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 |
|---|---|---|---|---|---|
| Do LLMs Have Values? A Quantitative Analysis and Alignment Framework for Values in Large Language Models Bing Li, Congyan Lang, Jingyu Chen, Keqing Zhang Published: 2026-09-15Area: cs.AICitations: - Tags: ai-safety, alignment-training, csai, preprint | 2026-09-15 | cs.AI | ai-safety, alignment-training, csai, preprint | - | - |
| Optimal Transport Metric Learning for Feature Alignment in Partially Supervised Segmentation Dakini Mallam Garba, Salim Abdou Daoura Published: 2026-09-15Area: eess.IVCitations: - Tags: ai-safety, alignment-training, eessiv, preprint | 2026-09-15 | eess.IV | ai-safety, alignment-training, eessiv, preprint | E15 / R12 (96%) | - |
| TAME: Token Attribution and Masking for Emergent misalignment Md Rayhanul Masud, Md Rizwan Parvez Published: 2026-09-15Area: cs.LGCitations: - Tags: ai-safety, alignment-training, cslg, preprint | 2026-09-15 | cs.LG | ai-safety, alignment-training, cslg, preprint | - | - |
| Beyond Safe Answers: Segment-Aware Listwise Alignment for Reasoning Safety in Large Reasoning Models Byeonggeuk Lim, Hayeong Ryu, Hoejoon Kwon, Junehyoung Kwon Published: 2026-09-14Area: cs.AICitations: - Tags: ai-safety, alignment-training, csai, preprint | 2026-09-14 | cs.AI | ai-safety, alignment-training, csai, preprint | - | - |
| Delegating Authorization to Misaligned Agents: Coalitional Alignment and Safe Control Aaron Roth, Natalie Collina, Sikata Bela Sengupta, Surbhi Goel Published: 2026-09-14Area: cs.GTCitations: - Tags: ai-safety, alignment-training, csgt, preprint | 2026-09-14 | cs.GT | ai-safety, alignment-training, csgt, preprint | - | - |
| Forty Shades of Blue: Quality-Diversity Alignment via Mode-Conditioned Reinforcement Learning Hangoo Kang, James Jihao Liu, Jiayi Yuan, Liwei Jiang Published: 2026-09-14Area: cs.CLCitations: - Tags: ai-safety, alignment-training, cscl, preprint | 2026-09-14 | cs.CL | ai-safety, alignment-training, cscl, preprint | - | - |
| Shallow Beliefs: Synthetic document finetuning does not inoculate against emergent misalignment from reward hacking Arun Jose, Julian Stastny Published: 2026-09-14Area: cs.AICitations: - Tags: ai-safety, alignment-training, csai, preprint | 2026-09-14 | cs.AI | ai-safety, alignment-training, csai, preprint | - | - |
| Diagnosing Temporal Misalignment in Multichannel Time-Series Classification with Minimum Description Length Daniel Kuhe, Jian-Jia Chen, Michael Frichert, Sebastian Buschj盲ger Published: 2026-09-13Area: cs.LGCitations: - Tags: ai-safety, alignment-training, cslg, preprint | 2026-09-13 | cs.LG | ai-safety, alignment-training, cslg, preprint | - | - |
| One Model, Two Physical Stories: Auditing Misalignment in Multi-Modal World Modeling Geigh Zollicoffer, Manish Bhattarai, Minh Vu, Rajiv Ranasinghe Published: 2026-09-13Area: cs.AICitations: - Tags: ai-safety, alignment-training, csai, preprint | 2026-09-13 | cs.AI | ai-safety, alignment-training, csai, preprint | - | - |
| Direct Preference Density Alignment for Conversational Audio Equalization Ioannis Stylianou, Jon Francombe, Pablo Martinez Nuevo, Sven Ewan Shepstone Published: 2026-09-11Area: cs.SDCitations: - Tags: ai-safety, alignment-training, cssd, preprint | 2026-09-11 | cs.SD | ai-safety, alignment-training, cssd, preprint | E8 / R8 (92%) | - |
| Toward Robust Personalized Alignment for LLMs: Mitigating Persona Drift in Multi-Turn Dialogue Fangming Liu, Jing Li, Siyuan Li, Youyuan Zhang Published: 2026-09-11Area: cs.AICitations: - Tags: ai-safety, alignment-training, csai, preprint | 2026-09-11 | cs.AI | ai-safety, alignment-training, csai, preprint | E14 / R13 (93%) | - |
| UFO: Chain-of-Evaluation for Omni-Condition Alignment in Multi-Modal Image Generation Danning Zhang, Mengqi Huang, Shancheng Fang, Shaojin Wu Published: 2026-09-11Area: cs.CVCitations: - Tags: ai-safety, alignment-training, cscv, preprint, safety-evaluation | 2026-09-11 | cs.CV | ai-safety, alignment-training, cscv, preprint, safety-evaluation | E10 / R7 (93%) | - |
| Artificial Id: Drive and Persistent Alignment in Agentic AI Yakov Pyotr Shkolnikov Published: 2026-09-10Area: cs.AICitations: - Tags: ai-safety, alignment-training, csai, preprint | 2026-09-10 | cs.AI | ai-safety, alignment-training, csai, preprint | E6 / R6 (93%) | - |
| Autonomy, Social Norms, and Alignment: Towards a Developmental Framework for Autonomous Artificial Agents Ludovica Marinucci, Marica Notte, Vieri Giuliano Santucci Published: 2026-09-10Area: cs.AICitations: 15 Tags: ai-safety, alignment-training, csai, preprint | 2026-09-10 | cs.AI | ai-safety, alignment-training, csai, preprint | E8 / R6 (93%) | 15 |
| Off-Target Effects of Response-Style Alignment in a Korean 27B Language Model Hyojung Han Published: 2026-09-10Area: cs.AICitations: 51 Tags: ai-safety, alignment-training, csai, preprint | 2026-09-10 | cs.AI | ai-safety, alignment-training, csai, preprint | E8 / R7 (91%) | 51 |
| Off-Target Effects of Response-Style Alignment in a Korean 27B Language Model Hyojung Han Published: 2026-09-10Area: cs.AICitations: - Tags: ai-safety, alignment-training, csai, preprint | 2026-09-10 | cs.AI | ai-safety, alignment-training, csai, preprint | E9 / R6 (92%) | - |
| Beyond Surface Imitation: Contrastive Modeling for Reasoning Path Alignment in Multimodal In-Context Learning Mingbo Yang, Peng Chen, Sunshang Wang, Wenqiang Wang Published: 2026-09-09Area: cs.AICitations: - Tags: ai-safety, alignment-training, csai, preprint | 2026-09-09 | cs.AI | ai-safety, alignment-training, csai, preprint | E12 / R7 (91%) | - |
| Compact Visuotactile World Models for Lifting: Prediction, Reward Alignment, and Force Constraints Qinzhen Ma Published: 2026-09-09Area: cs.ROCitations: - Tags: ai-safety, alignment-training, csro, preprint | 2026-09-09 | cs.RO | ai-safety, alignment-training, csro, preprint | E9 / R5 (95%) | - |
| Compact Visuotactile World Models for Lifting: Prediction, Reward Alignment, and Force Constraints Qinzhen Ma, Sida Peng Published: 2026-09-09Area: cs.ROCitations: 10 Tags: ai-safety, alignment-training, csro, preprint | 2026-09-09 | cs.RO | ai-safety, alignment-training, csro, preprint | E9 / R7 (94%) | 10 |
| FlowCPO: A Unified Divergence View of Preference Alignment for Flow Models Deyuan Liu, Pengfei Wan, Peng Sun, Shengyi Liao Published: 2026-09-09Area: stat.MLCitations: - Tags: ai-safety, alignment-training, preprint, statml | 2026-09-09 | stat.ML | ai-safety, alignment-training, preprint, statml | E14 / R11 (94%) | - |
| How Fragile Is Safety Alignment at Frontier Scale? A Single-Direction Attack on a 320B MoE Kai Shen, Tanyu Chen, Yi Shi Published: 2026-09-09Area: cs.CRCitations: - Tags: ai-safety, alignment-training, cscr, preprint | 2026-09-09 | cs.CR | ai-safety, alignment-training, cscr, preprint | E10 / R11 (91%) | - |
| MOONWALK: Mediating Operations with Intent-Evidence-Action Alignment Across Junior-Supervisor Review Workflows in Animation/VFX Pre-Production Bing-Yu Chen, Sai Ling, Shaune Jan, Shih-Yu Lai Published: 2026-09-09Area: cs.HCCitations: - Tags: ai-safety, alignment-training, cshc, preprint | 2026-09-09 | cs.HC | ai-safety, alignment-training, cshc, preprint | E10 / R7 (93%) | - |
| PRAGMA: Evaluating Personalized Guidance with Memory Alignment in Lifelong Conversations Hyojeong Yu, Hyukhun Koh, Kyomin Jung, Minsung Kim Published: 2026-09-09Area: cs.AICitations: 15 Tags: ai-safety, alignment-training, csai, preprint | 2026-09-09 | cs.AI | ai-safety, alignment-training, csai, preprint | E12 / R12 (93%) | 15 |
| Bridging the Semantic-Utility Gap in Multimodal RAG via Generator-in-the-Loop Alignment Christopher G. Brinton, Dong-Jun Han, Mung Chiang, Seyyedali Hosseinalipour Published: 2026-09-08Area: cs.AICitations: - Tags: ai-safety, alignment-training, csai, preprint | 2026-09-08 | cs.AI | ai-safety, alignment-training, csai, preprint | E13 / R10 (96%) | - |
| Does Deeper Reasoning Compromise Alignment? Revealing and Mitigating of Alignment Collapse in Large Reasoning Models Bairui Zhang, Henghua Zhang, Jia-Chen Zhang, Shaohua Li Published: 2026-09-08Area: cs.AICitations: - Tags: ai-safety, alignment-training, csai, preprint | 2026-09-08 | cs.AI | ai-safety, alignment-training, csai, preprint | E8 / R5 (95%) | - |
| Everything in Moderation: Per-Domain Coverage Optima and Alignment-Resistant Domain Gaps in Multi-Domain Mid-Training Kun Zheng, Yunpeng Xu Published: 2026-09-08Area: cs.AICitations: - Tags: ai-safety, alignment-training, csai, preprint | 2026-09-08 | cs.AI | ai-safety, alignment-training, csai, preprint | E12 / R10 (91%) | - |
| Inference-Time Nash Alignment Debmalya Mandal, Duohan Zhang, Hadi Hosseini Published: 2026-09-08Area: cs.AICitations: 45 Tags: ai-safety, alignment-training, csai, preprint | 2026-09-08 | cs.AI | ai-safety, alignment-training, csai, preprint | E12 / R12 (93%) | 45 |
| Suan: Rectifying Direct Preference Safety Alignment in Large Language Models Oleksandr Cherednichenko, Roman Klypa Published: 2026-09-08Area: cs.LGCitations: - Tags: ai-safety, alignment-training, cslg, preprint | 2026-09-08 | cs.LG | ai-safety, alignment-training, cslg, preprint | E13 / R10 (93%) | - |
| Beyond Sparse Rewards: A New Benchmark and Structure-Aware Graph Alignment for Micro-Drama Understanding Jinwen Luo, Shi-Zhe Chen, Siyuan Cheng, Tao Cheng Published: 2026-09-07Area: cs.AICitations: 15 Tags: ai-safety, alignment-training, csai, preprint | 2026-09-07 | cs.AI | ai-safety, alignment-training, csai, preprint | E17 / R10 (90%) | 15 |
| Norms at a Price: Why RL-Based Alignment Can Promise Conditional Compliance at Best Felix Jahn, Kevin Baum, R奴ta Binkyt臈 Published: 2026-09-07Area: cs.AICitations: - Tags: ai-safety, alignment-training, csai, preprint | 2026-09-07 | cs.AI | ai-safety, alignment-training, csai, preprint | E10 / R7 (95%) | - |