- How Much Parallelism Is "Free"? A Principle of Near-Free Parallelism for Parallel Decoding
2026/05/29 by Minghua He, Lingzhe Zhang, Yuan Liu +2 · 1 voice
Computer Science · #Advanced Data Storage Technologies #Data parallelism #Decoding methods #Error Correcting Code Techniques #Executable #Instruction-level parallelism #Parallel Computing and Optimization Techniques #Parallelism (grammar) #Parameterized complexity #Security token #Task parallelism #cs.PF
- The Bridge-Garden Dilemma in LLM Distillation: Why Mixing Hard and Soft Labels Works
2026/05/25 by Guanghui Wang, Kaiwen Lv Kacuila, Zhiyong Yang +5 · 1 voice
Computer Science · #Code (set theory) #Decomposition #Dilemma #Domain Adaptation and Few-Shot Learning #Face (sociological concept) #Inference #Intelligent Tutoring Systems and Adaptive Learning #Matching (statistics) #Mixing (physics) #Security token #Suite #Topic Modeling #cs.LG
- Beyond Accuracy: Unveiling Inefficiency Patterns in Tool-Integrated Reasoning
2026/04/07 by Qisheng Su, Shiting Huang, Zhen Fang +3 · 1 voice
Computer Science · #AI-based Problem Solving and Planning #Advanced Software Engineering Methodologies #Constraint Satisfaction and Optimization #Context (archaeology) #Forcing (mathematics) #Inefficiency #Inference #Metric (unit) #Quality (philosophy) #Security token #cs.PF #cs.SE
- EffiPair: Improving the Efficiency of LLM-generated Code with Relative Contrastive Feedback
2026/04/06 by Samira Hajizadeh, Suman Jana · 1 voice
Computer Science · Materials Science · #Code (set theory) #Execution time #Machine Learning in Materials Science #Pairwise comparison #Profiling (computer programming) #Security token #Software Engineering Research #Speedup #Task (project management) #Topic Modeling #cs.AI #cs.CL #cs.LG #cs.PL #cs.SE
- Structured Distillation for Personalized Agent Memory: 11x Token Reduction with Retrieval Preservation
2026/03/13 by Sydney Lewis · 1 voice
Computer Science · #Context (archaeology) #Distillation #Information Retrieval and Search Behavior #Object (grammar) #Pipeline (software) #Recall #Reduction (mathematics) #Security token #Simple (philosophy) #Structured prediction #Topic Modeling #Web Data Mining and Analysis #cs.AI #cs.CL #cs.IR
- OptiLeak: Efficient Prompt Reconstruction via Reinforcement Learning in Multi-tenant LLM Services
2026/02/24 by Longxiang Wang, Xiang Zheng, Xuhao Zhang +3 · 1 voice
Computer Science · #Advanced Data Storage Technologies #Information leakage #Key (lock) #Overfitting #Preference #Ranking (information retrieval) #Reinforcement learning #Security and Verification in Computing #Security token #Software System Performance and Reliability #cs.AI #cs.CR
- Trust The Typical
2026/02/04 by Debargha Ganguly, Sreehari Sankar, Biyao Zhang +11 · 1 voice
Computer Science · #Advanced Malware Detection Techniques #Adversarial Robustness in Machine Learning #Blocking (statistics) #Distribution (mathematics) #Hate Speech and Cyberbullying Detection #Overhead (engineering) #Production (economics) #Security token #Space (punctuation) #cs.AI #cs.CL #cs.DC #cs.LG
- SimpleMem: Efficient Lifelong Memory for LLM Agents
2026/01/05 by Jiaqi Liu, Yaofeng Su, Peng Xia +5 · 1 voice · 6 citations
Computer Science · #Benchmark (surveying) #Context (archaeology) #Filter (signal processing) #Inference #Information Retrieval and Search Behavior #Pipeline (software) #Process (computing) #Scope (computer science) #Security token #Semantic Web and Ontologies #Topic Modeling #cs.AI
- RePo: Language Models with Context Re-Positioning
2025/12/16 by Huayang Li, Tianyu Zhao, Li, Huayang +5 · 2 voices
Computer Science · #Code (set theory) #Cognition #Cognitive load #Constant (computer programming) #Context (archaeology) #Domain Adaptation and Few-Shot Learning #Integer (computer science) #Language model #Multimodal Machine Learning Applications #Security token #Topic Modeling #cs.AI #cs.CL #cs.LG
- ChunkLLM: A Lightweight Pluggable Framework for Accelerating LLMs Inference
2025/09/28 by Haojie Ouyang, Jianwei Lv, Ouyang, Haojie +10 · 7 voices
Computer Science · #Adapter (computing) #Benchmark (surveying) #Cache #Feature selection #Handwritten Text Recognition Techniques #Inference #Natural Language Processing Techniques #Security token #Speedup #Topic Modeling #Transformer
- Your LLM Knows the Future: Uncovering Its Multi-Token Prediction Potential
2025/07/16 by Mohammad Samragh, Samragh, Mohammad, Arnav Kundu +12 · 4 voices · 16 citations
Computer Science · Social Sciences · #Artificial Intelligence in Law #Coherence (philosophical gambling strategy) #Consistency (knowledge bases) #Inference #Key (lock) #Language model #Law, AI, and Intellectual Property #Legal Education and Practice Innovations #Security token #Semantics (computer science) #Set (abstract data type)
- Mixtral of Experts
2024/01/08 by Albert Q. Jiang, Alexandre Sablayrolles, Jiang, Albert Q. +51 · 5 voices · 427 citations
Computer Science · Engineering · #Artificial intelligence #Code (set theory) #Computer network #Computer science #Context (archaeology) #Engineering #Feed forward #Inference #Language model #Layer (electronics) #License #Machine Learning and Algorithms #Machine Learning and Data Classification #Operating system #Process (computing) #Programming language #Router #Security token #Set (abstract data type) #Topic Modeling
- xVal: A Continuous Numerical Tokenization for Scientific Language Models
2023/10/04 by Siavash Golkar, M. Pettee, Golkar, Siavash +28 · 2 voices · 5 citations
Computer Science · Mathematics · #Algorithm #Artificial intelligence #Bit array #Computer science #ENCODE #Embedding #Encoding (memory) #Generalization #Inference #Language model #Mathematics #Natural Language Processing Techniques #Scheme (mathematics) #Security token #String (physics) #Text Readability and Simplification #Theoretical computer science #Topic Modeling #cs.AI #cs.CL #cs.LG #stat.ML