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 |
|---|---|---|---|---|---|
| HEALing Entropy Collapse: Enhancing Exploration in Few-Shot RLVR via Hybrid-Domain Entropy Dynamics Alignment Ante Wang, Chenqing Liu, Delai Qiu, Hui Li Published: 2026-04-20Area: cs.LGCitations: - Tags: ai-safety, alignment-training, cslg, preprint | 2026-04-20 | cs.LG | ai-safety, alignment-training, cslg, preprint | E8 / R5 (98%) | - |
| REVEAL: Multimodal Vision-Language Alignment of Retinal Morphometry and Clinical Risks for Incident AD and Dementia Prediction Chenyu You, Kuang Gong, Lin Gu, Ruogu Fang Published: 2026-04-20Area: cs.CVCitations: - Tags: ai-safety, alignment-training, cscv, preprint | 2026-04-20 | cs.CV | ai-safety, alignment-training, cscv, preprint | E10 / R7 (100%) | - |
| The Triadic Loop: A Framework for Negotiating Alignment in AI Co-hosted Livestreaming Aneesha Singh, Katherine Wang, Nadia Berthouze Published: 2026-04-20Area: cs.HCCitations: - Tags: ai-safety, alignment-training, cshc, preprint | 2026-04-20 | cs.HC | ai-safety, alignment-training, cshc, preprint | E10 / R5 (98%) | - |
| Cat-DPO: Category-Adaptive Safety Alignment Kaize Ding, Ruiyao Xu, Tiankai Yang, Xinyuan Li Published: 2026-04-19Area: cs.CLCitations: - Tags: ai-safety, alignment-training, cscl, preprint | 2026-04-19 | cs.CL | ai-safety, alignment-training, cscl, preprint | E8 / R4 (98%) | - |
| Cat-DPO: Category-Adaptive Safety Alignment Kaize Ding, Ruiyao Xu, Tiankai Yang, Xinyuan Li Published: 2026-04-19Area: cs.CLCitations: - Tags: ai-safety, alignment-training, cscl, preprint | 2026-04-19 | cs.CL | ai-safety, alignment-training, cscl, preprint | E8 / R0 (100%) | - |
| Demystifying the unreasonable effectiveness of online alignment methods Enoch Hyunwook Kang Published: 2026-04-19Area: cs.LGCitations: - Tags: ai-safety, alignment-training, cslg, preprint | 2026-04-19 | cs.LG | ai-safety, alignment-training, cslg, preprint | E6 / R3 (97%) | - |
| Alignment Imprint: Zero-Shot AI-Generated Text Detection via Provable Preference Discrepancy Bin Chen, Changliang Zou, Dongjian Hu, Hao Wu Published: 2026-04-18Area: cs.AICitations: - Tags: ai-safety, alignment-training, csai, preprint | 2026-04-18 | cs.AI | ai-safety, alignment-training, csai, preprint | E8 / R4 (99%) | - |
| Training-inference input alignment outweighs framework choice in longitudinal retinal image prediction Jason I. Comander, Liyin Chen, Mengyu Wang, Nazlee Zebardast Published: 2026-04-18Area: cs.CVCitations: - Tags: ai-safety, alignment-training, cscv, preprint | 2026-04-18 | cs.CV | ai-safety, alignment-training, cscv, preprint | E13 / R0 (100%) | - |
| AIFIND: Artifact-Aware Interpreting Fine-Grained Alignment for Incremental Face Forgery Detection Beichen Zhang, Hao Wang, Shaoyi Fang, Weigang Zhang Published: 2026-04-17Area: cs.CVCitations: - Tags: ai-safety, alignment-training, cscv, preprint | 2026-04-17 | cs.CV | ai-safety, alignment-training, cscv, preprint | E11 / R10 (97%) | - |
| Joint-Centric Dual Contrastive Alignment with Structure-Preserving and Information-Balanced Regularization Behrouz Haji Soleimani, Habibeh Naderi, Stan Matwin Published: 2026-04-17Area: cs.LGCitations: - Tags: ai-safety, alignment-training, cslg, preprint | 2026-04-17 | cs.LG | ai-safety, alignment-training, cslg, preprint | E12 / R10 (98%) | - |
| Prototype-Grounded Concept Models for Verifiable Concept Alignment David Debot, Giuseppe Marra, Pietro Barbiero, Stefano Colamonaco Published: 2026-04-17Area: cs.LGCitations: - Tags: ai-safety, alignment-training, cslg, preprint | 2026-04-17 | cs.LG | ai-safety, alignment-training, cslg, preprint | E9 / R10 (97%) | - |
| The Possibility of Artificial Intelligence Becoming a Subject and the Alignment Problem Helena Esther Grass, Till Mossakowski Published: 2026-04-16Area: cs.AICitations: - Tags: ai-safety, alignment-training, csai, preprint | 2026-04-16 | cs.AI | ai-safety, alignment-training, csai, preprint | E5 / R4 (96%) | - |
| CLIP Architecture for Abdominal CT Image-Text Alignment and Zero-Shot Learning: Investigating Batch Composition and Data Scaling Kartik Bose, Pankaj Gupta, Shivika Published: 2026-04-15Area: cs.CVCitations: - Tags: ai-safety, alignment-training, cscv, preprint | 2026-04-15 | cs.CV | ai-safety, alignment-training, cscv, preprint | E5 / R3 (97%) | - |
| From Alignment to Prediction: A Study of Self-Supervised Learning and Predictive Representation Learning Mintu Dutta, Mohendra Roy, Ritesh Vyas Published: 2026-04-15Area: cs.LGCitations: - Tags: ai-safety, alignment-training, cslg, preprint | 2026-04-15 | cs.LG | ai-safety, alignment-training, cslg, preprint | E5 / R3 (96%) | - |
| Gaslight, Gatekeep, V1-V3: Early Visual Cortex Alignment Shields Vision-Language Models from Sycophantic Manipulation Arya Shah, Chaklam Silpasuwanchai, Mayank Singh, Vaibhav Tripathi Published: 2026-04-15Area: cs.CVCitations: - Tags: ai-safety, alignment-training, cscv, preprint | 2026-04-15 | cs.CV | ai-safety, alignment-training, cscv, preprint | E5 / R3 (95%) | - |
| Seeing the imagined: a latent functional alignment in visual imagery decoding from fMRI data Fabrizio Spera, Matteo Ciferri, Matteo Ferrante, Michal Olak Published: 2026-04-15Area: q-bio.NCCitations: - Tags: ai-safety, alignment-training, preprint, q-bionc | 2026-04-15 | q-bio.NC | ai-safety, alignment-training, preprint, q-bionc | E8 / R4 (93%) | - |
| Step-level Denoising-time Diffusion Alignment with Multiple Objectives Dawei Wang, Qi Zhang, Shaofeng Zou Published: 2026-04-15Area: cs.LGCitations: - Tags: ai-safety, alignment-training, cslg, preprint | 2026-04-15 | cs.LG | ai-safety, alignment-training, cslg, preprint | E4 / R3 (93%) | - |
| SOAR: Self-Correction for Optimal Alignment and Refinement in Diffusion Models Chunyu Wang, Hao Fei, Liefeng Bo, Linqing Wang Published: 2026-04-14Area: cs.LGCitations: - Tags: ai-safety, alignment-training, cslg, preprint | 2026-04-14 | cs.LG | ai-safety, alignment-training, cslg, preprint | E8 / R4 (95%) | - |
| SOAR: Self-Correction for Optimal Alignment and Refinement in Diffusion Models Chunyu Wang, Hao Fei, Liefeng Bo, Linqing Wang Published: 2026-04-14Area: cs.LGCitations: - Tags: ai-safety, alignment-training, cslg, preprint | 2026-04-14 | cs.LG | ai-safety, alignment-training, cslg, preprint | E5 / R3 (96%) | - |
| 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%) | - |
| 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%) | - |
| 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%) | - |
| 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%) | - |
| 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%) | - |