{"list":"other","total":52,"rows":[{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"id":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"id":"2005.11401","title":"Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks","created":"2020-05-22","cited_by_count":9297},{"id":"1908.10084","title":"Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks","created":"2019-08-27","cited_by_count":9170},{"id":"2505.09388","title":"Qwen3 Technical Report","created":"2025-05-14","cited_by_count":8820},{"id":"2305.18290","title":"Direct Preference Optimization: Your Language Model is Secretly a Reward Model","created":"2023-05-29","cited_by_count":8065},{"id":"2309.06180","title":"Efficient Memory Management for Large Language Model Serving with PagedAttention","created":"2023-09-12","cited_by_count":5944},{"id":"2412.15115","title":"Qwen2.5 Technical Report","created":"2024-12-19","cited_by_count":4942},{"id":"2204.05862","title":"Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback","created":"2022-04-12","cited_by_count":3720},{"id":"2205.14135","title":"FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness","created":"2022-05-27","cited_by_count":3673},{"id":"2309.16609","title":"Qwen Technical Report","created":"2023-09-28","cited_by_count":3344},{"id":"2212.08073","title":"Constitutional AI: Harmlessness from AI Feedback","created":"2022-12-15","cited_by_count":3050},{"id":"2503.14476","title":"DAPO: An Open-Source LLM Reinforcement Learning System at Scale","created":"2025-03-18","cited_by_count":2810},{"id":"2307.08691","title":"FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning","created":"2023-07-17","cited_by_count":2598},{"id":"2308.12950","title":"Code Llama: Open Foundation Models for Code","created":"2023-08-24","cited_by_count":2139},{"id":"2004.10964","title":"Don't Stop Pretraining: Adapt Language Models to Domains and Tasks","created":"2020-04-23","cited_by_count":1565},{"id":"1903.10676","title":"SciBERT: A Pretrained Language Model for Scientific Text","created":"2019-03-26","cited_by_count":1414},{"id":"2002.08155","title":"CodeBERT: A Pre-Trained Model for Programming and Natural Languages","created":"2020-02-19","cited_by_count":1310},{"id":"2305.11206","title":"LIMA: Less Is More for Alignment","created":"2023-05-18","cited_by_count":1100},{"id":"2007.15779","title":"Domain-Specific Language Model Pretraining for Biomedical Natural Language Processing","created":"2020-07-31","cited_by_count":1009},{"id":"2310.06452","title":"Understanding the Effects of RLHF on LLM Generalisation and Diversity","created":"2023-10-10","cited_by_count":396},{"id":"2310.10631","title":"Llemma: An Open Language Model For Mathematics","created":"2023-10-16","cited_by_count":388},{"id":"2506.04178","title":"OpenThoughts: Data Recipes for Reasoning Models","created":"2025-06-04","cited_by_count":304},{"id":"2302.03241","title":"Continual Pre-training of Language Models","created":"2023-02-07","cited_by_count":198},{"id":"2205.11275","title":"RL with KL penalties is better viewed as Bayesian inference","created":"2022-05-23","cited_by_count":135},{"id":"2403.04706","title":"Common 7B Language Models Already Possess Strong Math Capabilities","created":"2024-03-07","cited_by_count":109},{"id":"2507.00432","title":"Does Math Reasoning Improve General LLM Capabilities? Understanding Transferability of LLM Reasoning","created":"2025-07-01","cited_by_count":106},{"id":"2405.14918","title":"AnalogCoder: Analog Circuit Design via Training-Free Code Generation","created":"2024-05-23","cited_by_count":84},{"id":"2302.05836","title":"Theory on Forgetting and Generalization of Continual Learning","created":"2023-02-12","cited_by_count":72},{"id":"2308.16406","title":"CktGNN: Circuit Graph Neural Network for Electronic Design Automation","created":"2023-08-31","cited_by_count":58},{"id":"2310.05506","title":"MuggleMath: Assessing the Impact of Query and Response Augmentation on Math Reasoning","created":"2023-10-09","cited_by_count":45},{"id":"2505.17508","title":"On the Design of KL-Regularized Policy Gradient Algorithms for LLM Reasoning","created":"2025-05-23","cited_by_count":30},{"id":"2409.14739","title":"AmpAgent: An LLM-based Multi-Agent System for Multi-stage Amplifier Schematic Design from Literature for Process and Performance Porting","created":"2024-09-23","cited_by_count":29},{"id":"2405.09045","title":"AMSNet: Netlist Dataset for AMS Circuits","created":"2024-05-15","cited_by_count":25},{"id":"2406.18873","title":"LayoutCopilot: An LLM-powered Multi-agent Collaborative Framework for Interactive Analog Layout Design","created":"2024-06-27","cited_by_count":25},{"id":"2411.12930","title":"LEDRO: LLM-Enhanced Design Space Reduction and Optimization for Analog Circuits","created":"2024-11-19","cited_by_count":22},{"id":"2411.13560","title":"AMSnet-KG: A Netlist Dataset for LLM-based AMS Circuit Auto-Design Using Knowledge Graph RAG","created":"2024-11-07","cited_by_count":16},{"id":"2505.24138","title":"AMSbench: A Comprehensive Benchmark for Evaluating MLLM Capabilities in AMS Circuits","created":"2025-05-30","cited_by_count":15},{"id":"2507.10616","title":"Scalpel vs. Hammer: GRPO Amplifies Existing Capabilities, SFT Replaces Them","created":"2025-07-13","cited_by_count":15},{"id":"2508.02518","title":"AnalogCoder-Pro: Unifying Analog Circuit Generation and Optimization via Multi-modal LLMs","created":"2025-08-04","cited_by_count":15},{"id":"2502.04380","title":"Diversity as a Reward: Fine-Tuning LLMs on a Mixture of Domain-Undetermined Data","created":"2025-02-05","cited_by_count":13},{"id":"2502.02764","title":"LLM-USO: Large Language Model-based Universal Sizing Optimizer","created":"2025-02-04","cited_by_count":11},{"id":"2506.03122","title":"AUTOCIRCUIT-RL: Reinforcement Learning-Driven LLM for Automated Circuit Topology Generation","created":"2025-06-03","cited_by_count":11},{"id":"2410.20553","title":"SPICEPilot: Navigating SPICE Code Generation and Simulation with AI Guidance","created":"2024-10-27","cited_by_count":10},{"id":"2505.09155","title":"AMSnet 2.0: A Large AMS Database with AI Segmentation for Net Detection","created":"2025-05-14","cited_by_count":9},{"id":"2505.12762","title":"IDEAL: Data Equilibrium Adaptation for Multi-Capability Language Model Alignment","created":"2025-05-19","cited_by_count":8},{"id":"2504.11497","title":"LLM-based AI Agent for Sizing of Analog and Mixed Signal Circuit","created":"2025-04-14","cited_by_count":6},{"id":"2508.05113","title":"EasySize: Elastic Analog Circuit Sizing via LLM-Guided Heuristic Search","created":"2025-08-07","cited_by_count":5},{"id":"2506.09099","title":"Too Big to Think: Capacity, Memorization, and Generalization in Pre-Trained Transformers","created":"2025-06-10","cited_by_count":4},{"id":"2402.11093","title":"Modular Graph Extraction for Handwritten Circuit Diagram Images","created":"2024-02-16","cited_by_count":1}],"next_cursor":null}