignment-training, cscv, preprint | 2026-07-01 | cs.CV | ai-safety, alignment-training, cscv, preprint | E6 / R4 (95%) | - |
| Meta-Transfer Learning for mmWave Beam Alignment Ahmet Nuri Cevik, Sinem Coleri Published: 2026-07-01Area: eess.SPCitations: - Tags: ai-safety, alignment-training, eesssp, preprint | 2026-07-01 | eess.SP | ai-safety, alignment-training, eesssp, preprint | E6 / R4 (99%) | - |
| PAPA: Online Personalized Active Preference Alignment Anindya Sarkar, Isaac Lyngaas, Muralikrishnan Gopalakrishnan Meena, Nasik Muhammad Nafi Published: 2026-07-01Area: cs.LGCitations: - Tags: ai-safety, alignment-training, cslg, preprint | 2026-07-01 | cs.LG | ai-safety, alignment-training, cslg, preprint | E7 / R4 (96%) | - |
| The Illusion of High Utility in Safety Alignment of Text-to-Image Diffusion Models Adeel Yousaf, Amrit Singh Bedi, James Beetham, Mubarak Shah Published: 2026-07-01Area: cs.CVCitations: - Tags: ai-safety, alignment-training, cscv, preprint | 2026-07-01 | cs.CV | ai-safety, alignment-training, cscv, preprint | E9 / R5 (97%) | - |
| ADAPT: Attention Dynamics Alignment with Preference Tuning for Faithful MLLMs Jiajun Li, Yi Tu, Zhendong Mao, Zheren Fu Published: 2026-06-30Area: cs.CVCitations: - Tags: ai-safety, alignment-training, cscv, preprint | 2026-06-30 | cs.CV | ai-safety, alignment-training, cscv, preprint | E7 / R5 (98%) | - |
| Evil Spectra: How Optimisers can Amplify or Suppress Emergent Misalignment Jason R. Brown, Lev McKinney, Patrick Leask Published: 2026-06-30Area: cs.LGCitations: - Tags: ai-safety, alignment-training, cslg, preprint | 2026-06-30 | cs.LG | ai-safety, alignment-training, cslg, preprint | E9 / R4 (94%) | - |
| On the Convergence of Self-Improving Online LLM Alignment Jiayu Chen, Pangpang Liu, Vaneet Aggarwal, Xudong Wu Published: 2026-06-30Area: cs.LGCitations: - Tags: ai-safety, alignment-training, cslg, preprint | 2026-06-30 | cs.LG | ai-safety, alignment-training, cslg, preprint | E7 / R4 (96%) | - |
| Resolving superposition in AI for interpretability and cross-modal alignment in patient-neuronal images Daesoo Kim, Daeun Yoo, Eunsu Lee, Ian Choi Published: 2026-06-30Area: cs.LGCitations: - Tags: ai-safety, alignment-training, cslg, interpretability, preprint | 2026-06-30 | cs.LG | ai-safety, alignment-training, cslg, interpretability, preprint | E8 / R4 (97%) | - |
| Data-Efficient Multimodal Alignment for Histopathology-based Molecular Prediction Christian Gebbe, Dominik Vonficht, Dominik Winter, Lo茂c Le Bescond Published: 2026-06-29Area: eess.IVCitations: - Tags: ai-safety, alignment-training, eessiv, preprint | 2026-06-29 | eess.IV | ai-safety, alignment-training, eessiv, preprint | E10 / R5 (96%) | - |
| PromptGNN-sim: Deep Fusion and Alignment of GNN and LLMs for Text-Attributed Graph Learning Alexandra I. Cristea, Zhifei Hu Published: 2026-06-29Area: cs.AICitations: - Tags: ai-safety, alignment-training, csai, preprint | 2026-06-29 | cs.AI | ai-safety, alignment-training, csai, preprint | E8 / R4 (96%) | - |
| A Hybrid Framework for Song Lyric Annotation Based on Human-LLM Alignment Aditya Joshi, Erik Meijering, Frank Tran, Md Mahmudul Hasan Published: 2026-06-28Area: cs.CLCitations: - Tags: ai-safety, alignment-training, cscl, preprint | 2026-06-28 | cs.CL | ai-safety, alignment-training, cscl, preprint | E8 / R6 (98%) | - |
| Rank-Aware Hyperbolic Alignment for Vision-Language Dataset Distillation Jongoh Jeong, Kuk-Jin Yoon, Sun-Kyung Lee Published: 2026-06-28Area: cs.CVCitations: - Tags: ai-safety, alignment-training, cscv, preprint | 2026-06-28 | cs.CV | ai-safety, alignment-training, cscv, preprint | E9 / R4 (97%) | - |
| ReMAP-PET: Beyond Visual Understanding -- Learning Region-Guided Metabolic Alignment Semantics from Brain PET Dasen Dai, Hongjie Yu, Jagath C. Rajapakse, Qingxin Zhang Published: 2026-06-28Area: cs.CVCitations: - Tags: ai-safety, alignment-training, cscv, preprint | 2026-06-28 | cs.CV | ai-safety, alignment-training, cscv, preprint | E8 / R4 (98%) | - |
| The Joint Effect of Quantization and Sampling Temperature on LLM Safety Alignment: A Factorial Analysis Hari Prasad, Ritam Pal Published: 2026-06-28Area: cs.LGCitations: - Tags: ai-safety, alignment-training, cslg, preprint | 2026-06-28 | cs.LG | ai-safety, alignment-training, cslg, preprint | E10 / R3 (97%) | - |
| Editorial Alignment: A Participatory Approach to Engaging Editorial Expertise in LLM-mediated Knowledge Dissemination Karl-Emil Kj忙r Bilstrup, Kristoffer Laigaard Nielbo, Malthe Stavning Erslev, Simon Aagaard Enni Published: 2026-06-18Area: cs.HCCitations: - Tags: ai-safety, alignment-training, cshc, preprint | 2026-06-18 | cs.HC | ai-safety, alignment-training, cshc, preprint | E7 / R4 (94%) | - |
| Beyond Safe Data: Pretraining-Stage Alignment with Regular Safety Reflection Jinhan Li, Kaifeng Lyu, Kexian Tang, Yihan Xu Published: 2026-06-17Area: cs.AICitations: - Tags: ai-safety, alignment-training, csai, preprint | 2026-06-17 | cs.AI | ai-safety, alignment-training, csai, preprint | E8 / R5 (95%) | - |
| Beyond Tokenization: Direct Timestep Embedding and Contrastive Alignment for Time-Series Question Answering Hung Le, Huu Hiep Nguyen, Thin Nguyen, Yafeng Wu Published: 2026-06-17Area: cs.CLCitations: - Tags: ai-safety, alignment-training, cscl, preprint | 2026-06-17 | cs.CL | ai-safety, alignment-training, cscl, preprint | E7 / R4 (97%) | - |
| Emergent Alignment Martin Kol谩艡 Published: 2026-06-17Area: cs.AICitations: - Tags: ai-safety, alignment-training, csai, preprint | 2026-06-17 | cs.AI | ai-safety, alignment-training, csai, preprint | E8 / R4 (96%) | - |
| G-IdiomAlign: A Gloss-Pivoted Benchmark for Cross-Lingual Idiom Alignment Derek F. Wong, Fengying Ye, Lidia S. Chao, Runzhe Zhan Published: 2026-06-17Area: cs.CLCitations: - Tags: ai-safety, alignment-training, cscl, preprint | 2026-06-17 | cs.CL | ai-safety, alignment-training, cscl, preprint | E9 / R5 (98%) | - |
| Measuring Curriculum Alignment across Topical Coverage, Competency, and Cognitive Depth: A Longitudinal Framework Applied to CS2013 and CS2023 Khaled Shuaib, Mamoun Awad, Mary John, Nazar Zaki Published: 2026-06-17Area: cs.AICitations: - Tags: ai-safety, alignment-training, csai, preprint | 2026-06-17 | cs.AI | ai-safety, alignment-training, csai, preprint | E7 / R4 (94%) | - |
| CAOA -- Completion-Assisted Object-CAD Alignment Balakrishnan Prabhakaran, Hiranya Garbha Kumar, Minhas Kamal Published: 2026-06-16Area: cs.CVCitations: - Tags: ai-safety, alignment-training, cscv, preprint | 2026-06-16 | cs.CV | ai-safety, alignment-training, cscv, preprint | E8 / R5 (98%) | - |
| Plug-and-Adapt: Multimodal Coreference Resolution at First Sight with a Pretrained Alignment Model Ivor W. Tsang, Jinghan Wu, Jing Li, Xuetao Zhang Published: 2026-06-16Area: cs.CVCitations: - Tags: ai-safety, alignment-training, cscv, preprint | 2026-06-16 | cs.CV | ai-safety, alignment-training, cscv, preprint | E7 / R4 (98%) | - |
| See First, Answer Later: Visual Evidence Pre-Alignment via Sufficiency-Driven RL Guoshun Nan, Jiayu Huang, Junyi Zhu, Minghao Sun Published: 2026-06-16Area: cs.CVCitations: - Tags: ai-safety, alignment-training, cscv, preprint | 2026-06-16 | cs.CV | ai-safety, alignment-training, cscv, preprint | E7 / R4 (95%) | - |
| AuAu: A Benchmark for Auditing Authoritarian Alignment in Large Language Models Andreas Einwiller, Florian Lemmerich, Max Klabunde Published: 2026-06-15Area: cs.CLCitations: - Tags: ai-safety, alignment-training, cscl, preprint | 2026-06-15 | cs.CL | ai-safety, alignment-training, cscl, preprint | E7 / R4 (97%) | - |
| Decoupling Semantics from Distortions: Multi-Scale Two-Stream Vision-Language Alignment for AI-Generated Image Quality Assessment Zijie Meng Published: 2026-06-15Area: cs.CVCitations: - Tags: ai-safety, alignment-training, cscv, preprint | 2026-06-15 | cs.CV | ai-safety, alignment-training, cscv, preprint | E9 / R5 (99%) | - |
| Pulling The REINS: Training-Free Safety Alignment of Video Diffusion Models via Representation Steering Amit K. Roy-Chowdhury, Arindam Dutta, Athula Balachandran, Rohit Kundu Published: 2026-06-15Area: cs.CVCitations: - Tags: ai-safety, alignment-training, cscv, preprint | 2026-06-15 | cs.CV | ai-safety, alignment-training, cscv, preprint | E7 / R4 (97%) | - |
| SpecAlign: Efficient Specification-Grounded Alignment of Large Language Models via Synthetic Data Han Bao, Shiyi Du, Wenjie Wang, Xiangliang Zhang Published: 2026-06-15Area: cs.AICitations: - Tags: ai-safety, alignment-training, csai, preprint | 2026-06-15 | cs.AI | ai-safety, alignment-training, csai, preprint | E11 / R7 (99%) | - |
| TuneJury: An Open Metric for Improving Music Generation Preference Alignment Chris Donahue, Haiwen Xia, Junghyun Koo, Junwon Lee Published: 2026-06-15Area: cs.SDCitations: - Tags: ai-safety, alignment-training, cssd, preprint | 2026-06-15 | cs.SD | ai-safety, alignment-training, cssd, preprint | E9 / R5 (99%) | - |
| AP-GRPO: Anchor-Gated Phonetic Alignment with Policy Optimization for Pathological Speech Reconstruction Amir M. Rahmani, Henry Peng Zou, Hoang H Nguyen, Honghui Xu Published: 2026-06-14Area: cs.SDCitations: - Tags: ai-safety, alignment-training, cssd, preprint | 2026-06-14 | cs.SD | ai-safety, alignment-training, cssd, preprint | E10 / R4 (98%) | - |