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 |
|---|---|---|---|---|---|
| FedRot-LoRA: Mitigating Rotational Misalignment in Federated LoRA Dongjun Kim, Haoran Zhang, Haris Vikalo, Seohyeon Cha Published: 2026-02-27Area: cs.LGCitations: 15 Tags: ai-safety, alignment-training, cslg, preprint | 2026-02-27 | cs.LG | ai-safety, alignment-training, cslg, preprint | E13 / R8 (88%) | 15 |
| Hyperdimensional Cross-Modal Alignment of Frozen Language and Image Models for Efficient Image Captioning Abhishek Dalvi, Vasant Honavar Published: 2026-02-27Area: cs.CVCitations: - Tags: ai-safety, alignment-training, cscv, preprint | 2026-02-27 | cs.CV | ai-safety, alignment-training, cscv, preprint | E9 / R8 (91%) | - |
| A Holistic Framework for Robust Bangla ASR and Speaker Diarization with Optimized VAD and CTC Alignment Md. Ishtiak Moin, Shafnan Wasif, Zarif Ishmam, Zarif Mahir Published: 2026-02-26Area: cs.SDCitations: 14 Tags: ai-safety, alignment-training, cssd, preprint | 2026-02-26 | cs.SD | ai-safety, alignment-training, cssd, preprint | E11 / R7 (91%) | 14 |
| AMLRIS: Alignment-aware Masked Learning for Referring Image Segmentation Baochang Zhang, Changbai Li, Chunyu Xie, Dawei Leng Published: 2026-02-26Area: cs.CVCitations: 15 Tags: ai-safety, alignment-training, cscv, preprint | 2026-02-26 | cs.CV | ai-safety, alignment-training, cscv, preprint | E7 / R6 (94%) | 15 |
| Make It Hard to Hear, Easy to Learn: Long-Form Bengali ASR and Speaker Diarization via Extreme Augmentation and Perfect Alignment A H M Fuad, Bayazid Hasan, Risalat Labib, Sanjid Hasan Published: 2026-02-26Area: cs.SDCitations: 8 Tags: ai-safety, alignment-training, cssd, preprint | 2026-02-26 | cs.SD | ai-safety, alignment-training, cssd, preprint | E19 / R10 (91%) | 8 |
| Modeling Expert AI Diagnostic Alignment via Immutable Inference Snapshots Dimitrios P. Panagoulias, Evangelia-Aikaterini Tsichrintzi, Evridiki Tsoureli-Nikita, Georgios Savvidis Published: 2026-02-26Area: cs.AICitations: 28 Tags: ai-safety, alignment-training, csai, preprint | 2026-02-26 | cs.AI | ai-safety, alignment-training, csai, preprint | E10 / R9 (91%) | 28 |
| PATRA: Pattern-Aware Alignment and Balanced Reasoning for Time Series Question Answering Bin Yang, Chenjuan Guo, Christian S. Jensen, Junkai Lu Published: 2026-02-26Area: cs.AICitations: - Tags: ai-safety, alignment-training, csai, preprint | 2026-02-26 | cs.AI | ai-safety, alignment-training, csai, preprint | E10 / R7 (90%) | - |
| SOTAlign: Semi-Supervised Alignment of Unimodal Vision and Language Models via Optimal Transport Paul Krzakala, Quentin Bouniot, Simon Roschmann, Sonia Mazelet Published: 2026-02-26Area: cs.LGCitations: 15 Tags: ai-safety, alignment-training, cslg, preprint | 2026-02-26 | cs.LG | ai-safety, alignment-training, cslg, preprint | E13 / R9 (87%) | 15 |
| Towards LLM-Empowered Knowledge Tracing via LLM-Student Hierarchical Behavior Alignment in Hyperbolic Space Chunpei Li, Dongran Yu, Qingyun Sun, Shengpeng Wang Published: 2026-02-26Area: cs.AICitations: - Tags: ai-safety, alignment-training, csai, preprint | 2026-02-26 | cs.AI | ai-safety, alignment-training, csai, preprint | E9 / R10 (90%) | - |
| Enhancing Multilingual Embeddings via Multi-Way Parallel Text Alignment Barah Fazili, Koustava Goswami Published: 2026-02-25Area: cs.CLCitations: - Tags: ai-safety, alignment-training, cscl, preprint | 2026-02-25 | cs.CL | ai-safety, alignment-training, cscl, preprint | E17 / R16 (95%) | - |
| Provable Last-Iterate Convergence for Multi-Objective Safe LLM Alignment via Optimistic Primal-Dual Ness Shroff, Peizhong Ju, Yining Li Published: 2026-02-25Area: cs.LGCitations: - Tags: ai-safety, alignment-training, cslg, preprint | 2026-02-25 | cs.LG | ai-safety, alignment-training, cslg, preprint | E6 / R5 (93%) | - |
| StoryMovie: A Dataset for Semantic Alignment of Visual Stories with Movie Scripts and Subtitles Daniel Oliveira, David Martins de Matos Published: 2026-02-25Area: cs.CVCitations: 15 Tags: ai-safety, alignment-training, cscv, preprint | 2026-02-25 | cs.CV | ai-safety, alignment-training, cscv, preprint | E9 / R6 (93%) | 15 |
| Alignment-Weighted DPO: A principled reasoning approach to improve safety alignment Alfy Samuel, Anoop Kumar, Daben Liu, Mengxuan Hu Published: 2026-02-24Area: cs.CLCitations: 45 Tags: ai-safety, alignment-training, cscl, preprint | 2026-02-24 | cs.CL | ai-safety, alignment-training, cscl, preprint | E6 / R5 (91%) | 45 |
| ERA: Evidence-based Reliability Alignment for Honest Retrieval-Augmented Generation Byung-Jun Lee, Meeyoung Cha, Sunguk Shin, Sungwon Park Published: 2026-02-24Area: cs.IRCitations: - Tags: ai-safety, alignment-training, csir, preprint | 2026-02-24 | cs.IR | ai-safety, alignment-training, csir, preprint | E8 / R7 (91%) | - |
| Pressure Reveals Character: Behavioural Alignment Evaluation at Depth John Burden, Nora Petrova Published: 2026-02-24Area: cs.AICitations: 15 Tags: ai-safety, alignment-training, csai, preprint, safety-evaluation | 2026-02-24 | cs.AI | ai-safety, alignment-training, csai, preprint, safety-evaluation | E18 / R12 (94%) | 15 |
| CTC-TTS: LLM-based dual-streaming text-to-speech with CTC alignment Hanwen Liu, Hao Huang, Saierdaer Yusuyin, Zhijian Ou Published: 2026-02-23Area: eess.ASCitations: - Tags: ai-safety, alignment-training, eessas, preprint | 2026-02-23 | eess.AS | ai-safety, alignment-training, eessas, preprint | E15 / R14 (90%) | - |
| GOAL: Geometrically Optimal Alignment for Continual Generalized Category Discovery Chenhao Ding, Jizhou Han, Qiang Wang, Shaokun Wang Published: 2026-02-23Area: cs.CVCitations: 1 Tags: ai-safety, alignment-training, cscv, preprint | 2026-02-23 | cs.CV | ai-safety, alignment-training, cscv, preprint | E9 / R8 (90%) | 1 |
| Thought Virus: Viral Misalignment via Subliminal Prompting in Multi-Agent Systems Ben Hagag, Jonas M眉ller, Michael Mulet, Moritz Weckbecker Published: 2026-02-23Area: cs.MACitations: - Tags: ai-safety, alignment-training, csma, preprint | 2026-02-23 | cs.MA | ai-safety, alignment-training, csma, preprint | E10 / R8 (88%) | - |
| Time Series, Vision, and Language: Exploring the Limits of Alignment in Contrastive Representation Spaces Pratham Yashwante, Rose Yu Published: 2026-02-22Area: cs.AICitations: 15 Tags: ai-safety, alignment-training, csai, preprint | 2026-02-22 | cs.AI | ai-safety, alignment-training, csai, preprint | E9 / R6 (93%) | 15 |
| MiSCHiEF: A Benchmark in Minimal-Pairs of Safety and Culture for Holistic Evaluation of Fine-Grained Image-Caption Alignment Advait Swaminathan, Kevin Zhu, Nguyen Dao Minh Anh, Sagarika Banerjee Published: 2026-02-21Area: cs.CVCitations: 45 Tags: ai-safety, alignment-training, cscv, preprint, safety-evaluation | 2026-02-21 | cs.CV | ai-safety, alignment-training, cscv, preprint, safety-evaluation | E15 / R9 (90%) | 45 |
| Synthesizing Multimodal Geometry Datasets from Scratch and Enabling Visual Alignment via Plotting Code Binhang Yuan, Bohan Zeng, Chen Chen, Haobo Lin Published: 2026-02-21Area: cs.CVCitations: - Tags: ai-safety, alignment-training, cscv, preprint | 2026-02-21 | cs.CV | ai-safety, alignment-training, cscv, preprint | E5 / R5 (91%) | - |
| Alignment in Time: Peak-Aware Orchestration for Long-Horizon Agentic Systems Dominic DiFranzo, Hanjing Shi Published: 2026-02-20Area: cs.AICitations: 15 Tags: ai-safety, alignment-training, csai, preprint | 2026-02-20 | cs.AI | ai-safety, alignment-training, csai, preprint | E8 / R6 (89%) | 15 |
| Hierarchical Reward Design from Language: Enhancing Alignment of Agent Behavior with Human Specifications Ryan Diaz, Sangwon Seo, Vaibhav Unhelkar, Zhiqin Qian Published: 2026-02-20Area: cs.AICitations: - Tags: ai-safety, alignment-training, csai, preprint | 2026-02-20 | cs.AI | ai-safety, alignment-training, csai, preprint | E9 / R7 (93%) | - |
| ROCKET: Residual-Oriented Multi-Layer Alignment for Spatially-Aware Vision-Language-Action Models Ang Li, Chenxiang Luo, Guoheng Sun, Kaixi Feng Published: 2026-02-20Area: cs.CVCitations: - Tags: ai-safety, alignment-training, cscv, preprint | 2026-02-20 | cs.CV | ai-safety, alignment-training, cscv, preprint | E9 / R6 (91%) | - |
| Federated Latent Space Alignment for Multi-user Semantic Communications Emilio Calvanese Strinati, Giuseppe Di Poce, Mario Edoardo Pandolfo, Paolo Di Lorenzo Published: 2026-02-19Area: cs.ITCitations: - Tags: ai-safety, alignment-training, csit, preprint | 2026-02-19 | cs.IT | ai-safety, alignment-training, csit, preprint | E11 / R8 (96%) | - |
| FLoRG: Federated Fine-tuning with Low-rank Gram Matrices and Procrustes Alignment Chuiyang Meng, Ming Tang, Vincent W. S. Wong Published: 2026-02-19Area: cs.LGCitations: 15 Tags: ai-safety, alignment-training, cslg, preprint | 2026-02-19 | cs.LG | ai-safety, alignment-training, cslg, preprint | E11 / R11 (91%) | 15 |
| ODESteer: A Unified ODE-Based Steering Framework for LLM Alignment Haosen Sun, Hongjue Zhao, Huajie Shao, Jiangtao Kong Published: 2026-02-19Area: cs.AICitations: - Tags: ai-safety, alignment-training, csai, preprint | 2026-02-19 | cs.AI | ai-safety, alignment-training, csai, preprint | E10 / R8 (92%) | - |
| Align Once, Benefit Multilingually: Enforcing Multilingual Consistency for LLM Safety Alignment Juntao Dai, Xiaohao Liu, Yaodong Yang, Yuyan Bu Published: 2026-02-18Area: cs.CLCitations: 1 Tags: ai-safety, alignment-training, cscl, preprint | 2026-02-18 | cs.CL | ai-safety, alignment-training, cscl, preprint | E10 / R7 (92%) | 1 |
| Intra-Fairness Dynamics: The Bias Spillover Effect in Targeted LLM Alignment Eva Paraschou, Line Harder Clemmensen, Sneha Das Published: 2026-02-18Area: cs.LGCitations: - Tags: ai-safety, alignment-training, cslg, preprint | 2026-02-18 | cs.LG | ai-safety, alignment-training, cslg, preprint | E11 / R10 (95%) | - |
| Narrow Fine-Tuning Erodes Safety Alignment in Vision-Language Agents Idhant Gulati, Shivam Raval Published: 2026-02-18Area: cs.AICitations: 15 Tags: ai-safety, alignment-training, csai, preprint | 2026-02-18 | cs.AI | ai-safety, alignment-training, csai, preprint | E8 / R6 (92%) | 15 |