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 |
|---|---|---|---|---|---|
| Unified Static-Dynamic Pruning for Efficient LLM Inference Jaeyoung Do, Jinhyeok Kim, Yejoon Lee Published: 2026-07-24Area: cs.DCCitations: - Tags: ai-safety, csdc, preprint | 2026-07-24 | cs.DC | ai-safety, csdc, preprint | E10 / R8 (91%) | - |
| A Framework for Reputation Aware Uninorm-driven Consensus Algorithms for Blockchain Networks Bruno Ramos-Cruz, David Richerby, Javier Andreu-Perez, Luis Mart铆nez Published: 2026-07-22Area: cs.DCCitations: - Tags: ai-safety, csdc, preprint | 2026-07-22 | cs.DC | ai-safety, csdc, preprint | E8 / R7 (93%) | - |
| Fine-grained Computation-Communication Overlap via Tile-level Signaling and Scheduling for Mixture-of-Experts Anna Wingkvist, Minyu Cui, Morgan Ericsson Published: 2026-07-21Area: cs.DCCitations: - Tags: ai-safety, csdc, preprint | 2026-07-21 | cs.DC | ai-safety, csdc, preprint | E9 / R7 (90%) | - |
| Talaria: Session-Aware Serverless Serving of Hundred-Billion-Parameter LLMs Derek Li, Frank Du, Goalen Gao, Unicornt Zhao Published: 2026-07-19Area: cs.DCCitations: 15 Tags: ai-safety, csdc, preprint | 2026-07-19 | cs.DC | ai-safety, csdc, preprint | E19 / R15 (90%) | 15 |
| JoyNexus: Service-Oriented Multi-Tenant Post-Training for VLA Models Chen Zhao, Chen Zhou, Haoran Sun, Hedan Yang Published: 2026-07-17Area: cs.DCCitations: - Tags: ai-safety, csdc, preprint | 2026-07-17 | cs.DC | ai-safety, csdc, preprint | E14 / R12 (90%) | - |
| Scalable LLM Agent Tool Access in the Cloud Biao Lyu, Changgang Zheng, Enge Song, Gianni Antichi Published: 2026-07-17Area: cs.DCCitations: 64 Tags: ai-safety, csdc, preprint | 2026-07-17 | cs.DC | ai-safety, csdc, preprint | E12 / R12 (91%) | 64 |
| EdgeFaaS: A Function-based Framework for Edge Computing Ming Zhao, Neha Vadnere, Sreehari Sadesh, Yitao Chen Published: 2026-07-16Area: cs.DCCitations: - Tags: ai-safety, csdc, preprint | 2026-07-16 | cs.DC | ai-safety, csdc, preprint | E10 / R9 (91%) | - |
| The Cost and Network Limits of Space-Based AI Compute Kees van Berkel Published: 2026-07-15Area: cs.DCCitations: 32 Tags: ai-safety, csdc, preprint | 2026-07-15 | cs.DC | ai-safety, csdc, preprint | E8 / R8 (94%) | 32 |
| Toward Trustworthy Autonomous Science: A Two-Year Community Roadmap Amanda Randles, Anna Giannakou, Ben Mintz, Carrie Eckert Published: 2026-07-13Area: cs.DCCitations: - Tags: ai-safety, csdc, preprint | 2026-07-13 | cs.DC | ai-safety, csdc, preprint | E10 / R9 (90%) | - |
| Automated Tensor Scheduling for Hybrid CPU-GPU LLM Inference on Consumer Devices Hongyi Ye, Mingyang Li, Wu-jun Li, Yangyijian Liu Published: 2026-07-11Area: cs.DCCitations: - Tags: ai-safety, csdc, preprint | 2026-07-11 | cs.DC | ai-safety, csdc, preprint | E11 / R10 (93%) | - |
| Automated Tensor Scheduling for Hybrid CPU-GPU LLM Inference on Consumer Devices Hongyi Ye, Mingyang Li, Wu-jun Li, Yangyijian Liu Published: 2026-07-11Area: cs.DCCitations: - Tags: ai-safety, csdc, preprint | 2026-07-11 | cs.DC | ai-safety, csdc, preprint | E10 / R10 (95%) | - |
| STEEL: Sparsity-Aware Fused Attention for Energy-Efficient Long-Sequence Inference on AMD's XDNA NPU Francesco Conti, Gagandeep Singh, Joseph Melber, Kristof Denolf Published: 2026-07-10Area: cs.DCCitations: - Tags: ai-safety, csdc, preprint | 2026-07-10 | cs.DC | ai-safety, csdc, preprint | E8 / R7 (95%) | - |
| SMetric: Rethink LLM Scheduling for Serving Agents with Balanced Session-centric Scheduling Chenguang Fang, Haibo Chen, Jiahao Wang, Jinbo Han Published: 2026-07-09Area: cs.DCCitations: - Tags: ai-safety, csdc, preprint | 2026-07-09 | cs.DC | ai-safety, csdc, preprint | E11 / R10 (94%) | - |
| UBEP: Re-architecting Expert Parallelism Communication Library for Production Superpods Baochuan Yang, Chang Liu, Guanhua Li, Guihai Chen Published: 2026-07-07Area: cs.DCCitations: - Tags: ai-safety, csdc, preprint | 2026-07-07 | cs.DC | ai-safety, csdc, preprint | E10 / R10 (94%) | - |
| UBEP: Re-architecting Expert Parallelism Communication Library for Production Superpods Baochuan Yang, Chang Liu, Guanhua Li, Guihai Chen Published: 2026-07-07Area: cs.DCCitations: - Tags: ai-safety, csdc, preprint | 2026-07-07 | cs.DC | ai-safety, csdc, preprint | E8 / R5 (94%) | - |
| A Workflow-Aware Serving Layer for Agentic Applications Chun Tao, Hanchen Yang, Jiayi Qian, Souvik Kundu Published: 2026-07-03Area: cs.DCCitations: - Tags: ai-safety, csdc, preprint | 2026-07-03 | cs.DC | ai-safety, csdc, preprint | E12 / R13 (93%) | - |
| SPORK: Self-Speculative Forking to Accelerate Agentic LLM Inference Huajun Bai, Huichuan Zheng, Jiwu Shu, Weiwei Lv Published: 2026-07-03Area: cs.DCCitations: - Tags: ai-safety, csdc, preprint | 2026-07-03 | cs.DC | ai-safety, csdc, preprint | E14 / R10 (94%) | - |
| Fine-Grained Computation Offload for Off-the-Shelf Servers in Tens of Lines Bojie Li Published: 2026-07-02Area: cs.DCCitations: 25 Tags: ai-safety, csdc, preprint | 2026-07-02 | cs.DC | ai-safety, csdc, preprint | E10 / R6 (92%) | 25 |
| Mixture-of-Parallelisms: Towards Memory-Efficient Training Stack for Mixture-of-Experts Models Semih Yavuz, Shafiq Joty, Shrey Pandit, Silvio Savarese Published: 2026-07-02Area: cs.DCCitations: - Tags: ai-safety, csdc, preprint | 2026-07-02 | cs.DC | ai-safety, csdc, preprint | E7 / R4 (96%) | - |
| Securing People and their Machines Against Major Faults Ehud Shapiro, Idit Keidar, Ohad Eitan Published: 2026-07-02Area: cs.DCCitations: - Tags: ai-safety, csdc, preprint | 2026-07-02 | cs.DC | ai-safety, csdc, preprint | E8 / R5 (96%) | - |
| Towards Load-Aware Prefill Deflection for Disaggregated LLM Serving Anjaly Parayil, Renee St. Amant, Shrikara Arun, Srikant Bharadwaj Published: 2026-07-02Area: cs.DCCitations: - Tags: ai-safety, csdc, preprint | 2026-07-02 | cs.DC | ai-safety, csdc, preprint | E7 / R4 (97%) | - |
| From Tensor Buffer to Distributed Memory Hierarchy: A Survey of KV Cache Management for LLM Serving Jie Li, Tongyang Wang, Yong Chen Published: 2026-06-30Area: cs.DCCitations: - Tags: ai-safety, csdc, preprint | 2026-06-30 | cs.DC | ai-safety, csdc, preprint | E10 / R9 (91%) | - |
| Spotlight: Synergizing Seed Exploration and Spot GPUs for DiT RL Post-Training Dakai An, Dmitrii Ustiugov, Jiamang Wang, Ju Huang Published: 2026-06-17Area: cs.DCCitations: - Tags: ai-safety, csdc, preprint | 2026-06-17 | cs.DC | ai-safety, csdc, preprint | E9 / R5 (98%) | - |
| SMEPilot: Characterizing and Optimizing LLM Inference with Scalable Matrix Extensions Feiyang Chen, Haibo Chen Published: 2026-06-15Area: cs.DCCitations: - Tags: ai-safety, csdc, preprint | 2026-06-15 | cs.DC | ai-safety, csdc, preprint | E9 / R4 (97%) | - |
| PreLort: Prefix-Nested LoRA for Federated Fine-Tuning under Rank Heterogeneity Andrej Jovanovic, Karthik Nandakumar, Muhammad Waseem, Nicholas D. Lane Published: 2026-06-14Area: cs.DCCitations: - Tags: ai-safety, csdc, preprint | 2026-06-14 | cs.DC | ai-safety, csdc, preprint | E10 / R5 (98%) | - |
| Quantifying the Impact of Lossy Compression on Neural Generative Surrogate Modeling Charles Jekel, Harshitha Menon, Peter Lindstrom, Valerio Pascucci Published: 2026-06-14Area: cs.DCCitations: - Tags: ai-safety, csdc, preprint | 2026-06-14 | cs.DC | ai-safety, csdc, preprint | E8 / R4 (96%) | - |
| CoAgent: Concurrency Control for Multi-Agent Systems Dingyan Zhang, Haibo Chen, Hongtao Lyu, Mingyu Wu Published: 2026-06-13Area: cs.DCCitations: - Tags: ai-safety, csdc, preprint | 2026-06-13 | cs.DC | ai-safety, csdc, preprint | E7 / R4 (95%) | - |
| Cost-Aware Speculative Execution for LLM-Agent Workflows: An Integrated Five-Dimension Method Faisal Fareed Published: 2026-06-05Area: cs.DCCitations: - Tags: ai-safety, csdc, preprint | 2026-06-05 | cs.DC | ai-safety, csdc, preprint | E13 / R10 (94%) | - |
| Autonomic Federated-Market Orchestration for the Edge-Cloud Continuum Abhishek Kumar, Jukka Riekki, Lauri Lov茅n, Roberto Morabito Published: 2026-05-26Area: cs.DCCitations: - Tags: ai-safety, csdc, preprint | 2026-05-26 | cs.DC | ai-safety, csdc, preprint | E16 / R14 (90%) | - |
| When Agents Control Robots: A Zero Trust Policy Model for Agentic Cyber-Physical Systems Kavishka Fernando, Susan Rea, Tharindu Ranathunga Published: 2026-05-25Area: cs.DCCitations: 17 Tags: ai-safety, csdc, preprint | 2026-05-25 | cs.DC | ai-safety, csdc, preprint | E14 / R17 (92%) | 17 |