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 |
|---|---|---|---|---|---|
| A Blind Spot in Alignment: Quantifying Biosecurity Risks in Large Language Models Boyuan Chen, Donghai Hong, He Geng, Jiaming Ji Published: 2026-08-03Area: q-bio.QMCitations: - Tags: ai-safety, alignment-training, preprint, q-bioqm | 2026-08-03 | q-bio.QM | ai-safety, alignment-training, preprint, q-bioqm | E10 / R10 (92%) | - |
| From Profiling to Synthesis: Benchmarking Implicit Behavioral Alignment in Personalized LLM Agents Bobo Li, Haiwen Yi, Hao Fei, Jiajia Song Published: 2026-08-03Area: cs.AICitations: - Tags: ai-safety, alignment-training, csai, preprint | 2026-08-03 | cs.AI | ai-safety, alignment-training, csai, preprint | - | - |
| Separating Decision-Rule Misalignment from Readout-Coverage Limitations in Speech Language Models Baorian Nuchged, Linkai Peng Published: 2026-08-03Area: cs.CLCitations: 37 Tags: ai-safety, alignment-training, cscl, preprint | 2026-08-03 | cs.CL | ai-safety, alignment-training, cscl, preprint | E8 / R5 (91%) | 37 |
| Moving the Safety Barrier: Dynamic Routing Adaptive Alignment Against White-Box Attacks Chao Wu, Cheng Ji, Chuancheng Shi, Fei Shen Published: 2026-08-02Area: cs.CRCitations: - Tags: ai-safety, alignment-training, cscr, preprint | 2026-08-02 | cs.CR | ai-safety, alignment-training, cscr, preprint | E12 / R11 (91%) | - |
| No Single Neuron of Failure: Distributed Safety Alignment Against White-Box Attacks Chuancheng Shi, Fei Shen, Shangze Li, Simiao Xie Published: 2026-08-02Area: cs.AICitations: - Tags: ai-safety, alignment-training, csai, preprint | 2026-08-02 | cs.AI | ai-safety, alignment-training, csai, preprint | - | - |
| Scoring Rules! Statistical and Strategic Alignment for Text Evaluation Metrics Grant Schoenebeck, Jason Hartline, Shengwei Xu, Yifan Wu Published: 2026-08-02Area: cs.AICitations: - Tags: ai-safety, alignment-training, csai, preprint, safety-evaluation | 2026-08-02 | cs.AI | ai-safety, alignment-training, csai, preprint, safety-evaluation | - | - |
| AI Alignment and Fiduciary Obligation Benjamin Lange Published: 2026-08-01Area: cs.CYCitations: - Tags: ai-safety, alignment-training, cscy, preprint | 2026-08-01 | cs.CY | ai-safety, alignment-training, cscy, preprint | E9 / R8 (91%) | - |
| Boosting Generalizable Depth Estimation in Endoscopy by Mixture of Lightweight Experts and Intrinsic Image Alignment Beilei Cui, Changjing Liu, Hongliang Ren, Liangjing Shao Published: 2026-08-01Area: cs.CVCitations: - Tags: ai-safety, alignment-training, cscv, preprint | 2026-08-01 | cs.CV | ai-safety, alignment-training, cscv, preprint | E12 / R11 (94%) | - |
| Adjudicated Captioning: Multi-Agent Alignment Scoring and Consensus-Distilled Beam Arbitration for Strict Zero-Shot Image Captioning Duy Tran Thanh, Long Nguyen-Vu, Ngo Tan Vu Khanh, Thien-Phuc Doan Published: 2026-07-31Area: cs.CVCitations: 29 Tags: ai-safety, alignment-training, cscv, preprint | 2026-07-31 | cs.CV | ai-safety, alignment-training, cscv, preprint | E12 / R10 (92%) | 29 |
| Inference-Time Policy Alignment for Fair Reinforcement Learning Conor Wallace, Peilang Li, Umer Siddique, Yongcan Cao Published: 2026-07-31Area: cs.LGCitations: 15 Tags: ai-safety, alignment-training, cslg, preprint | 2026-07-31 | cs.LG | ai-safety, alignment-training, cslg, preprint | E7 / R6 (92%) | 15 |
| Fragility of Value under Imperfect Alignment Winter Cross Published: 2026-07-30Area: cs.AICitations: - Tags: ai-safety, alignment-training, csai, preprint | 2026-07-30 | cs.AI | ai-safety, alignment-training, csai, preprint | E8 / R5 (90%) | - |
| Fragility of Value under Imperfect Alignment Winter Cross Published: 2026-07-30Area: cs.AICitations: 15 Tags: ai-safety, alignment-training, csai, preprint | 2026-07-30 | cs.AI | ai-safety, alignment-training, csai, preprint | E12 / R8 (88%) | 15 |
| MMLDSum-LLM: Multimodal Long-Document Summarization with Visual-Alignment and Keyword-Aware Chuangchuang Wang, Dongyu Chen, Haonan Lu, Jiahua Yang Published: 2026-07-30Area: cs.AICitations: 15 Tags: ai-safety, alignment-training, csai, preprint | 2026-07-30 | cs.AI | ai-safety, alignment-training, csai, preprint | E10 / R8 (92%) | 15 |
| One Anchor for All: Unified Multilingual and Multimodal Safety Alignment for LVLMs Chuancheng Shi, Enyi Shi, Fei Shen, Jinhui Tang Published: 2026-07-30Area: cs.AICitations: - Tags: ai-safety, alignment-training, csai, preprint | 2026-07-30 | cs.AI | ai-safety, alignment-training, csai, preprint | E11 / R7 (93%) | - |
| PAIChecker: Uncovering and Checking PR-Issue Misalignment in SWE-Bench-Like Benchmarks Junjielong Xu, Manyi Wang, Pinjia He Published: 2026-07-30Area: cs.SECitations: 15 Tags: ai-safety, alignment-training, csse, preprint | 2026-07-30 | cs.SE | ai-safety, alignment-training, csse, preprint | E10 / R9 (94%) | 15 |
| PAIChecker: Uncovering and Checking PR-Issue Misalignment in SWE-Bench-Like Benchmarks Junjielong Xu, Manyi Wang, Pinjia He Published: 2026-07-30Area: cs.SECitations: - Tags: ai-safety, alignment-training, csse, preprint | 2026-07-30 | cs.SE | ai-safety, alignment-training, csse, preprint | E12 / R12 (90%) | - |
| Constitutional Midtraining: Content Presence Drives Alignment Gains Bernie Hogan, Cameron Tice, Desiree Cho, Hunar Batra Published: 2026-07-29Area: cs.CLCitations: - Tags: ai-safety, alignment-training, cscl, preprint | 2026-07-29 | cs.CL | ai-safety, alignment-training, cscl, preprint | E8 / R8 (91%) | - |
| Constitutional Midtraining: Content Presence Drives Alignment Gains Bernie Hogan, Cameron Tice, Desiree Cho, Hunar Batra Published: 2026-07-29Area: cs.CLCitations: - Tags: ai-safety, alignment-training, cscl, preprint | 2026-07-29 | cs.CL | ai-safety, alignment-training, cscl, preprint | E9 / R7 (93%) | - |
| Defending Against Backdoor Attacks via Alignment Checking in Model-Contrastive Federated Learning Guijuan Wang, Hongliang Zhang, Jiguo Yu, Tianqing He Published: 2026-07-29Area: cs.CRCitations: 47 Tags: ai-safety, alignment-training, cscr, preprint | 2026-07-29 | cs.CR | ai-safety, alignment-training, cscr, preprint | E8 / R7 (92%) | 47 |
| Misalignment Has a Personality: A Big Five Account of Emergent Misalignment Hasibur Rahman, Smit Desai Published: 2026-07-29Area: cs.CLCitations: 15 Tags: ai-safety, alignment-training, cscl, preprint | 2026-07-29 | cs.CL | ai-safety, alignment-training, cscl, preprint | E13 / R6 (90%) | 15 |
| On-Policy Distillation for LLM Safety: A Routing Approach to Template-Robust Realignment Lingyu Shen, Sheng Wen, Wanlun Ma, Xi Xiao Published: 2026-07-29Area: cs.AICitations: - Tags: ai-safety, alignment-training, csai, preprint | 2026-07-29 | cs.AI | ai-safety, alignment-training, csai, preprint | - | - |
| Progressive Multimodal Alignment for Continual Instruction Tuning Duzhen Zhang, Jiahua Dong, Qiaoyi Su, Tielin Zhang Published: 2026-07-29Area: cs.CVCitations: - Tags: ai-safety, alignment-training, cscv, preprint | 2026-07-29 | cs.CV | ai-safety, alignment-training, cscv, preprint | E9 / R6 (89%) | - |
| Progressive Multimodal Alignment for Continual Instruction Tuning Duzhen Zhang, Jiahua Dong, Qiaoyi Su, Tielin Zhang Published: 2026-07-29Area: cs.CVCitations: 45 Tags: ai-safety, alignment-training, cscv, preprint | 2026-07-29 | cs.CV | ai-safety, alignment-training, cscv, preprint | E13 / R11 (92%) | 45 |
| SciFigAlign: Scoring Scientific Figures by Fine-tuned Alignment of Visuals with Manuscript Evidence Chengkun Yue, Chuanzhi Xu, Huiqi Liang, Pengfei Ye Published: 2026-07-29Area: cs.CVCitations: - Tags: ai-safety, alignment-training, cscv, preprint | 2026-07-29 | cs.CV | ai-safety, alignment-training, cscv, preprint | - | - |
| Zero-Fi: Zero-Shot Wi-Fi-Based Human Activity Recognition via Contrastive Signal-Language Alignment Cheng Guo, Haopeng Zhang, Hongfei Xue, Jingzhe Zhang Published: 2026-07-29Area: cs.CVCitations: - Tags: ai-safety, alignment-training, cscv, preprint | 2026-07-29 | cs.CV | ai-safety, alignment-training, cscv, preprint | E8 / R6 (90%) | - |
| Even More Deception: Objective Misalignment in Mixed-Motive LLM Multi-Agent Systems Florian Carichon, Golnoosh Farnadi, Margarida Carvalho, Marylou Fauchard Published: 2026-07-28Area: cs.AICitations: - Tags: ai-safety, alignment-training, csai, preprint | 2026-07-28 | cs.AI | ai-safety, alignment-training, csai, preprint | E15 / R12 (93%) | - |
| IRIS: Reusable Identity Representations from Frozen LLMs for Entity Alignment Ge Wang, Shengtao Li, Shouqian Shi, Xinran Liu Published: 2026-07-28Area: cs.CLCitations: - Tags: ai-safety, alignment-training, cscl, preprint | 2026-07-28 | cs.CL | ai-safety, alignment-training, cscl, preprint | - | - |
| Joint Text-Audio Alignment for EEG-to-Text Decoding in Chinese Speech Production and Perception Feng Tian, Tian Zheng, Xiaolan Peng, Xinxin Zhu Published: 2026-07-28Area: cs.AICitations: - Tags: ai-safety, alignment-training, csai, preprint | 2026-07-28 | cs.AI | ai-safety, alignment-training, csai, preprint | - | - |
| Multi-Sensor Alignment for Weather Simulations Aditya Mohan, Devyani Lambhate, Samsad Alam, Vaibhav Katewa Published: 2026-07-28Area: cs.AICitations: - Tags: ai-safety, alignment-training, csai, preprint | 2026-07-28 | cs.AI | ai-safety, alignment-training, csai, preprint | - | - |
| Rashomon Alignment Bernhard Pfahringer, Carlos Soares, Mois茅s Santos, Peter van der Putten Published: 2026-07-28Area: cs.LGCitations: - Tags: ai-safety, alignment-training, cslg, preprint | 2026-07-28 | cs.LG | ai-safety, alignment-training, cslg, preprint | - | - |