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 |
|---|---|---|---|---|---|
| Wrong Code, Right Structure: Learning Netlist Representations from Imperfect LLM-Generated RTL Cangyuan Li, Siyang Cai, Ying Wang, Yinhe Han Published: 2026-03-10Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-03-10 | cs.LG | ai-safety, cslg, preprint | E5 / R3 (93%) | - |
| $V_{0.5}$: Generalist Value Model as a Prior for Sparse RL Rollouts De-Chuan Zhan, Han-Jia Ye, Hongyan Hao, Qi Gu Published: 2026-03-11Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-03-11 | cs.LG | ai-safety, cslg, preprint | E5 / R3 (95%) | - |
| AI-Enhanced Spatial Cellular Traffic Demand Prediction with Contextual Clustering and Error Correction for 5G/6G Planning Colin Brown, Halim Yanikomeroglu, Mohamad Alkadamani Published: 2026-03-11Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-03-11 | cs.LG | ai-safety, cslg, preprint | E5 / R3 (94%) | - |
| Attention Gathers, MLPs Compose: A Causal Analysis of an Action-Outcome Circuit in VideoViT Sai V R Chereddy Published: 2026-03-11Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-03-11 | cs.LG | ai-safety, cslg, preprint | E5 / R3 (94%) | - |
| Causal Concept Graphs in LLM Latent Space for Stepwise Reasoning Faiza Feroz, Md Muntaqim Meherab, Noor Islam S. Mohammad Published: 2026-03-11Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-03-11 | cs.LG | ai-safety, cslg, preprint | E6 / R4 (97%) | - |
| Continuous Diffusion Transformers for Designing Synthetic Regulatory Elements Jonathan Liu, Kia Ghods Published: 2026-03-11Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-03-11 | cs.LG | ai-safety, cslg, preprint | E6 / R4 (98%) | - |
| Contract And Conquer: How to Provably Compute Adversarial Examples for a Black-Box Model? Anna Chistyakova, Mikhail Pautov Published: 2026-03-11Area: cs.LGCitations: - Tags: adversarial-robustness, ai-safety, cslg, preprint | 2026-03-11 | cs.LG | adversarial-robustness, ai-safety, cslg, preprint | E4 / R3 (98%) | - |
| CUPID: A Plug-in Framework for Joint Aleatoric and Epistemic Uncertainty Estimation with a Single Model Xinran Xu, Xiuyi Fan Published: 2026-03-11Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-03-11 | cs.LG | ai-safety, cslg, preprint | E6 / R4 (96%) | - |
| Designing Service Systems from Textual Evidence David Simchi-Levi, Hanwei Li, Hongyu Chen, Ruicheng Ao Published: 2026-03-11Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-03-11 | cs.LG | ai-safety, cslg, preprint | E5 / R3 (96%) | - |
| Domain-Adaptive Health Indicator Learning with Degradation-Stage Synchronized Sampling and Cross-Domain Autoencoder Gawon Lee, Hanbyeol Park, Hyerim Bae, Jungho Choo Published: 2026-03-11Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-03-11 | cs.LG | ai-safety, cslg, preprint | E5 / R3 (95%) | - |
| Dynamics-Predictive Sampling for Active RL Finetuning of Large Reasoning Models Heming Zou, Qi Wang, Xiangyang Ji, Yixiu Mao Published: 2026-03-11Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-03-11 | cs.LG | ai-safety, cslg, preprint | E5 / R3 (96%) | - |
| Effective Dataset Distillation for Spatio-Temporal Forecasting with Bi-dimensional Compression Kijung Shin, Taehyung Kwon, Yeongho Kim, Yeonje Choi Published: 2026-03-11Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-03-11 | cs.LG | ai-safety, cslg, preprint | E5 / R3 (93%) | - |
| Federated Active Learning Under Extreme Non-IID and Global Class Imbalance Chen-Chen Zong, Sheng-Jun Huang Published: 2026-03-11Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-03-11 | cs.LG | ai-safety, cslg, preprint | E5 / R3 (94%) | - |
| Gradient Flow Drifting: Generative Modeling via Wasserstein Gradient Flows of KDE-Approximated Divergences Jiarui Cao, Yuxin Liu, Zixuan Wei Published: 2026-03-11Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-03-11 | cs.LG | ai-safety, cslg, preprint | E5 / R3 (95%) | - |
| Graph Tokenization for Bridging Graphs and Transformers Cheng Yang, Chuan Shi, Enmao Diao, Zeyuan Guo Published: 2026-03-11Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-03-11 | cs.LG | ai-safety, cslg, preprint | E5 / R3 (94%) | - |
| Hindsight-Anchored Policy Optimization: Turning Failure into Feedback in Sparse Reward Settings Devin Chen, Kai Wei, Ke Wang, Yuning Wu Published: 2026-03-11Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-03-11 | cs.LG | ai-safety, cslg, preprint | E5 / R3 (92%) | - |
| Historical Consensus: Preventing Posterior Collapse via Iterative Selection of Gaussian Mixture Priors Jian Zhang, Zegu Zhang Published: 2026-03-11Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-03-11 | cs.LG | ai-safety, cslg, preprint | E5 / R3 (96%) | - |
| Implicit Statistical Inference in Transformers: Approximating Likelihood-Ratio Tests In-Context Faris Chaudhry, Siddhant Gadkari Published: 2026-03-11Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-03-11 | cs.LG | ai-safety, cslg, preprint | E5 / R3 (95%) | - |
| Jailbreak Scaling Laws for Large Language Models: Polynomial-Exponential Crossover Annesya Banerjee, Cengiz Pehlevan, Indranil Halder Published: 2026-03-11Area: cs.LGCitations: - Tags: adversarial-robustness, ai-safety, cslg, preprint | 2026-03-11 | cs.LG | adversarial-robustness, ai-safety, cslg, preprint | E6 / R3 (96%) | - |
| LookaheadKV: Fast and Accurate KV Cache Eviction by Glimpsing into the Future without Generation Akhil Kedia, Hyemi Jang, Ingyu Seong, Jinwoo Ahn Published: 2026-03-11Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-03-11 | cs.LG | ai-safety, cslg, preprint | E5 / R3 (95%) | - |
| Neural Field Thermal Tomography: A Differentiable Physics Framework for Non-Destructive Evaluation Aditya Sood, Christine Allen-Blanchette, Dongzhe Zheng, Tao Zhong Published: 2026-03-11Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint, safety-evaluation | 2026-03-11 | cs.LG | ai-safety, cslg, preprint, safety-evaluation | E5 / R3 (94%) | - |
| On the Learning Dynamics of Two-layer Linear Networks with Label Noise SGD Andi Han, Junchi Yan, Mingze Wang, Taiji Suzuki Published: 2026-03-11Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-03-11 | cs.LG | ai-safety, cslg, preprint | E5 / R3 (93%) | - |
| Optimal Expert-Attention Allocation in Mixture-of-Experts: A Scalable Law for Dynamic Model Design Changxin Tian, Jia Liu, Junzhuo Li, Peijie Jiang Published: 2026-03-11Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-03-11 | cs.LG | ai-safety, cslg, preprint | E4 / R3 (94%) | - |
| Procedural Fairness via Group Counterfactual Explanation Gideon Popoola, John Sheppard Published: 2026-03-11Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-03-11 | cs.LG | ai-safety, cslg, preprint | E5 / R3 (94%) | - |
| Protein Counterfactuals via Diffusion-Guided Latent Optimization Lukas Kades, Sidney Bender, Weronika K艂os Published: 2026-03-11Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-03-11 | cs.LG | ai-safety, cslg, preprint | E6 / R4 (96%) | - |
| Reinforcement Learning with Conditional Expectation Reward Caijun Xu, Changyi Xiao, Yixin Cao Published: 2026-03-11Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-03-11 | cs.LG | ai-safety, cslg, preprint | E5 / R3 (95%) | - |
| Representation Finetuning for Continual Learning Fengyu Cong, Haihua Luo, Huiyan Xue, Qi Xu Published: 2026-03-11Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-03-11 | cs.LG | ai-safety, cslg, preprint | E4 / R3 (94%) | - |
| Safe RLHF Beyond Expectation: Stochastic Dominance for Universal Spectral Risk Control Ativ Joshi, Rajarshi Bhattacharjee, Scott Niekum, Yaswanth Chittepu Published: 2026-03-11Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-03-11 | cs.LG | ai-safety, cslg, preprint | E6 / R3 (96%) | - |
| SCORE: Replacing Layer Stacking with Contractive Recurrent Depth Guillaume Godin Published: 2026-03-11Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-03-11 | cs.LG | ai-safety, cslg, preprint | E5 / R4 (97%) | - |
| Task-Conditioned Routing Signatures in Sparse Mixture-of-Experts Transformers Mynampati Sri Ranganadha Avinash Published: 2026-03-11Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-03-11 | cs.LG | ai-safety, cslg, preprint | E4 / R3 (95%) | - |