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 |
|---|---|---|---|---|---|
| CLIMB: A Clinical Multimorbidity Benchmark for Diagnosing Co-occurring Conditions through Multiturn Conversations Akhil Arora, Alexandra V. Kulinkina, Aniruddha Mukherjee, David Sasu Published: 2026-09-28Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-09-28 | cs.LG | ai-safety, cslg, preprint | - | - |
| Coding Agent Memory Post-training: Unlocking the Memory Potential of Pre-trained File Operations for Long-Horizon Tasks via Reinforcement Learning Cong Fang, Heming Xia, Jiayin Zhu, Kelong Mao Published: 2026-09-28Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-09-28 | cs.LG | ai-safety, cslg, preprint | - | - |
| Coding Agent Memory Post-training: Unlocking the Memory Potential of Pre-trained File Operations for Long-Horizon Tasks via Reinforcement Learning Cong Fang, Heming Xia, Jiayin Zhu, Kelong Mao Published: 2026-09-28Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-09-28 | cs.LG | ai-safety, cslg, preprint | E14 / R13 (94%) | - |
| Commutator Memory: Sparse, Path-Local Reading and Steering in Language Models John Sweeney Published: 2026-09-28Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-09-28 | cs.LG | ai-safety, cslg, preprint | - | - |
| Composable Decoding on the Probability Simplex: Theory and Implementation Ahmed Khaled Khamis, Haitham Bou-Ammar, Matthieu Zimmer, Rasul Tutunov Published: 2026-09-28Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-09-28 | cs.LG | ai-safety, cslg, preprint | - | - |
| CTP-FL: Common-Trajectory Gradient Prediction for Federated Learning Junkang Liu Published: 2026-09-28Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-09-28 | cs.LG | ai-safety, cslg, preprint | - | - |
| Cyclostationary Phase Conditioning for Medical Time Series Diffusion Jorge da Silva Goncalves, Julia E. Vogt, Michele Copetti, Samuel Ruiperez-Campillo Published: 2026-09-28Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-09-28 | cs.LG | ai-safety, cslg, preprint | E10 / R9 (95%) | - |
| Cyclostationary Phase Conditioning for Medical Time Series Diffusion Jorge da Silva Goncalves, Julia E. Vogt, Michele Copetti, Samuel Ruiperez-Campillo Published: 2026-09-28Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-09-28 | cs.LG | ai-safety, cslg, preprint | - | - |
| Direct Self-Evolving Optimization: Evolving LLMs without Challenger Training Jiayun Wang, Yu Wang, Yuyang Deng Published: 2026-09-28Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-09-28 | cs.LG | ai-safety, cslg, preprint | - | - |
| Distillation Defenses Easily Break After Reinforcement Learning Alexander Panfilov, Oliver Britton, Shidan Javaheri, Yarin Gal Published: 2026-09-28Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-09-28 | cs.LG | ai-safety, cslg, preprint | - | - |
| DivOPD: Spread Wide, Look Close for Asynchronous On-Policy Distillation of Multi-turn Agents Chaoxu Pang, Hanyang Wang, Jingqing Ruan, Ke Zeng Published: 2026-09-28Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-09-28 | cs.LG | ai-safety, cslg, preprint | - | - |
| d-OPD: Future-Aware On-Policy Distillation for Block Diffusion Language Models Qinghao Hu, Ruitao Liu, Song Han Published: 2026-09-28Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-09-28 | cs.LG | ai-safety, cslg, preprint | - | - |
| Do Temporal Link Predictors Need Learned Memory? A Smoothed-Count Baseline with a Handful of Parameters Ingo Scholtes, Lisi Qarkaxhija Published: 2026-09-28Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-09-28 | cs.LG | ai-safety, cslg, preprint | - | - |
| Do World Models Learn Global Understanding? Alexander Detkov, Matt Thomson Published: 2026-09-28Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-09-28 | cs.LG | ai-safety, cslg, preprint | - | - |
| Draft in Parallel, Condition Through Depth: Adjacent Causal Injection for Speculative Decoding Bo Jiang, Haocheng Sun, Haohui Zhang, Keyu Chen Published: 2026-09-28Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-09-28 | cs.LG | ai-safety, cslg, preprint | - | - |
| DR-net-Mamba: Selective State-Space Modeling for Long-Range ECG Time-Series Denoising Andreas P. Streich, Basile Morel, Julia E. Vogt, Samuel Ruiperez-Campillo Published: 2026-09-28Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-09-28 | cs.LG | ai-safety, cslg, preprint | - | - |
| Drug-Target Interaction Prediction via Hierarchical Sequential Cross-Attention over Chemical and Protein Language Models Abdelkrim Aries, Brigitte Vannier, Hamza Abdelali, Khadidja Henni Published: 2026-09-28Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-09-28 | cs.LG | ai-safety, cslg, preprint | - | - |
| Emergence, Not Bandwidth: Physical Coupling and the Limits of Learned Multi-Agent Communication Aniket Bera, Mihir Chauhan Published: 2026-09-28Area: cs.LGCitations: 12 Tags: ai-safety, cslg, preprint | 2026-09-28 | cs.LG | ai-safety, cslg, preprint | E12 / R6 (94%) | 12 |
| Emergence, Not Bandwidth: Physical Coupling and the Limits of Learned Multi-Agent Communication Aniket Bera, Mihir Chauhan Published: 2026-09-28Area: cs.LGCitations: 12 Tags: ai-safety, cslg, preprint | 2026-09-28 | cs.LG | ai-safety, cslg, preprint | E12 / R7 (93%) | 12 |
| Encoder-Sharing Hierarchical Federated Multi-Task Learning for VANETs M. Saeid HaghighiFard, Sinem Coleri Published: 2026-09-28Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-09-28 | cs.LG | ai-safety, cslg, preprint | - | - |
| EntroPack: Fast and Accurate Entropy-Coded Weight Compression at Arbitrary Bitrates Hong Zhang, Yingda Chen, Zhongjie Duan Published: 2026-09-28Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-09-28 | cs.LG | ai-safety, cslg, preprint | - | - |
| eval-unlearn: Benchmarking unlearning in Text-to-Image Diffusion Models Brandon Siao Xiang Ling, Francesco Leofante, Ji Shen Lim, Kai Sheng Ong Published: 2026-09-28Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-09-28 | cs.LG | ai-safety, cslg, preprint | - | - |
| Explainability from Training with Applications to TCR-Epitope Prediction Jiarui Li, Ramgopal Mettu, Samuel Landry, Zhengming Ding Published: 2026-09-28Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-09-28 | cs.LG | ai-safety, cslg, preprint | - | - |
| FLARE: Flow Matching with Local Axis-Angle Representations for Stochastic Micromagnetic Evolution Jianmin Li, Pengyu Li, Renjie Tong, Xuanlue Jiang Published: 2026-09-28Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-09-28 | cs.LG | ai-safety, cslg, preprint | - | - |
| FlexLoop: Depth-Elastic Looped Policies for Adaptive Test-Time Computation in Deep RL Longbo Huang, Ruishuo Chen, Xun Wang, Yu Chen Published: 2026-09-28Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-09-28 | cs.LG | ai-safety, cslg, preprint | - | - |
| FLOORA: A Human-Aligned Domain-Specific Language Model for Architectural Design Adam Gaier, Angela Ju, Beatriz Guerra, Bryan Lim Published: 2026-09-28Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-09-28 | cs.LG | ai-safety, cslg, preprint | E8 / R7 (93%) | - |
| From Attention Sensitivity to Layer Role: Revisiting Mixed-Precision Quantization of Transformers Adrian Weller, Mahmoudreza Babaei, Milad Hosseini, Nafiseh HosseinpourFardi Published: 2026-09-28Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-09-28 | cs.LG | ai-safety, cslg, preprint | - | - |
| From Data to Program: Fast & Direct Generative Program Inference from Empirical Data Leman Akoglu, Simon Kl眉ttermann, Xueying Ding Published: 2026-09-28Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-09-28 | cs.LG | ai-safety, cslg, preprint | - | - |
| From Preference to Reciprocity: Decentralized Matching with Empirically Grounded LLM-agent Based Modeling Pin Gao, Shipei Zeng, Wangxuan Fan, Xiangcheng Meng Published: 2026-09-28Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-09-28 | cs.LG | ai-safety, cslg, preprint | - | - |
| Frontier Learning: Training LLM Reasoners at the Edge of Capability Aurelien Lucchi, Ilija Bogunovic, Robin Faro, Shyam Sundhar Ramesh Published: 2026-09-28Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-09-28 | cs.LG | ai-safety, cslg, preprint | - | - |