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 |
|---|---|---|---|---|---|
| Twist, Don't Tilt: Trajectory-Exact Constrained Decoding for Masked Diffusion Models Aditya Thimmaiah, Haris Vikalo, Jayanth Srinivasa, Junyi Jessy Li Published: 2026-09-28Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-09-28 | cs.LG | ai-safety, cslg, preprint | - | - |
| Understanding Decision-Making Mechanisms in Neural Routing Solvers Fatemeh Askari, Mahdieh Soleymani Baghshah, Mazdak Teymourian, Mohammad Izadi Published: 2026-09-28Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-09-28 | cs.LG | ai-safety, cslg, preprint | E10 / R10 (95%) | - |
| VEX-Bench: Benchmarking Verification Complexity of LLM-Generated Misinformation Christopher Leckie, Elif Buse Doyuran, Hanxun Huang, Phoebe Matich Published: 2026-09-28Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-09-28 | cs.LG | ai-safety, cslg, preprint | - | - |
| WorldGraph: Graph-Native World Modeling Xike Xie, Yipeng Li, Zezhong Ding Published: 2026-09-28Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-09-28 | cs.LG | ai-safety, cslg, preprint | - | - |
| X-Reset: Scaling Object-Centric Reinforcement Learning via Cross-Embodiment Resets Chenyang Ma, Prithwish Dan, Wei Zhan Published: 2026-09-28Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-09-28 | cs.LG | ai-safety, cslg, preprint | - | - |
| A Cheap Verifier is Good Enough: LLM Post-training is Robust to Erroneous Rewards Andreas Plesner, Anish Athalye, Curtis Northcutt, Francisco Guzm谩n Published: 2026-09-27Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-09-27 | cs.LG | ai-safety, cslg, preprint | - | - |
| Algorithmic Harms Associated with Generative Model-Augmented Recommendation Systems Christine Herlihy, Kevin Bannerman Hutchful, Pedro Silva, Shloka Desai Published: 2026-09-27Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-09-27 | cs.LG | ai-safety, cslg, preprint | - | - |
| A Light Bilevel Refinement Aligns Self-Supervised Representations for Stronger Task-Specific Learning Gustav Wagner Zakarias, Zheng-Hua Tan Published: 2026-09-27Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-09-27 | cs.LG | ai-safety, cslg, preprint | - | - |
| AutoHGNN: Robust and Efficient Neural Architecture Search for Hypergraph Neural Networks Baisong Liu, Chengbin Peng, Pietro Li貌 b, Sirui Li Published: 2026-09-27Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-09-27 | cs.LG | ai-safety, cslg, preprint | - | - |
| BERT4DTI : BERT-based Model for Predicting Drug-Protein Interactions Abdelkrim Arie, Amina Selma Haichour, Khadidja Henni, Lina Abou-Abbas Published: 2026-09-27Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-09-27 | cs.LG | ai-safety, cslg, preprint | - | - |
| Beyond Conservatism: Recoverability-Conditioned Exploration for Model-Based Imitation Learning Qiang Wu, Shenghua Wan, Xuanlin Chen, Xunlan Zhou Published: 2026-09-27Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-09-27 | cs.LG | ai-safety, cslg, preprint | - | - |
| Beyond Fixed Features: Architecture-Dependent Sensitivity to Node Representations under Heterophily Priyanath Maji, Rajavinoth Paul Durai, Sidharth Gaur Published: 2026-09-27Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-09-27 | cs.LG | ai-safety, cslg, preprint | - | - |
| Beyond the Training Horizon: Mechanisms and Limits of Length Generalization in Looped Transformers Jia Liang, Liangming Pan, Xi Jin Published: 2026-09-27Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-09-27 | cs.LG | ai-safety, cslg, preprint | - | - |
| Beyond Timestamps: Decision-Aligned On-Policy Distillation for Long-Horizon Agents Can Lv, Heng Chang, Huan Zhang, Jinrong Liu Published: 2026-09-27Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-09-27 | cs.LG | ai-safety, cslg, preprint | - | - |
| BITS: Rethinking Fair and Comprehensive Evaluation for Irregular Time Series Forecasting Bin Yang, Chenjuan Guo, Christian S. Jensen, Hao Miao Published: 2026-09-27Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint, safety-evaluation | 2026-09-27 | cs.LG | ai-safety, cslg, preprint, safety-evaluation | - | - |
| BOReFT: Manifold Steering of Language Models for Black-box Optimization Andrew McCallum, Dhruv Agarwal, Horst Samulowitz, Kavitha Srinivas Published: 2026-09-27Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-09-27 | cs.LG | ai-safety, cslg, preprint | - | - |
| Chameleon: Dynamic Format Adapter for Efficient Diffusion Arnab Sanyal, Sandeep Chinchali Published: 2026-09-27Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-09-27 | cs.LG | ai-safety, cslg, preprint | - | - |
| Collaborative Synthetic Data for Privacy-Preserving Financial Fraud Detection Across Organizational Silos Burhanettin Bahadir Kibar, Domenique Zipperling, Niklas K{眉}hl, Simeon Allmendinger Published: 2026-09-27Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-09-27 | cs.LG | ai-safety, cslg, preprint | - | - |
| Compressing Value Predictions for Learning-Augmented Metrical Task Systems Kun He, Sizhe Li, Yecheng Li Published: 2026-09-27Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-09-27 | cs.LG | ai-safety, cslg, preprint | - | - |
| DEALS: Decentralized Expertise-Aware Load Serving for Multi-Agent LLM Systems Alvaro Velasquez, Jia Liu, Jingjuan Huang, Wenbin Wang Published: 2026-09-27Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-09-27 | cs.LG | ai-safety, cslg, preprint | - | - |
| Decoupling Token Roles in Autoregressive Pretraining Chris Russell, Junchi Yu, Kevin Qinghong Lin, Lei Feng Published: 2026-09-27Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-09-27 | cs.LG | ai-safety, cslg, preprint | - | - |
| Diffusion-Based Rollouts as a Stabilization Mechanism for Long-Horizon Environmental Forecasting Aaron J. Hill, Amy McGovern, Efi Foufoula-Georgiou, Marina Vicens-Miquel Published: 2026-09-27Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-09-27 | cs.LG | ai-safety, cslg, preprint | - | - |
| Diffusion Reward Models Bingxiang He, Chaojun Xiao, Cheng Qian, Chun Yu Published: 2026-09-27Area: cs.LGCitations: 15 Tags: ai-safety, cslg, preprint | 2026-09-27 | cs.LG | ai-safety, cslg, preprint | E8 / R6 (90%) | 15 |
| Diffusion Reward Models Bingxiang He, Chaojun Xiao, Cheng Qian, Chun Yu Published: 2026-09-27Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-09-27 | cs.LG | ai-safety, cslg, preprint | - | - |
| D-JEPA: Design-Recoverable JEPA Representation with Swappable Physics Decoders Aashwin Anand Mishra, Nitin Nagesh Kulkarni, Peter Lyu, Yin Yu Published: 2026-09-27Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-09-27 | cs.LG | ai-safety, cslg, preprint | - | - |
| Domain Generalization under Sampling Pattern Shifts in Irregular Time Series Changhun Kim, Donghwee Yoon, Eunho Yang, Grigorios Chrysos Published: 2026-09-27Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-09-27 | cs.LG | ai-safety, cslg, preprint | - | - |
| Do We Really Need KL Divergence for On-Policy Distillation of Large Language Models? Ce Luo, Fukang Wen, Gao Huang, Hui Wu Published: 2026-09-27Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-09-27 | cs.LG | ai-safety, cslg, preprint | - | - |
| Dynamic Kuramoto-Hodge Operators for PDEs on Complex Geometries and Topologies Xiang Li, Yue Song Published: 2026-09-27Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-09-27 | cs.LG | ai-safety, cslg, preprint | - | - |
| ECG-Scroll: A Long-Horizon, Streaming Benchmark and Agent Environment for Interpretation of Ambulatory Electrocardiograms Chenglin Li, Haitao Li, Yiheng Mao, Zhengxing Huang Published: 2026-09-27Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-09-27 | cs.LG | ai-safety, cslg, preprint | - | - |
| Engineering Efficient Self-Play Chess: Search, Replay, and Throughput Under Limited Compute Bertil Braun Published: 2026-09-27Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-09-27 | cs.LG | ai-safety, cslg, preprint | E8 / R6 (89%) | - |