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 |
|---|---|---|---|---|---|
| Gaussian Neural Networks Peter Kuhn, Victoria Heusinger-He脽 Published: 2026-09-28Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-09-28 | cs.LG | ai-safety, cslg, preprint | - | - |
| GradLev: Token-Parallel Test-Time Training Via Costate Prediction Bo Liu, Qiang Liu Published: 2026-09-28Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-09-28 | cs.LG | ai-safety, cslg, preprint | - | - |
| GradLev: Token-Parallel Test-Time Training Via Costate Prediction Bo Liu, Qiang Liu Published: 2026-09-28Area: cs.LGCitations: 45 Tags: ai-safety, cslg, preprint | 2026-09-28 | cs.LG | ai-safety, cslg, preprint | E10 / R8 (91%) | 45 |
| Graph neural networks for sampling-invariant embeddings of organized signal sets Jesus Angulo, Martin Bauw, Santiago Velasco-Forero Published: 2026-09-28Area: cs.LGCitations: 18 Tags: ai-safety, cslg, preprint | 2026-09-28 | cs.LG | ai-safety, cslg, preprint | E7 / R5 (91%) | 18 |
| Graph World Models for Constrained Epidemic Policy Planning Lingyi Wang, Naren Ramakrishnan, Rashed Shelim, Walid Saad Published: 2026-09-28Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-09-28 | cs.LG | ai-safety, cslg, preprint | - | - |
| How to Loop MoE: Flatten the Experts, Untie the Attention Chuang Ma, Debargha Ganguly, Mohsen Hariri, Qianying Liu Published: 2026-09-28Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-09-28 | cs.LG | ai-safety, cslg, preprint | - | - |
| Improving Generative Model Self-Training with Geometrically Modified Outputs Patrick Batsell, Richard Baraniuk, Thomas Walker Published: 2026-09-28Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-09-28 | cs.LG | ai-safety, cslg, preprint | - | - |
| Improving scalable oversight with co-trained monitors Benedict Tessler, Enric Boix Adser脿, Joseph H. Rudoler, Kevin Tan Published: 2026-09-28Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-09-28 | cs.LG | ai-safety, cslg, preprint | E7 / R4 (93%) | - |
| In-Context Learning Amplifies a Latent Symbolic Circuit Melissa Wessel Published: 2026-09-28Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-09-28 | cs.LG | ai-safety, cslg, preprint | - | - |
| Intrinsic Associative Memory on Riemannian Manifolds: Curvature, Capacity, and Emergent Modes Krishnakumar Balasubramanian, Zhaoyang Shi Published: 2026-09-28Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-09-28 | cs.LG | ai-safety, cslg, preprint | E9 / R7 (86%) | - |
| KV-streams for Efficient Compaction in Agentic Reinforcement Learning Abhay Puri, Alessandro Sordoni, Augustine N. Mavor-Parker, Dane Malenfant Published: 2026-09-28Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-09-28 | cs.LG | ai-safety, cslg, preprint | - | - |
| KV-streams for Efficient Compaction in Agentic Reinforcement Learning Abhay Puri, Alessandro Sordoni, Augustine N. Mavor-Parker, Dane Malenfant Published: 2026-09-28Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-09-28 | cs.LG | ai-safety, cslg, preprint | E17 / R17 (92%) | - |
| Large Language Models for Automated Cross-Domain Machine Learning Task Type Identification: A Benchmark Dataset and Evaluation Martin Heckmann, Petros Tsialis, Steffen Limmer, Tobias Rodemann Published: 2026-09-28Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint, safety-evaluation | 2026-09-28 | cs.LG | ai-safety, cslg, preprint, safety-evaluation | - | - |
| Learn Here, Move Less Elsewhere: Input-Conditioned Plasticity from Retained-Domain Activation Atlases Bangyang Wei, Jiangtao Lin, Siyi Liu, Yihang Ding Published: 2026-09-28Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-09-28 | cs.LG | ai-safety, cslg, preprint | - | - |
| Learning Perturbation Robust Policies for LLM Agents with Stable Optimization Huanrui Yang, Jingdi Chen, Pengxin Wang, Yuanzhe LI Published: 2026-09-28Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-09-28 | cs.LG | ai-safety, cslg, preprint | - | - |
| Learning to Re-Draft: A Variational Stackelberg Game for Discrete Diffusion Alice Wang, Dmitrii Moor, Federico Tomasi, Mounia Lalmas Published: 2026-09-28Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-09-28 | cs.LG | ai-safety, cslg, preprint | - | - |
| Learning to Steer, Steering to See: Unveiling the Geometry of RLVR in Large Language Models via Trainable Vectors Ding Cao, Guangzhong Sun, Guiquan Liu, Jiaxuan Wang Published: 2026-09-28Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-09-28 | cs.LG | ai-safety, cslg, preprint | - | - |
| Learning What to Recall: Adaptive Multi-Cue Episodic Memory for World Models Amir Bar, Bac Nguyen, Beomsu Kim, Chieh-Hsin Lai Published: 2026-09-28Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-09-28 | cs.LG | ai-safety, cslg, preprint | - | - |
| Learn Now, Use Next, Trust Later: Prequential Test-Time Learning for LLM Agents Haibo Shi, Haijin Liang, Reed Li, Tong Zhao Published: 2026-09-28Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-09-28 | cs.LG | ai-safety, cslg, preprint | E10 / R7 (91%) | - |
| Let the Neurons Die: Exploiting ReLU-Induced Model Degradation Aditi Maheshwari, David Lie, Joshua Abraham, Kexin Li Published: 2026-09-28Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-09-28 | cs.LG | ai-safety, cslg, preprint | - | - |
| LoopICL: Looping a single transformer block to solve tabular tasks Amir Rezaei Balef, Katharina Eggensperger Published: 2026-09-28Area: cs.LGCitations: 45 Tags: ai-safety, cslg, preprint | 2026-09-28 | cs.LG | ai-safety, cslg, preprint | E12 / R8 (93%) | 45 |
| LRC-JEPA: Disentangling Dynamics and Residual Context for Efficient World Models Jingyi Liang, Lei Chu, Luzhe Huang, Yuhuan Zhao Published: 2026-09-28Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-09-28 | cs.LG | ai-safety, cslg, preprint | - | - |
| MASCIT: A Mask-Aware State Space Classifier for Naturally Irregular Time Series Hyeon-Gi Kim, Jonghun Park, Yoo-Min Jung Published: 2026-09-28Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-09-28 | cs.LG | ai-safety, cslg, preprint | - | - |
| MaskCoFT: Masked Co-Adaptive Fine-Tuning for Memory-Efficient MoE Inference Hadjer Benmeziane, Junfeng Wu, Kaoutar El Maghraoui, Liu Liu Published: 2026-09-28Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-09-28 | cs.LG | ai-safety, cslg, preprint | - | - |
| MoRE: Scaling mixture of experts with hardware-aware low-rank routing Enric Boix-Adser脿, Honam Wong, Surbhi Goel Published: 2026-09-28Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-09-28 | cs.LG | ai-safety, cslg, preprint | - | - |
| Multi-Attractor GNNs: Set-Valued Expressivity Beyond Unique Equilibria Jialin Liu Published: 2026-09-28Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-09-28 | cs.LG | ai-safety, cslg, preprint | - | - |
| Neural networks for spectral optimization Alexis de Villeroch茅, Beniamin Bogosel, Dorin Bucur, Jacques-Olivier Lachaud Published: 2026-09-28Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-09-28 | cs.LG | ai-safety, cslg, preprint | E9 / R8 (93%) | - |
| No Pain, More Gain: Iterative Merging for Effective Multi-Teacher On-Policy Distillation Boseop Kim, Chaeyun Jang, Juho Lee, Noah Lee Published: 2026-09-28Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-09-28 | cs.LG | ai-safety, cslg, preprint | - | - |
| Normative Loss Landscape Navigation: A Trajectory-Based Approach to Mitigating Forgetting in Incremental Learning Isabelle Aguilar, Luis Fernando Herbozo Contreras, Omid Kavehei, Zayn Andre Zainal Published: 2026-09-28Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-09-28 | cs.LG | ai-safety, cslg, preprint | E10 / R8 (89%) | - |
| One Sequence, Many Decodings: CAGenMol-2 Recasts Drug Design as Masked Molecular Inference Enyan Dai, Lei Wang, Li Liu, Wen-Cai Ye Published: 2026-09-28Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-09-28 | cs.LG | ai-safety, cslg, preprint | - | - |