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 |
|---|---|---|---|---|---|
| Arkios: An Open Bilingual English-Nepali Language Model Trained From Scratch, with a Devanagari-Aware Tokenizer Chetan Phakami Pun, Sajal Regmi, Siddhartha Pudasaini Published: 2026-08-30Area: cs.CLCitations: 12 Tags: ai-safety, cscl, preprint | 2026-08-30 | cs.CL | ai-safety, cscl, preprint | E11 / R10 (91%) | 12 |
| Arkios: An Open Bilingual English-Nepali Language Model Trained From Scratch, with a Devanagari-Aware Tokenizer Chetan Phakami Pun, Sajal Regmi, Siddhartha Pudasaini Published: 2026-08-30Area: cs.CLCitations: 15 Tags: ai-safety, cscl, preprint | 2026-08-30 | cs.CL | ai-safety, cscl, preprint | E13 / R13 (95%) | 15 |
| Auditing Harness Tampering in Self-Improving Agents Jie Shao, Xiaoyi Zhang, Xing Wang Published: 2026-08-30Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-08-30 | cs.CL | ai-safety, cscl, preprint | E14 / R18 (92%) | - |
| Beyond Fluency: A Rubric-Based Benchmark for Evaluating Saudi Dialect and Cultural Competence in Large Language Models Ahmed Rashad, Ghassan Al-Sumaidaee, Maxim Legg, Sajjad Abdoli Published: 2026-08-30Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-08-30 | cs.CL | ai-safety, cscl, preprint | E10 / R8 (94%) | - |
| CUDA-Harness: Harnessing Agentic CUDA Kernel Generation and Optimization from Natural Language An Zou, Qi Fan, Yehan Ma Published: 2026-08-30Area: cs.CLCitations: 15 Tags: ai-safety, cscl, preprint | 2026-08-30 | cs.CL | ai-safety, cscl, preprint | E10 / R7 (91%) | 15 |
| Do Multimodal LLMs See Before They Read? Diagnosing Contextual Sycophancy Hen-Hsen Huang, Yi-Cheng Lai Published: 2026-08-30Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-08-30 | cs.CL | ai-safety, cscl, preprint | E12 / R7 (94%) | - |
| Evaluating LLMs on Conversational Text-to-SQL under Chain Ambiguity and Intent Drift Feiran Huang, Hao Chen, Jiayan Lin, Qinggang Zhang Published: 2026-08-30Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-08-30 | cs.CL | ai-safety, cscl, preprint | E10 / R8 (91%) | - |
| From Detection to Refusal: Safer LLMs via Circuit-Guided Weight Scaling Chung-En Sun, Kuan-Lin Chu, Tsui-Wei Weng Published: 2026-08-30Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-08-30 | cs.CL | ai-safety, cscl, preprint | E14 / R11 (92%) | - |
| Generating Clinical Vignettes that Preserve Cognitive Formulations Amit Oren, Dean Ariel, Guy Laban, Nimrod Hertz-Palmor Published: 2026-08-30Area: cs.CLCitations: 15 Tags: ai-safety, cscl, preprint | 2026-08-30 | cs.CL | ai-safety, cscl, preprint | E6 / R5 (93%) | 15 |
| GUI-CC: Benchmarking Contextual Consistency of GUI World Models as Agent Environments Boxu Liu, Guo Gan, Jinbiao Wei, Lin Fu Published: 2026-08-30Area: cs.CLCitations: 15 Tags: ai-safety, cscl, preprint | 2026-08-30 | cs.CL | ai-safety, cscl, preprint | E12 / R11 (91%) | 15 |
| IndicDetect: Evaluating Cross-Lingual LLM-Generated Text Detection for Hindi, Telugu, and Tamil Bhaskar Ganesh Devalla, Derek F. Wong, Greeshma Yaluru, Junchao Wu Published: 2026-08-30Area: cs.CLCitations: 15 Tags: ai-safety, cscl, preprint | 2026-08-30 | cs.CL | ai-safety, cscl, preprint | E18 / R17 (94%) | 15 |
| Life Operators: a self-evolving framework for multiscale life modelling Shuo Wang, Yike Guo Published: 2026-08-30Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-08-30 | cs.CL | ai-safety, cscl, preprint | E13 / R12 (93%) | - |
| Medical Causal Hypothesis Verification with Large Language Models Abrar Ansari, Elena Zheleva, Md Aminul Islam, Safiyyah Ahmed Published: 2026-08-30Area: cs.CLCitations: 8 Tags: ai-safety, cscl, preprint | 2026-08-30 | cs.CL | ai-safety, cscl, preprint | E14 / R10 (92%) | 8 |
| Memory-First Fact-Checking: A Knowledge-Graph-Grounded Multi-Agent System for Misinformation Detection Adrian Groza, Alexandru Lecu, Amelia Petrenciuc Published: 2026-08-30Area: cs.CLCitations: 22 Tags: ai-safety, cscl, preprint | 2026-08-30 | cs.CL | ai-safety, cscl, preprint | E10 / R11 (93%) | 22 |
| MI-Distillation: Selecting from Model-Interpolated Instruct-Reasoning Data Spectrum for Chain-of-Thought Distillation Bo Zhang, HongKai Zheng, Hongliang Dai, Piji Li Published: 2026-08-30Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-08-30 | cs.CL | ai-safety, cscl, preprint | E11 / R8 (90%) | - |
| MUDDLE: Measuring Understanding of Documents under Distractor and Length Effects Andrew Feng, Jason Luo, Judy Song, Kevin Zhu Published: 2026-08-30Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-08-30 | cs.CL | ai-safety, cscl, preprint | E10 / R7 (93%) | - |
| OCGQuant: Outlier-Companion Grouping for NVFP4 Quantization Binjun Li, Hanling Yi, Pengyu Li, Xiaoqing Liu Published: 2026-08-30Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-08-30 | cs.CL | ai-safety, cscl, preprint | E10 / R9 (95%) | - |
| Pak3H: Evaluating the Cost of Cultural Mismatch in LLM Alignment with a Human-Contextualized Urdu Benchmark Abdullah Hashmat, Agha Ali Raza, Usman Naseem Published: 2026-08-30Area: cs.CLCitations: - Tags: ai-safety, alignment-training, cscl, preprint | 2026-08-30 | cs.CL | ai-safety, alignment-training, cscl, preprint | E19 / R16 (93%) | - |
| R$^2$A: Learning Persona Policies Through Persona Representation Learning and Runtime Alignment Chengsong You, Junwei Zhou, Mohan Zhang, Xiaohan Jia Published: 2026-08-30Area: cs.CLCitations: - Tags: ai-safety, alignment-training, cscl, preprint | 2026-08-30 | cs.CL | ai-safety, alignment-training, cscl, preprint | E10 / R10 (93%) | - |
| REIGN: Refurbished Embeddings with Integrated Guidance Networks for Efficient Context-Length Scaling Devrim 脟avu艧o臒lu, Emre Akba艧 Published: 2026-08-30Area: cs.CLCitations: 45 Tags: ai-safety, cscl, preprint | 2026-08-30 | cs.CL | ai-safety, cscl, preprint | E10 / R7 (92%) | 45 |
| REIGN: Refurbished Embeddings with Integrated Guidance Networks for Efficient Context-Length Scaling Devrim 脟avu艧o臒lu, Emre Akba艧 Published: 2026-08-30Area: cs.CLCitations: 45 Tags: ai-safety, cscl, preprint | 2026-08-30 | cs.CL | ai-safety, cscl, preprint | E10 / R8 (88%) | 45 |
| RePro: Proof-Verified Benchmark Rewriting for Reliable Evaluation of LLM Mathematical Problem Solving Jinjin Gu, Junhua Zhao, Xinlei Wang, Xiyuan Zhou Published: 2026-08-30Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint, safety-evaluation | 2026-08-30 | cs.CL | ai-safety, cscl, preprint, safety-evaluation | E10 / R8 (91%) | - |
| Scientific Agent Skills: A Library of Procedural Knowledge for Research Agents Aubrey M. Brueckner, Darshil Patel, Timothy Kassis, Vinayak Agarwal Published: 2026-08-30Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-08-30 | cs.CL | ai-safety, cscl, preprint | E10 / R9 (90%) | - |
| Scientific Agent Skills: A Library of Procedural Knowledge for Research Agents Aubrey M. Brueckner, Darshil Patel, Timothy Kassis, Vinayak Agarwal Published: 2026-08-30Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-08-30 | cs.CL | ai-safety, cscl, preprint | E25 / R15 (88%) | - |
| Sleight of Word Benchmark: Can Language Models Notice If Their Own Output Was Tampered With? Alberto Cetoli Published: 2026-08-30Area: cs.CLCitations: 15 Tags: ai-safety, cscl, preprint | 2026-08-30 | cs.CL | ai-safety, cscl, preprint | E11 / R11 (90%) | 15 |
| SUP-MIMIC: A Multi-Task Clinical Diagnosis Benchmark for Evaluating LLMs' Robustness to Contradictory Evidence Bo Wang, Chong Feng, Ge Shi, Xia Liu Published: 2026-08-30Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-08-30 | cs.CL | ai-safety, cscl, preprint | E12 / R10 (91%) | - |
| The Emergent Symbolic Structure of Artificial Neural Networks Paul Smolensky, Paul Soulos, R. Thomas McCoy, Tal Linzen Published: 2026-08-30Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-08-30 | cs.CL | ai-safety, cscl, preprint | - | - |
| ValueGraph: Value-Signal Guided Graph Pre-training for Contextualized User Representation Fengzhu Zeng, Mohammad Amanlou, Prasanta Bhattacharya, Wei Gao Published: 2026-08-30Area: cs.CLCitations: 15 Tags: ai-safety, cscl, preprint | 2026-08-30 | cs.CL | ai-safety, cscl, preprint | E11 / R10 (89%) | 15 |
| When Less is More: Understanding When Token Filtering Helps and Fails in AI-generated Text Detection Lvxiaowei Xu, Ming Cai, Xiaoyang Han Published: 2026-08-30Area: cs.CLCitations: 15 Tags: ai-safety, cscl, preprint | 2026-08-30 | cs.CL | ai-safety, cscl, preprint | E15 / R6 (94%) | 15 |
| Zero-Shot Respiratory Sound Classification through LLM-Augmented Audio-Text Alignment Aaqib Saeed, Hung Manh Pham, Mathias Funk, Mustafa Talha 陌lerisoy Published: 2026-08-30Area: cs.CLCitations: - Tags: ai-safety, alignment-training, cscl, preprint | 2026-08-30 | cs.CL | ai-safety, alignment-training, cscl, preprint | E10 / R8 (93%) | - |