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 |
|---|---|---|---|---|---|
| The Invisible Editorial Layer: Formalizing Undisclosed Inference-Time Steering, Probability Placement, and the Attribution Problem in Deployed Language Models Augusto Camargo Published: 2026-08-25Area: cs.AICitations: 20 Tags: ai-safety, csai, preprint | 2026-08-25 | cs.AI | ai-safety, csai, preprint | E12 / R7 (93%) | 20 |
| The Invisible Editorial Layer: Formalizing Undisclosed Inference-Time Steering, Probability Placement, and the Attribution Problem in Deployed Language Models Augusto Camargo Published: 2026-08-25Area: cs.AICitations: - Tags: ai-safety, csai, preprint | 2026-08-25 | cs.AI | ai-safety, csai, preprint | E8 / R5 (92%) | - |
| The RAT: A Unified Bayesian Model for RAG Evaluation Felix Matthias Saaro, Jan Deriu, Mark Cieliebak, Pius von D盲niken Published: 2026-08-25Area: cs.CLCitations: 45 Tags: ai-safety, cscl, preprint, safety-evaluation | 2026-08-25 | cs.CL | ai-safety, cscl, preprint, safety-evaluation | E16 / R14 (95%) | 45 |
| The Shadow Price of Intelligence: Quality Degradation in LLM Inference as a Supply Chain Problem Elioth Sanabria Published: 2026-08-25Area: math.OCCitations: 12 Tags: ai-safety, mathoc, preprint | 2026-08-25 | math.OC | ai-safety, mathoc, preprint | E8 / R6 (93%) | 12 |
| The Von-Neumann State-Space Transformer for neural decoding Morteza Sarafyazd Published: 2026-08-25Area: cs.LGCitations: 13 Tags: ai-safety, cslg, preprint | 2026-08-25 | cs.LG | ai-safety, cslg, preprint | E8 / R7 (93%) | 13 |
| Tlow: Flow-based Item Tokenizer for Recommendation Chonggang Song, Jingtao Ding, Lingling Yi, Nian Li Published: 2026-08-25Area: cs.IRCitations: 15 Tags: ai-safety, csir, preprint | 2026-08-25 | cs.IR | ai-safety, csir, preprint | E9 / R8 (92%) | 15 |
| Toward Machine Learning with the Unit as a Primitive: Learning from Unit-Linked Events Heyang Gong Published: 2026-08-25Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-08-25 | cs.LG | ai-safety, cslg, preprint | E6 / R5 (89%) | - |
| Towards Reliable, Generalizable, and Specific In-Context Knowledge Editing via Multi-Objective Reinforcement Learning Girija Bhusal, Haipeng Chen, Maiqi Jiang, Tejal Nair Published: 2026-08-25Area: cs.AICitations: - Tags: ai-safety, csai, preprint | 2026-08-25 | cs.AI | ai-safety, csai, preprint | E12 / R9 (92%) | - |
| TRACE: An Evidence-Grounded Benchmark for Safety Evaluation of Large Reasoning Models Ali Almadan, Aminullah Tora, Changchun Yang, Faisal Wahbo Published: 2026-08-25Area: cs.AICitations: 15 Tags: ai-safety, csai, preprint, safety-evaluation | 2026-08-25 | cs.AI | ai-safety, csai, preprint, safety-evaluation | E11 / R7 (92%) | 15 |
| TransPhy: Visual In-Context Learning for Physically Grounded Image Editing Haoran Tang, Jinsheng Quan, Lei Yang, Quan Wang Published: 2026-08-25Area: cs.CVCitations: - Tags: ai-safety, cscv, preprint | 2026-08-25 | cs.CV | ai-safety, cscv, preprint | E7 / R6 (93%) | - |
| Tunable Tool-Call Rates in LLM Agents via Representation Steering Chenguang Wang, Dawn Song, Vincent Siu, Yang Liu Published: 2026-08-25Area: cs.AICitations: - Tags: ai-safety, csai, preprint | 2026-08-25 | cs.AI | ai-safety, csai, preprint | E10 / R7 (93%) | - |
| Understanding the Energy Scaling of Large Language Model Inference Across Context Lengths and Attention Architectures Arghavan Asad, Jos H枚ll, Molka Chkir, Syed Muhammad Danish Published: 2026-08-25Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-08-25 | cs.LG | ai-safety, cslg, preprint | E10 / R9 (94%) | - |
| Unsupervised Post-Training of Foundation Models: A Survey Aiwei Liu, Cehao Yang, Hui Xiong, Huizai Yao Published: 2026-08-25Area: cs.CLCitations: 91 Tags: ai-safety, cscl, preprint | 2026-08-25 | cs.CL | ai-safety, cscl, preprint | E10 / R8 (93%) | 91 |
| Unsupervised Post-Training of Foundation Models: A Survey Aiwei Liu, Cehao Yang, Hui Xiong, Huizai Yao Published: 2026-08-25Area: cs.CLCitations: 78 Tags: ai-safety, cscl, preprint | 2026-08-25 | cs.CL | ai-safety, cscl, preprint | E12 / R11 (92%) | 78 |
| VideoHarness-RSI: Recursive Harness Self-Improvement for Long-Video Understanding with Frozen Vision-Language Models Guoyang Xu, Hao Chen Published: 2026-08-25Area: cs.AICitations: - Tags: ai-safety, csai, preprint | 2026-08-25 | cs.AI | ai-safety, csai, preprint | E9 / R8 (92%) | - |
| VisCache: Visual KV Cache Pruning for Efficient Vision Large Language Model Inference Guangxu Zhu, Lyuke Wang, Zhuo Li Published: 2026-08-25Area: cs.CVCitations: 15 Tags: ai-safety, cscv, preprint | 2026-08-25 | cs.CV | ai-safety, cscv, preprint | E14 / R14 (89%) | 15 |
| WebMCP-Phalanx: Enforcing and Characterizing Trust Boundaries for Browser-Integrated LLM Agents Kuo-Hui Yeh, Lin-Fa Lee, YI-YU Chang Published: 2026-08-25Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-08-25 | cs.CR | ai-safety, cscr, preprint | E9 / R8 (93%) | - |
| What Guides the Agent? Adjudicating Unauthorized Behavior via Localizing Behavior-Guiding Instructions Haohua Du, Puhan Luo, Ruiqi Li, Yichao Gao Published: 2026-08-25Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-08-25 | cs.CR | ai-safety, cscr, preprint | E8 / R6 (92%) | - |
| When Does Context Routing Help? A Systematic Study of Multi-Modal Fusion in Time Series Forecasting Deepayan Chakrabarti, Gaoyuan Du, Haoqi Yao, Jiating Lin Published: 2026-08-25Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-08-25 | cs.LG | ai-safety, cslg, preprint | E10 / R6 (90%) | - |
| When Do Supervised UQ Ensembles Improve LLM Hallucination Detection? A Robustness Study Dylan Bouchard, Mohit Singh Chauhan, Vipin Gyanchandani Published: 2026-08-25Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-08-25 | cs.LG | ai-safety, cslg, preprint | E14 / R8 (92%) | - |
| When Less Is More: An Empirical Study of Minimal Responses in Counseling Dialogues and the Behavior of LLMs Zhiyang Qi Published: 2026-08-25Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-08-25 | cs.CL | ai-safety, cscl, preprint | E18 / R9 (93%) | - |
| When "Must" Becomes "Maybe": Constraint Weakening in LLM Agent Workflows Huifei Wang, Yancheng Zhu, Yifan Yuan, Yiheng Sun Published: 2026-08-25Area: cs.AICitations: - Tags: ai-safety, csai, preprint | 2026-08-25 | cs.AI | ai-safety, csai, preprint | E12 / R10 (95%) | - |
| When Seeing Is Not Enough: Benchmarking Interactive Visual Grounding in LVLMs Owen Rambow, Zhengxiang Wang Published: 2026-08-25Area: cs.AICitations: 45 Tags: ai-safety, csai, preprint | 2026-08-25 | cs.AI | ai-safety, csai, preprint | E13 / R8 (93%) | 45 |
| Why fragmented parliaments stop passing legislation: Opposition discipline and representation across four democratic institutions Fuad Ali Published: 2026-08-25Area: physics.soc-phCitations: - Tags: ai-safety, physicssoc-ph, preprint | 2026-08-25 | physics.soc-ph | ai-safety, physicssoc-ph, preprint | E12 / R7 (95%) | - |
| A-CPES: A Reference Framework for Agentic AI in Cyber-Physical Energy Systems Jiachen Xu, Qiuye Sun, Xiaoyu Zhang, Yushuai Li Published: 2026-08-24Area: cs.AICitations: 28 Tags: ai-safety, csai, preprint | 2026-08-24 | cs.AI | ai-safety, csai, preprint | E10 / R9 (90%) | 28 |
| Act with Intent: Distilling Behavior Intent for Vision-Language-Action Models Sangoh Lee, Sangwoo Mo, Wook-Shin Han Published: 2026-08-24Area: cs.ROCitations: - Tags: ai-safety, csro, preprint | 2026-08-24 | cs.RO | ai-safety, csro, preprint | - | - |
| Adapter-Based Few-Shot Continual Learning for Malicious Packet Recognition Andrew Arash Mahyari, Guillermo Francia, III Eman El-Sheikh, Kyle Stein Published: 2026-08-24Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-08-24 | cs.CR | ai-safety, cscr, preprint | - | - |
| Adaptive Item-based Collaborative Structures via Noise Rescheduling in Diffusion for Generative Recommendation Heng Chang, Jiaqi Wang, Jihong Guan, Shuigeng Zhou Published: 2026-08-24Area: cs.IRCitations: - Tags: ai-safety, csir, preprint | 2026-08-24 | cs.IR | ai-safety, csir, preprint | - | - |
| Adversarial Entropy Inflation Against Gumbel-Based Inference Verification Nikita Kezins Published: 2026-08-24Area: cs.CRCitations: - Tags: adversarial-robustness, ai-safety, cscr, preprint | 2026-08-24 | cs.CR | adversarial-robustness, ai-safety, cscr, preprint | - | - |
| AffectOmni: RL-Verifiable People-Centric Grounded Affective Reasoning for Social and Art-Related Scenes Bimei Wang, Bin Hu, Hong Peng, Jisheng Dang Published: 2026-08-24Area: cs.AICitations: - Tags: ai-safety, csai, preprint | 2026-08-24 | cs.AI | ai-safety, csai, preprint | E11 / R9 (95%) | - |