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 |
|---|---|---|---|---|---|
| Data-Driven Personas for Survey Simulation: Insights into Simulation Alignment Across Data-Access Regimes Dongryeol Lee, Leonardo Perelli, Saab Mansour, Weronika 艁ajewska Published: 2026-10-05Area: cs.AICitations: - Tags: ai-safety, alignment-training, csai, preprint | 2026-10-05 | cs.AI | ai-safety, alignment-training, csai, preprint | E12 / R9 (94%) | - |
| Defense-in-Depth for LLMs: Evaluating Memory Gates Against Activation-Induced and Memory-Induced Sycophancy Maheep Chaudhary, Ritvij Sharma, Russell Dlugosz, Ryan Zhou Published: 2026-10-05Area: cs.AICitations: 18 Tags: ai-safety, csai, preprint | 2026-10-05 | cs.AI | ai-safety, csai, preprint | E16 / R11 (94%) | 18 |
| DGA-Muon: Decoupled Geometry-Aligned Adaptive Scaling for Muon Runsheng Yu, Wenpeng Zhang Published: 2026-10-05Area: cs.AICitations: - Tags: ai-safety, csai, preprint | 2026-10-05 | cs.AI | ai-safety, csai, preprint | - | - |
| DGA-Muon: Decoupled Geometry-Aligned Adaptive Scaling for Muon Runsheng Yu, Wenpeng Zhang Published: 2026-10-05Area: cs.AICitations: 45 Tags: ai-safety, csai, preprint | 2026-10-05 | cs.AI | ai-safety, csai, preprint | E6 / R5 (92%) | 45 |
| DiMOS: Doob-Guided Inference-Time Multi-Objective Search for Scientific Design Han Liu, Kaize Ding, Minshuo Chen, Qijie Zhu Published: 2026-10-05Area: cs.AICitations: - Tags: ai-safety, csai, preprint | 2026-10-05 | cs.AI | ai-safety, csai, preprint | - | - |
| Does Muon Need Fine-Grained Spectral Shaping? Aristides Gionis, Meher Chaitanya, Tianyi Zhou Published: 2026-10-05Area: cs.AICitations: - Tags: ai-safety, csai, preprint | 2026-10-05 | cs.AI | ai-safety, csai, preprint | E11 / R7 (92%) | - |
| Does the Model Use the Feature? Separating Steering from Mechanism in LLMs Tong Che, Yilong Li Published: 2026-10-05Area: cs.AICitations: 25 Tags: ai-safety, csai, preprint | 2026-10-05 | cs.AI | ai-safety, csai, preprint | E13 / R9 (93%) | 25 |
| Do Small Language Models Learn to Negotiate? A Controlled Scaling Study of RL-Trained Sellers Pedro Tabacof, Sagar Joglekar Published: 2026-10-05Area: cs.AICitations: - Tags: ai-safety, csai, preprint | 2026-10-05 | cs.AI | ai-safety, csai, preprint | - | - |
| Do Time-Series QA Systems Read the Time Series? Evidence Use and Reasoning Reliability Dongsheng Luo, Janki Bhimani, Jingchao Ni, Mo Sha Published: 2026-10-05Area: cs.AICitations: - Tags: ai-safety, csai, preprint | 2026-10-05 | cs.AI | ai-safety, csai, preprint | - | - |
| DPNL: A DPLL-based Algorithm for Probabilistic Neurosymbolic Learning Luisa Sophie Werner, Nabil Laya{茂}da, Nils Gesbert, Pierre Genev{猫}s Published: 2026-10-05Area: cs.AICitations: - Tags: ai-safety, csai, preprint | 2026-10-05 | cs.AI | ai-safety, csai, preprint | - | - |
| Energy-Conditioned Noise Schedule and Whitening for Spectral Diffusion Bane Vasic, Bata Vasic Published: 2026-10-05Area: cs.AICitations: 16 Tags: ai-safety, csai, preprint | 2026-10-05 | cs.AI | ai-safety, csai, preprint | E12 / R8 (96%) | 16 |
| Evaluate the Stack, Not the Layer: Do Deterministic and LLM Gates for Agent Actions Fail Independently? Chenglin Yang Published: 2026-10-05Area: cs.AICitations: 21 Tags: ai-safety, csai, preprint | 2026-10-05 | cs.AI | ai-safety, csai, preprint | E13 / R8 (92%) | 21 |
| Evaluating Escalation Signals for LLM Routing: Targets, Controls, and Five Ways to Fool Yourself Andrea Morandi, Mahesh Viswanathan, Ramin Pishehvar Published: 2026-10-05Area: cs.AICitations: 15 Tags: ai-safety, csai, preprint | 2026-10-05 | cs.AI | ai-safety, csai, preprint | E8 / R5 (90%) | 15 |
| Evolving in Thought Space: Training a Small Model at Test Time Unlocks Better Discoveries Ao Qu, Baichuan Mo, Bo Liu, Chonghe Jiang Published: 2026-10-05Area: cs.AICitations: - Tags: ai-safety, csai, preprint | 2026-10-05 | cs.AI | ai-safety, csai, preprint | - | - |
| FREA: A Multi-Source Expert Benchmark for Reaction Feasibility Verification Botao Yu, Bo Zhou, Daniel Adu-Ampratwum, Frazier N. Baker Published: 2026-10-05Area: cs.AICitations: - Tags: ai-safety, csai, preprint | 2026-10-05 | cs.AI | ai-safety, csai, preprint | - | - |
| FreSia: Frequency-Semantic Instantiation and Alignment for Multivariate Time Series Analysis Guoqing Ji, Hezhe Qiao, Hui He, Yubo Wang Published: 2026-10-05Area: cs.AICitations: - Tags: ai-safety, alignment-training, csai, preprint | 2026-10-05 | cs.AI | ai-safety, alignment-training, csai, preprint | - | - |
| From Benchmark to Bench: Can Agents Survive Real-World Drug Discovery? Alessandro Tibo, Helen Lai, Levent Guner, Pierre Llompart Published: 2026-10-05Area: cs.AICitations: 38 Tags: ai-safety, csai, preprint | 2026-10-05 | cs.AI | ai-safety, csai, preprint | E10 / R11 (93%) | 38 |
| From Benchmark to Bench: Can Agents Survive Real-World Drug Discovery? Alessandro Tibo, Helen Lai, Levent Guner, Pierre Llompart Published: 2026-10-05Area: cs.AICitations: - Tags: ai-safety, csai, preprint | 2026-10-05 | cs.AI | ai-safety, csai, preprint | - | - |
| From Local Evidence to Safety Verdicts: Causal Tracing in Vision-Language Models Alexander Romanus, Faezeh Dehghan Tarzjani, Mevan Wijewardena, Sampad Mohanty Published: 2026-10-05Area: cs.AICitations: 22 Tags: ai-safety, csai, preprint | 2026-10-05 | cs.AI | ai-safety, csai, preprint | E8 / R7 (92%) | 22 |
| From Papers to Mechanisms: An Evidence-Grounded Knowledge Substrate for Scientific Language Models Jiafan Lu, Qiuhui Chen, Tao Dai, Weimin Zhong Published: 2026-10-05Area: cs.AICitations: - Tags: ai-safety, csai, preprint | 2026-10-05 | cs.AI | ai-safety, csai, preprint | - | - |
| From Token-Max to Outcome-Max: How You Use AI Determines Its Productivity Beibei Li, Chen Xu, Chenyan Xiong, Mengqiao Liu Published: 2026-10-05Area: cs.AICitations: - Tags: ai-safety, csai, preprint | 2026-10-05 | cs.AI | ai-safety, csai, preprint | - | - |
| GPlaceRL: An Open-Source Graph Reinforcement Learning Framework for Detailed Placement Athanasios Tziouvaras, Christos Anagnostopoulos, Christos Poulos, Foteini Oikonomou Published: 2026-10-05Area: cs.AICitations: - Tags: ai-safety, csai, preprint | 2026-10-05 | cs.AI | ai-safety, csai, preprint | - | - |
| GraphDecide: Benchmarking System One Models on Graph Tasks Li Zhao, Xianliang Yang, Yapu Zhang Published: 2026-10-05Area: cs.AICitations: - Tags: ai-safety, csai, preprint | 2026-10-05 | cs.AI | ai-safety, csai, preprint | - | - |
| GraphDecisionBench: Benchmarking System One Models on Graph Tasks Li Zhao, Xianliang Yang, Yapu Zhang Published: 2026-10-05Area: cs.AICitations: 38 Tags: ai-safety, csai, preprint | 2026-10-05 | cs.AI | ai-safety, csai, preprint | E10 / R9 (95%) | 38 |
| Grounded Joint-Attention Other-Play for Zero-Shot Coordination Andreas Bulling, Constantin Ruhdorfer, Fabian K枚gel, Giulia Benintendi Published: 2026-10-05Area: cs.AICitations: - Tags: ai-safety, csai, preprint | 2026-10-05 | cs.AI | ai-safety, csai, preprint | - | - |
| Grounding What Shapes the Plan: Rethinking Groundedness for Physical Intelligence in Autonomous Driving Boris Ivanovic, Boyi Li, Chaowei Xiao, Marco Pavone Published: 2026-10-05Area: cs.AICitations: 15 Tags: ai-safety, csai, preprint | 2026-10-05 | cs.AI | ai-safety, csai, preprint | E8 / R7 (91%) | 15 |
| HERA: Harness-Environment Co-Evolution for Reliable Agentic Abstention Bingbing Wen, Guang Yang, Han Luo, Lucy Lu Wang Published: 2026-10-05Area: cs.AICitations: - Tags: ai-safety, csai, preprint | 2026-10-05 | cs.AI | ai-safety, csai, preprint | - | - |
| How Should a Prompt Optimizer Spend a Tight Budget? BudgetAPO with Noise-Adaptive Evaluation Haoyue Liu, Huanyu Yan, Xiaoying Tang, Zhichao Wang Published: 2026-10-05Area: cs.AICitations: 15 Tags: ai-safety, csai, preprint, safety-evaluation | 2026-10-05 | cs.AI | ai-safety, csai, preprint, safety-evaluation | E13 / R7 (92%) | 15 |
| How Should a Prompt Optimizer Spend a Tight Budget? BudgetAPO with Noise-Adaptive Evaluation Haoyue Liu, Huanyu Yan, Xiaoying Tang, Zhichao Wang Published: 2026-10-05Area: cs.AICitations: - Tags: ai-safety, csai, preprint, safety-evaluation | 2026-10-05 | cs.AI | ai-safety, csai, preprint, safety-evaluation | - | - |
| Impact of Data Augmentation on Confidence Calibration in Melanoma Classification Morgan May, Pierpaolo Dondio, Simon Caton Published: 2026-10-05Area: cs.AICitations: - Tags: ai-safety, csai, preprint | 2026-10-05 | cs.AI | ai-safety, csai, preprint | - | - |