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 |
|---|---|---|---|---|---|
| Thinking Beyond Videos: Unifying Video Reasoning and Deep Research for Open-World Video Agents Bin Wen, Bohan Hou, Changyi Liu, Han Li Published: 2026-08-24Area: cs.CVCitations: - Tags: ai-safety, cscv, preprint | 2026-08-24 | cs.CV | ai-safety, cscv, preprint | - | - |
| Think Only When Needed: Prompt-Authority Control for Selective Slow-Path Intervention in Vision-Language-Action Manipulation Chenwei Wang, Huiming Chen, Jiazhuo Li, Xiaojun Zhu Published: 2026-08-24Area: cs.ROCitations: - Tags: ai-safety, csro, preprint | 2026-08-24 | cs.RO | ai-safety, csro, preprint | - | - |
| Too much of a good thing -- when knowledge distillation promotes overfitting, and how to avoid it Christian Wagner, Daniel Molina, Irene Trigueros-Lorca, Isaac Triguero Published: 2026-08-24Area: cs.CVCitations: 15 Tags: ai-safety, cscv, preprint | 2026-08-24 | cs.CV | ai-safety, cscv, preprint | E9 / R6 (91%) | 15 |
| Toward Effective and Reliable LLM Agents via Dynamic Ontology Chengyuan Yang, Lingbing Guo, Wei Hu, Xiaohui Zhang Published: 2026-08-24Area: cs.AICitations: - Tags: ai-safety, csai, preprint | 2026-08-24 | cs.AI | ai-safety, csai, preprint | - | - |
| Towards a Densing Law for User Representation Learning at Billion-Scale Capacity Baokun Wang, Bin Dou, Huan Li, Junru Zhang Published: 2026-08-24Area: cs.IRCitations: - Tags: ai-safety, csir, preprint | 2026-08-24 | cs.IR | ai-safety, csir, preprint | - | - |
| Towards Comprehensive Basketball Understanding Jiayuan Rao, Shangzhe Di, Weidi Xie, Yirong Hu Published: 2026-08-24Area: cs.CVCitations: - Tags: ai-safety, cscv, preprint | 2026-08-24 | cs.CV | ai-safety, cscv, preprint | - | - |
| TRACE: A Self-Evolving Skill Bank for Consistent, Limit-Aware LLM Agents Jian Luan, Kun Shao, Menghao Zhang, Wenhao Wu Published: 2026-08-24Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-08-24 | cs.CL | ai-safety, cscl, preprint | E11 / R7 (93%) | - |
| Triplet2Track: A Hierarchical System with Object-Centric Representations for Reliable Long-Horizon Manipulation Chuan Wen, Gaojing Zhang, Jianxiang Liu, Ning Guo Published: 2026-08-24Area: cs.ROCitations: - Tags: ai-safety, csro, preprint | 2026-08-24 | cs.RO | ai-safety, csro, preprint | E13 / R11 (92%) | - |
| TrustShiftProbe: Characterizing, Benchmarking, and Defending Staged Trust Attacks on MCP Servers Daniel Takabi, Mehrdad Rostamzadeh, Mohammad Ghasemigol, Sidhant Narula Published: 2026-08-24Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-08-24 | cs.CR | ai-safety, cscr, preprint | E11 / R9 (93%) | - |
| Unlearning Is Not Just Erasing: Temporal Decoupling via Generation Inequality Jinyu Guo, Qirui Ye, Shiyao Guo, Wenyi Li Published: 2026-08-24Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-08-24 | cs.CL | ai-safety, cscl, preprint | - | - |
| Walking on the DARKSIDE Aldo Gangemi, Emanuele Bottazzi Published: 2026-08-24Area: cs.AICitations: - Tags: ai-safety, csai, preprint | 2026-08-24 | cs.AI | ai-safety, csai, preprint | - | - |
| What is mathematics now, and what should it be? Jeremy Avigad Published: 2026-08-24Area: cs.AICitations: - Tags: ai-safety, csai, preprint | 2026-08-24 | cs.AI | ai-safety, csai, preprint | - | - |
| What Process Evaluation of Coding Agents Actually Measures: Action, Task, and Step Are Three Different Levels Dong Sun, Jiawei He, Jie jia, Mengyu Shi Published: 2026-08-24Area: cs.AICitations: - Tags: ai-safety, csai, preprint, safety-evaluation | 2026-08-24 | cs.AI | ai-safety, csai, preprint, safety-evaluation | - | - |
| What Proves You Wrong: Benchmarking Language Models on Falsifiable Research Ideation Aomufei Yuan, Haoli Bai, Hongyao Zuo, Linli Yao Published: 2026-08-24Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-08-24 | cs.CL | ai-safety, cscl, preprint | - | - |
| What Reaches Expert Review? Representation, Structural Screening, and Candidate-Form Dependence in AI-Assisted Item Development Christopher Brooks Published: 2026-08-24Area: cs.CLCitations: 15 Tags: ai-safety, cscl, preprint | 2026-08-24 | cs.CL | ai-safety, cscl, preprint | E10 / R8 (90%) | 15 |
| What's the Catch? Evaluating Temporal Consistency in Vision-Language Models Danae S谩nchez Villegas, Marek Hradil Published: 2026-08-24Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-08-24 | cs.CL | ai-safety, cscl, preprint | - | - |
| What's the Catch? Evaluating Temporal Consistency in Vision-Language Models Danae S谩nchez Villegas, Marek Hradil Published: 2026-08-24Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-08-24 | cs.CL | ai-safety, cscl, preprint | E10 / R10 (92%) | - |
| When Does Frequency Decomposition Benefit Physics-Informed Neural Networks? A Preliminary Ablation Study Shubham Rai Published: 2026-08-24Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-08-24 | cs.LG | ai-safety, cslg, preprint | E11 / R11 (93%) | - |
| When Names Cross Scripts: A Source-Grounded Benchmark for Historical Entity Reconciliation in the Mongol World Xiang Chen, Zeyu Zhang Published: 2026-08-24Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-08-24 | cs.CL | ai-safety, cscl, preprint | - | - |
| When Youth Enter The Chat: An Epistemic Shift in the Validation of LLM-Based Measures of Student Talk Dorottya Demszky, James Malamut, Liliana Santos-Deonizio, Ram贸n Antonio Mart铆nez Published: 2026-08-24Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-08-24 | cs.CL | ai-safety, cscl, preprint | E8 / R6 (93%) | - |
| When Youth Enter The Chat: An Epistemic Shift in the Validation of LLM-Based Measures of Student Talk Dorottya Demszky, James Malamut, Liliana Santos-Deonizio, Ram贸n Mart铆nez Published: 2026-08-24Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-08-24 | cs.CL | ai-safety, cscl, preprint | E8 / R6 (95%) | - |
| WildHandBench: A Benchmark for Handwritten Text Understanding that Challenges MLLMs and Humans Changda Zhou, Cheng Cui, Jianwen Yang, Jianying Qu Published: 2026-08-24Area: cs.CVCitations: - Tags: ai-safety, cscv, preprint | 2026-08-24 | cs.CV | ai-safety, cscv, preprint | - | - |
| XTC: Head-Aware Sampling by Excluding Top Choices Allen Roush, Judah Goldfeder, Philipp Emanuel Weidmann, Ravid Shwartz-Ziv Published: 2026-08-24Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-08-24 | cs.CL | ai-safety, cscl, preprint | E12 / R12 (93%) | - |
| Your AI, On a Dial: Controlling Investment Bias in LLMs with a Single Neuron Alejandro Lopez-Lira, Chanyeol Choi, Gakyung Kwon, Hoyoung Lee Published: 2026-08-24Area: cs.AICitations: - Tags: ai-safety, csai, preprint | 2026-08-24 | cs.AI | ai-safety, csai, preprint | E10 / R10 (91%) | - |
| Addressing the Selection Problem in Explainable AI Claire Vlases, Katelyn Morrison Published: 2026-08-23Area: cs.AICitations: - Tags: ai-safety, csai, preprint | 2026-08-23 | cs.AI | ai-safety, csai, preprint | E12 / R9 (91%) | - |
| Aggregation-Aware Synthetic Text Generation Against Authorship Re-Identification Anna Squicciarini, Qian Ma, Sarah Rajtmajer Published: 2026-08-23Area: cs.AICitations: 45 Tags: ai-safety, csai, preprint | 2026-08-23 | cs.AI | ai-safety, csai, preprint | E10 / R9 (93%) | 45 |
| AI-based worker guidance in assembly and disassembly operations using multimodal ego/exo-centric data capture and structured task knowledge J枚rg Kr眉ger, Vivek Chavan Published: 2026-08-23Area: cs.CVCitations: 23 Tags: ai-safety, cscv, preprint | 2026-08-23 | cs.CV | ai-safety, cscv, preprint | E8 / R8 (94%) | 23 |
| A Lightweight Multimodal Vision-Language Framework for Early-Stage Anatomical Green Fruit Classification in Commercial Orchards Chen Chen, Manoj Karkee, Ranjan Sapkota, William Bu Published: 2026-08-23Area: cs.CVCitations: - Tags: ai-safety, cscv, preprint | 2026-08-23 | cs.CV | ai-safety, cscv, preprint | E10 / R10 (94%) | - |
| Analyzing and Mitigating Cross-Lingual Degradation in Multilingual Medical VQA Bing Qin, Haochun Wang, Jingbo Wang, Sendong Zhao Published: 2026-08-23Area: cs.AICitations: - Tags: ai-safety, csai, preprint | 2026-08-23 | cs.AI | ai-safety, csai, preprint | E20 / R7 (93%) | - |
| A survey detection channel overrides the pixels in an astronomical foundation model, and biases tomographic mean redshifts Ihor Kendiukhov Published: 2026-08-23Area: cs.AICitations: - Tags: ai-safety, csai, preprint | 2026-08-23 | cs.AI | ai-safety, csai, preprint | E7 / R6 (94%) | - |