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 |
|---|---|---|---|---|---|
| A Controlled Study of Attention-Only Transformers Henry Ndubuaku, Jakub Mroz, Justin H Lee, Karen Mosoyan Published: 2026-07-20Area: cs.LGCitations: 15 Tags: ai-safety, cslg, preprint | 2026-07-20 | cs.LG | ai-safety, cslg, preprint | E9 / R8 (91%) | 15 |
| After the Euclidean Highway: Hyperbolic Expert AI as the Next Innovation In Seok Kang, Kwan Soo Shin, Munho Lee Published: 2026-07-20Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-07-20 | cs.LG | ai-safety, cslg, preprint | E11 / R10 (90%) | - |
| A Geometric Perspective on Stabilizing Value Conflict Resolution Andy Liu, Saket Reddy Published: 2026-07-20Area: cs.LGCitations: 15 Tags: ai-safety, cslg, preprint | 2026-07-20 | cs.LG | ai-safety, cslg, preprint | E12 / R7 (92%) | 15 |
| An Analysis of Residual-Stream Geometry Across Transformer Depth Ravi Shankar Kolli, Sunit Bhattacharya Published: 2026-07-20Area: cs.LGCitations: 15 Tags: ai-safety, cslg, preprint | 2026-07-20 | cs.LG | ai-safety, cslg, preprint | E9 / R6 (90%) | 15 |
| Automated Data Engineering and Feature Selection for the Case Study of Warpage Detection in Fused Deposition Modeling Nazanin Mahjourian, Saleh Valizadeh Sotubadi, Vinh Nguyen Published: 2026-07-20Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-07-20 | cs.LG | ai-safety, cslg, preprint | E13 / R8 (92%) | - |
| Beyond Objective Expressivity: Geometry Preservation in Multimodal Contrastive Learning Benjamin Wild, Roland Eils, Tillmann Rheude Published: 2026-07-20Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-07-20 | cs.LG | ai-safety, cslg, preprint | E8 / R7 (95%) | - |
| CANDOR: Chance-Calibrated Discordance in Frozen Foundation Encoders Daniel Truhn, Soroosh Tayebi Arasteh, Sven Nebelung Published: 2026-07-20Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-07-20 | cs.LG | ai-safety, cslg, preprint | E8 / R8 (92%) | - |
| Censoring-Aware In-Context Learning for Generalized Supplier Lead Time Estimation in Supply Chain Planning Ali Etemad, Behrouz Haji Soleimani, Christopher Wang, Sebastien Ouellet Published: 2026-07-20Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-07-20 | cs.LG | ai-safety, cslg, preprint | E9 / R7 (91%) | - |
| CoCurve: Cross-Module Co-Pruning Curvature for Training-Free Structured LLM Pruning Chau Yuen, Tiantong Wang, Wei Yang Bryan Lim, Zhiren Gong Published: 2026-07-20Area: cs.LGCitations: 15 Tags: ai-safety, cslg, preprint | 2026-07-20 | cs.LG | ai-safety, cslg, preprint | E13 / R10 (89%) | 15 |
| Differentiable Logic Gate Networks for Low-Latency EEG Classification on Edge Devices Camilo E. Valderrama, Shyamal Y. Dharia, Stephen D. Smith Published: 2026-07-20Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-07-20 | cs.LG | ai-safety, cslg, preprint | E10 / R8 (92%) | - |
| Do Language Models Dream of Binding Molecules? Benchmarking LLMs under Spatial Constraints Alex Aliper, Alex Zhavoronkov, Maksim Kuznetsov, Maxim Malkov Published: 2026-07-20Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-07-20 | cs.LG | ai-safety, cslg, preprint | E9 / R8 (93%) | - |
| Enhancing Rubric-based RL via Self-Distillation Chao Ye, Cheng Peng, Guangcheng Zhu, Haobo Wang Published: 2026-07-20Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-07-20 | cs.LG | ai-safety, cslg, preprint | E9 / R7 (91%) | - |
| Enhancing Rubric-based RL via Self-Distillation Chao Ye, Cheng Peng, Guangcheng Zhu, Haobo Wang Published: 2026-07-20Area: cs.LGCitations: 45 Tags: ai-safety, cslg, preprint | 2026-07-20 | cs.LG | ai-safety, cslg, preprint | E9 / R8 (92%) | 45 |
| Estimating Rare Events in Language Models with Proper Evaluation Anqi Liu, Nikita Y. Parulekar Published: 2026-07-20Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint, safety-evaluation | 2026-07-20 | cs.LG | ai-safety, cslg, preprint, safety-evaluation | E6 / R6 (90%) | - |
| Feature Attribution-Based Explainability Analysis of Deep Learning Models in Predictive Process Monitoring Johannes De Smedt, Kseniya Sahatova, Rafael Seidi Oyamada, Xuefei Lu Published: 2026-07-20Area: cs.LGCitations: 32 Tags: ai-safety, cslg, preprint | 2026-07-20 | cs.LG | ai-safety, cslg, preprint | E11 / R9 (92%) | 32 |
| Federated Lightweight Fine-Tuning Radhakrishna Achanta, Will Reed Published: 2026-07-20Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-07-20 | cs.LG | ai-safety, cslg, preprint | E8 / R6 (92%) | - |
| FIFA World Cup 2026 as a Contamination-Free Benchmark for LLM Forecasting Agents: Four Models, a Bookmaker, and 104 Matches Cong Guo, Jason Xu, Jiacheng Ding Published: 2026-07-20Area: cs.LGCitations: 36 Tags: ai-safety, cslg, preprint | 2026-07-20 | cs.LG | ai-safety, cslg, preprint | E10 / R13 (92%) | 36 |
| Generalised Bellman recurrence and three dualities in sequential decision-making Daniel Polani, David Hyland, Fernando E. Rosas Published: 2026-07-20Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-07-20 | cs.LG | ai-safety, cslg, preprint | E13 / R13 (93%) | - |
| Generalize and Guide: Decomposing Rewards for Few-Shot Inverse Reinforcement Learning Grace Zhang, Ziyi Liu Published: 2026-07-20Area: cs.LGCitations: 15 Tags: ai-safety, cslg, preprint | 2026-07-20 | cs.LG | ai-safety, cslg, preprint | E8 / R6 (93%) | 15 |
| Harness Engineering for LLM-Driven GPU Kernel Generation Chenyu Ma, Hangfei Xu, Shengzhao Wen, Yanpeng Wang Published: 2026-07-20Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-07-20 | cs.LG | ai-safety, cslg, preprint | E16 / R16 (89%) | - |
| Intelligence from Learnable Novelty Michael Levin, Yanbo Zhang Published: 2026-07-20Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-07-20 | cs.LG | ai-safety, cslg, preprint | E9 / R7 (87%) | - |
| MADA-RL: Multi-Agent Debate-Aware Reinforcement Learning for Parameter-Efficient Reasoning in Compact Models Cuong Xuan Chu, Evgeny Kharlamov, Martino M. L. Pulici, Volker Tresp Published: 2026-07-20Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-07-20 | cs.LG | ai-safety, cslg, preprint | E9 / R6 (89%) | - |
| MambaLSTM: A Spatio-Temporal Framework for Enhanced Traffic Accident Risk Prediction Muting Li, Thar Baker, Yachao Yuan, Zhen Yu Published: 2026-07-20Area: cs.LGCitations: 26 Tags: ai-safety, cslg, preprint | 2026-07-20 | cs.LG | ai-safety, cslg, preprint | E11 / R10 (95%) | 26 |
| Multi-layer MIMO Relay as Deep Physical Neural Networks: Power Amplifiers as Activation Functions Deniz G眉nd眉z, Itsik Bergel, Meng Hua Published: 2026-07-20Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-07-20 | cs.LG | ai-safety, cslg, preprint | E8 / R6 (94%) | - |
| MXSens: Sensitivity-Aware Mixed-Precision Quantization for Efficient LLM Inference Amir Yazdanbakhsh, Ayan Chakraborty, Babak Falsafi, Danila Mishin Published: 2026-07-20Area: cs.LGCitations: 15 Tags: ai-safety, cslg, preprint | 2026-07-20 | cs.LG | ai-safety, cslg, preprint | E10 / R7 (90%) | 15 |
| Now We Know? A Systematic Comparison of TerraMind and THOR Arnt-B酶rre Salberg, Eva Gmelich Meijling, Frederick Schindlegger, Johannes Jakubik Published: 2026-07-20Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-07-20 | cs.LG | ai-safety, cslg, preprint | E11 / R10 (92%) | - |
| One-step lowest-variance selection in a Gaussian random-field model motivated by masked diffusion: Total correlation and a square root collision threshold Linjun Li Published: 2026-07-20Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-07-20 | cs.LG | ai-safety, cslg, preprint | E6 / R5 (89%) | - |
| Operational Proto-Introspection in Looped Language Models: Process-Quality Taps, Executable Branching, and the Readout-Control Boundary Jan Kirin Published: 2026-07-20Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-07-20 | cs.LG | ai-safety, cslg, preprint | E8 / R7 (91%) | - |
| OR Else: A Differentiable Trust Region for Policy Optimization Chinmay Rane, Kanishka Tyagi, Michael Manry Published: 2026-07-20Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-07-20 | cs.LG | ai-safety, cslg, preprint | E12 / R10 (96%) | - |
| Phasor Attention: Mean Root Square Normalization for Phase Manifold Preservation Hwi-yeol Yun, Sangkeun Jung, Sungwoo Goo Published: 2026-07-20Area: cs.LGCitations: 11 Tags: ai-safety, cslg, preprint | 2026-07-20 | cs.LG | ai-safety, cslg, preprint | E8 / R7 (92%) | 11 |