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 |
|---|---|---|---|---|---|
| Toward Executable Repository-Level Code Generation via Environment Alignment Hongyu Zhang, Junlei Shen, Linhao Wu, Lu Zhang Published: 2026-04-04Area: cs.SECitations: - Tags: ai-safety, alignment-training, csse, preprint | 2026-04-04 | cs.SE | ai-safety, alignment-training, csse, preprint | E5 / R3 (96%) | - |
| APPA: Adaptive Preference Pluralistic Alignment for Fair Federated RLHF of LLMs Mahmoud Srewa, Salma Elmalaki, Tianyu Zhao Published: 2026-04-05Area: cs.LGCitations: - Tags: ai-safety, alignment-training, cslg, preprint | 2026-04-05 | cs.LG | ai-safety, alignment-training, cslg, preprint | E8 / R4 (95%) | - |
| FreakOut-LLM: The Effect of Emotional Stimuli on Safety Alignment Asaf Shabtai, Daniel Kuznetsov, Karin Shistik, Ofir Cohen Published: 2026-04-05Area: cs.CRCitations: - Tags: ai-safety, alignment-training, cscr, preprint | 2026-04-05 | cs.CR | ai-safety, alignment-training, cscr, preprint | E5 / R3 (96%) | - |
| How Alignment Routes: Localizing, Scaling, and Controlling Policy Circuits in Language Models Gregory N. Frank Published: 2026-04-06Area: cs.CLCitations: - Tags: ai-safety, alignment-training, cscl, preprint | 2026-04-06 | cs.CL | ai-safety, alignment-training, cscl, preprint | E6 / R3 (94%) | - |
| Relative Density Ratio Optimization for Stable and Statistically Consistent Model Alignment Atsutoshi Kumagai, Hiroshi Takahashi, Kazutoshi Shinoda, Kosuke Nishida Published: 2026-04-06Area: cs.LGCitations: - Tags: ai-safety, alignment-training, cslg, preprint | 2026-04-06 | cs.LG | ai-safety, alignment-training, cslg, preprint | E5 / R3 (94%) | - |
| Beyond Compromise: Pareto-Lenient Consensus for Efficient Multi-Preference LLM Alignment Honggang Zhang, Renxuan Tan, Rongpeng Li, Zhifeng Zhao Published: 2026-04-07Area: cs.AICitations: - Tags: ai-safety, alignment-training, csai, preprint | 2026-04-07 | cs.AI | ai-safety, alignment-training, csai, preprint | E5 / R3 (95%) | - |
| Simulating the Evolution of Alignment and Values in Machine Intelligence Jonathan Elsworth Eicher Published: 2026-04-07Area: cs.AICitations: - Tags: ai-safety, alignment-training, csai, preprint | 2026-04-07 | cs.AI | ai-safety, alignment-training, csai, preprint | E5 / R3 (93%) | - |
| The Master Key Hypothesis: Unlocking Cross-Model Capability Transfer via Linear Subspace Alignment Anjie Fang, Fardin Abdi, Mohit Bansal, Pin-Jie Lin Published: 2026-04-07Area: cs.LGCitations: - Tags: ai-safety, alignment-training, cslg, preprint | 2026-04-07 | cs.LG | ai-safety, alignment-training, cslg, preprint | E5 / R3 (96%) | - |
| FVD: Inference-Time Alignment of Diffusion Models via Fleming-Viot Resampling Jia Yi Zhang, Sagnik Mukherjee, Shivanshu Shekhar, Tong Zhang Published: 2026-04-08Area: cs.AICitations: - Tags: ai-safety, alignment-training, csai, preprint | 2026-04-08 | cs.AI | ai-safety, alignment-training, csai, preprint | E5 / R3 (95%) | - |
| Information as Structural Alignment: A Dynamical Theory of Continual Learning Radu Negulescu Published: 2026-04-08Area: cs.LGCitations: - Tags: ai-safety, alignment-training, cslg, preprint | 2026-04-08 | cs.LG | ai-safety, alignment-training, cslg, preprint | E5 / R2 (97%) | - |
| Multi-Faceted Self-Consistent Preference Alignment for Query Rewriting in Conversational Search Peifeng Li, Qiaoming Zhu, Zhiyu Cao Published: 2026-04-08Area: cs.CLCitations: - Tags: ai-safety, alignment-training, cscl, preprint | 2026-04-08 | cs.CL | ai-safety, alignment-training, cscl, preprint | E5 / R3 (98%) | - |
| Towards Privacy-Preserving Large Language Model: Text-free Inference Through Alignment and Adaptation Chanhee Park, Heuiseok Lim, Hyeonseok Moon, Jeongho Yoon Published: 2026-04-08Area: cs.CRCitations: - Tags: ai-safety, alignment-training, cscr, preprint | 2026-04-08 | cs.CR | ai-safety, alignment-training, cscr, preprint | E5 / R3 (95%) | - |
| Cards Against LLMs: Benchmarking Humor Alignment in Large Language Models Guillaume Bied, Hannu Toivonen, Tijl De Bie, Yousra Fettach Published: 2026-04-09Area: cs.CLCitations: - Tags: ai-safety, alignment-training, cscl, preprint | 2026-04-09 | cs.CL | ai-safety, alignment-training, cscl, preprint | E6 / R5 (98%) | - |
| DSCA: Dynamic Subspace Concept Alignment for Lifelong VLM Editing Gyanendra Das, Sai Satyam Jena Published: 2026-04-09Area: cs.CVCitations: - Tags: ai-safety, alignment-training, cscv, preprint | 2026-04-09 | cs.CV | ai-safety, alignment-training, cscv, preprint | E4 / R3 (95%) | - |
| Lessons Without Borders? Evaluating Cultural Alignment of LLMs Using Multilingual Story Moral Generation Andrew Piper, Sophie Wu Published: 2026-04-09Area: cs.CLCitations: - Tags: ai-safety, alignment-training, cscl, preprint | 2026-04-09 | cs.CL | ai-safety, alignment-training, cscl, preprint | E6 / R3 (96%) | - |
| Multi-Modal Learning meets Genetic Programming: Analyzing Alignment in Latent Space Optimization Benjamin L茅ger, Christian Gagn茅, Kazem Meidani Published: 2026-04-09Area: cs.NECitations: - Tags: ai-safety, alignment-training, csne, preprint | 2026-04-09 | cs.NE | ai-safety, alignment-training, csne, preprint | E6 / R3 (97%) | - |
| Multi-Modal Learning meets Genetic Programming: Analyzing Alignment in Latent Space Optimization Benjamin L茅ger, Christian Gagn茅, Kazem Meidani Published: 2026-04-09Area: cs.NECitations: - Tags: ai-safety, alignment-training, csne, preprint | 2026-04-09 | cs.NE | ai-safety, alignment-training, csne, preprint | E5 / R3 (96%) | - |
| ProMedical: Hierarchical Fine-Grained Criteria Modeling for Medical LLM Alignment via Explicit Injection He Geng, Hui Chu, Jiaxue Hu, Lixian Lai Published: 2026-04-09Area: cs.AICitations: - Tags: ai-safety, alignment-training, csai, preprint | 2026-04-09 | cs.AI | ai-safety, alignment-training, csai, preprint | E6 / R4 (96%) | - |
| SPARD: Self-Paced Curriculum for RL Alignment via Integrating Reward Dynamics and Data Utility Chengqiang Lu, Defu Lian, Enhong Chen, Hang Lv Published: 2026-04-09Area: cs.AICitations: - Tags: ai-safety, alignment-training, csai, preprint | 2026-04-09 | cs.AI | ai-safety, alignment-training, csai, preprint | E6 / R4 (97%) | - |
| TASU2: Controllable CTC Simulation for Alignment and Low-Resource Adaptation of Speech LLMs Chenghao Wang, Jing Peng, Junjie Li, Kai Yu Published: 2026-04-09Area: eess.ASCitations: - Tags: ai-safety, alignment-training, eessas, preprint | 2026-04-09 | eess.AS | ai-safety, alignment-training, eessas, preprint | E5 / R3 (94%) | - |
| Frequency-Enhanced Diffusion Models: Curriculum-Guided Semantic Alignment for Zero-Shot Skeleton Action Recognition Jingyu Pan, Yuxi Zhou, Zhengbo Zhang, Zhigang Tu Published: 2026-04-10Area: cs.CVCitations: - Tags: ai-safety, alignment-training, cscv, preprint | 2026-04-10 | cs.CV | ai-safety, alignment-training, cscv, preprint | E5 / R3 (96%) | - |
| PerMix-RLVR: Preserving Persona Expressivity under Verifiable-Reward Alignment Jihwan Oh, Minchan Jeong, Murad Aghazada, Se-Young Yun Published: 2026-04-10Area: cs.CLCitations: - Tags: ai-safety, alignment-training, cscl, preprint | 2026-04-10 | cs.CL | ai-safety, alignment-training, cscl, preprint | E5 / R3 (95%) | - |
| Semantic Rate-Distortion for Bounded Multi-Agent Communication: Capacity-Derived Semantic Spaces and the Communication Cost of Alignment Anthony T. Nixon Published: 2026-04-10Area: cs.ITCitations: - Tags: ai-safety, alignment-training, csit, preprint | 2026-04-10 | cs.IT | ai-safety, alignment-training, csit, preprint | E5 / R3 (95%) | - |
| CoSToM:Causal-oriented Steering for Intrinsic Theory-of-Mind Alignment in Large Language Models Mengfan Li, Xuanhua Shi, Yang Deng Published: 2026-04-11Area: cs.CLCitations: - Tags: ai-safety, alignment-training, cscl, preprint | 2026-04-11 | cs.CL | ai-safety, alignment-training, cscl, preprint | E5 / R3 (95%) | - |
| Computational Lesions in Multilingual Language Models Separate Shared and Language-specific Brain Alignment Chengqing Zong, Goran Nenadic, Hongpeng Zhou, Jingyuan Sun Published: 2026-04-12Area: cs.CLCitations: - Tags: ai-safety, alignment-training, cscl, preprint | 2026-04-12 | cs.CL | ai-safety, alignment-training, cscl, preprint | E5 / R3 (94%) | - |
| Principles Do Not Apply Themselves: A Hermeneutic Perspective on AI Alignment Behrooz Razeghi Published: 2026-04-12Area: cs.AICitations: - Tags: ai-safety, alignment-training, csai, preprint | 2026-04-12 | cs.AI | ai-safety, alignment-training, csai, preprint | E5 / R3 (94%) | - |
| Do LLMs Know Tool Irrelevance? Demystifying Structural Alignment Bias in Tool Invocations Fang Fang, Ge Zhang, Pengfei Cao, Xixun Lin Published: 2026-04-13Area: cs.CLCitations: - Tags: ai-safety, alignment-training, cscl, preprint | 2026-04-13 | cs.CL | ai-safety, alignment-training, cscl, preprint | E4 / R3 (96%) | - |
| LASA: Language-Agnostic Semantic Alignment at the Semantic Bottleneck for LLM Safety Han Qiu, Haoran Liu, Hongning Wang, Hui Xue Published: 2026-04-13Area: cs.LGCitations: - Tags: ai-safety, alignment-training, cslg, preprint | 2026-04-13 | cs.LG | ai-safety, alignment-training, cslg, preprint | E5 / R3 (99%) | - |
| Narrative over Numbers: The Identifiable Victim Effect and its Amplification Under Alignment and Reasoning in Large Language Models Syed Rifat Raiyan Published: 2026-04-13Area: cs.CLCitations: - Tags: ai-safety, alignment-training, cscl, preprint | 2026-04-13 | cs.CL | ai-safety, alignment-training, cscl, preprint | E5 / R3 (95%) | - |
| OOM-RL: Out-of-Money Reinforcement Learning Market-Driven Alignment for LLM-Based Multi-Agent Systems Kun Liu, Liqun Chen Published: 2026-04-13Area: cs.AICitations: - Tags: ai-safety, alignment-training, csai, preprint | 2026-04-13 | cs.AI | ai-safety, alignment-training, csai, preprint | E5 / R4 (96%) | - |