{"list":"other","total":67,"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":"2407.21783","title":"The Llama 3 Herd of Models","created":"2024-07-31","cited_by_count":14715},{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"id":"2110.14168","title":"Training Verifiers to Solve Math Word Problems","created":"2021-10-27","cited_by_count":10109},{"id":"2210.03629","title":"ReAct: Synergizing Reasoning and Acting in Language Models","created":"2022-10-06","cited_by_count":8695},{"id":"2306.05685","title":"Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena","created":"2023-06-09","cited_by_count":8626},{"id":"2204.02311","title":"PaLM: Scaling Language Modeling with Pathways","created":"2022-04-05","cited_by_count":5326},{"id":"1801.01290","title":"Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor","created":"2018-01-04","cited_by_count":4885},{"id":"1612.00796","title":"Overcoming catastrophic forgetting in neural networks","created":"2016-12-02","cited_by_count":4787},{"id":"2303.11366","title":"Reflexion: Language Agents with Verbal Reinforcement Learning","created":"2023-03-20","cited_by_count":4276},{"id":"2302.04761","title":"Toolformer: Language Models Can Teach Themselves to Use Tools","created":"2023-02-09","cited_by_count":4182},{"id":"2304.03442","title":"Generative Agents: Interactive Simulacra of Human Behavior","created":"2023-04-07","cited_by_count":3568},{"id":"2205.01068","title":"OPT: Open Pre-trained Transformer Language Models","created":"2022-05-02","cited_by_count":3512},{"id":"2303.17651","title":"Self-Refine: Iterative Refinement with Self-Feedback","created":"2023-03-30","cited_by_count":3442},{"id":"2305.16291","title":"Voyager: An Open-Ended Embodied Agent with Large Language Models","created":"2023-05-25","cited_by_count":2191},{"id":"2206.04615","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","created":"2022-06-09","cited_by_count":1998},{"id":"2308.08155","title":"AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation","created":"2023-08-16","cited_by_count":1988},{"id":"2308.00352","title":"MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework","created":"2023-08-01","cited_by_count":1808},{"id":"2403.04132","title":"Chatbot Arena: An Open Platform for Evaluating LLMs by Human Preference","created":"2024-03-07","cited_by_count":1184},{"id":"1811.11682","title":"Experience Replay for Continual Learning","created":"2018-11-28","cited_by_count":1095},{"id":"2302.00487","title":"A Comprehensive Survey of Continual Learning: Theory, Method and Application","created":"2023-01-31","cited_by_count":872},{"id":"2210.02414","title":"GLM-130B: An Open Bilingual Pre-trained Model","created":"2022-10-05","cited_by_count":843},{"id":"2104.14337","title":"Dynabench: Rethinking Benchmarking in NLP","created":"2021-04-07","cited_by_count":459},{"id":"2401.08417","title":"Contrastive Preference Optimization: Pushing the Boundaries of LLM Performance in Machine Translation","created":"2024-01-16","cited_by_count":394},{"id":"2206.10498","title":"PlanBench: An Extensible Benchmark for Evaluating Large Language Models on Planning and Reasoning about Change","created":"2022-06-21","cited_by_count":382},{"id":"2302.09210","title":"How Good Are GPT Models at Machine Translation? A Comprehensive Evaluation","created":"2023-02-18","cited_by_count":348},{"id":"2310.18018","title":"NLP Evaluation in trouble: On the Need to Measure LLM Data Contamination for each Benchmark","created":"2023-10-27","cited_by_count":348},{"id":"2210.01240","title":"Language Models Are Greedy Reasoners: A Systematic Formal Analysis of Chain-of-Thought","created":"2022-10-03","cited_by_count":337},{"id":"2402.10669","title":"Humans or LLMs as the Judge? A Study on Judgement Biases","created":"2024-02-16","cited_by_count":323},{"id":"2103.17230","title":"Rainbow Memory: Continual Learning with a Memory of Diverse Samples","created":"2021-03-31","cited_by_count":273},{"id":"2305.16653","title":"AdaPlanner: Adaptive Planning from Feedback with Language Models","created":"2023-05-26","cited_by_count":196},{"id":"2304.04675","title":"Multilingual Machine Translation with Large Language Models: Empirical Results and Analysis","created":"2023-04-10","cited_by_count":160},{"id":"1810.10815","title":"Adaptive Online Learning in Dynamic Environments","created":"2018-10-25","cited_by_count":133},{"id":"2310.01557","title":"SmartPlay: A Benchmark for LLMs as Intelligent Agents","created":"2023-10-02","cited_by_count":125},{"id":"2310.10134","title":"CLIN: A Continually Learning Language Agent for Rapid Task Adaptation and Generalization","created":"2023-10-16","cited_by_count":95},{"id":"2402.17574","title":"Agent-Pro: Learning to Evolve via Policy-Level Reflection and Optimization","created":"2024-02-27","cited_by_count":94},{"id":"2304.02210","title":"Document-Level Machine Translation with Large Language Models","created":"2023-04-05","cited_by_count":90},{"id":"2402.03610","title":"RAP: Retrieval-Augmented Planning with Contextual Memory for Multimodal LLM Agents","created":"2024-02-06","cited_by_count":80},{"id":"2306.07209","title":"Data-Copilot: Bridging Billions of Data and Humans with Autonomous Workflow","created":"2023-06-12","cited_by_count":76},{"id":"2404.05221","title":"LLM Reasoners: New Evaluation, Library, and Analysis of Step-by-Step Reasoning with Large Language Models","created":"2024-04-08","cited_by_count":70},{"id":"2405.16247","title":"AutoManual: Constructing Instruction Manuals by LLM Agents via Interactive Environmental Learning","created":"2024-05-25","cited_by_count":61},{"id":"2404.13813","title":"From LLM to NMT: Advancing Low-Resource Machine Translation with Claude","created":"2024-04-22","cited_by_count":58},{"id":"2302.01047","title":"Real-Time Evaluation in Online Continual Learning: A New Hope","created":"2023-02-02","cited_by_count":47},{"id":"2405.20267","title":"Auto-Arena: Automating LLM Evaluations with Agent Peer Battles and Committee Discussions","created":"2024-05-30","cited_by_count":42},{"id":"2503.15138","title":"VideoGen-of-Thought: Step-by-step generating multi-shot video with minimal manual intervention","created":"2025-03-19","cited_by_count":36},{"id":"2412.06394","title":"GameArena: Evaluating LLM Reasoning through Live Computer Games","created":"2024-12-09","cited_by_count":32},{"id":"2403.07548","title":"Online Continual Learning For Interactive Instruction Following Agents","created":"2024-03-12","cited_by_count":22},{"id":"2405.07472","title":"GaussianVTON: 3D Human Virtual Try-ON via Multi-Stage Gaussian Splatting Editing with Image Prompting","created":"2024-05-13","cited_by_count":22},{"id":"2508.10858","title":"Hierarchical Fine-grained Preference Optimization for Physically Plausible Video Generation","created":"2025-08-14","cited_by_count":21},{"id":"2503.06689","title":"DependEval: Benchmarking LLMs for Repository Dependency Understanding","created":"2025-03-09","cited_by_count":17},{"id":"2504.13122","title":"VistaDPO: Video Hierarchical Spatial-Temporal Direct Preference Optimization for Large Video Models","created":"2025-04-17","cited_by_count":17},{"id":"2409.00755","title":"Trusted Unified Feature-Neighborhood Dynamics for Multi-View Classification","created":"2024-09-01","cited_by_count":15},{"id":"2210.11694","title":"Multi-View Reasoning: Consistent Contrastive Learning for Math Word Problem","created":"2022-10-21","cited_by_count":13},{"id":"2409.07388","title":"Recent Advances in Multimodal Affective Computing: An NLP Perspective","created":"2024-09-11","cited_by_count":13},{"id":"2404.09640","title":"CREST: Cross-modal Resonance through Evidential Deep Learning for Enhanced Zero-Shot Learning","created":"2024-04-15","cited_by_count":12},{"id":"2408.16272","title":"Beyond Uncertainty: Evidential Deep Learning for Robust Video Temporal Grounding","created":"2024-08-29","cited_by_count":10},{"id":"2504.00043","title":"CrossWordBench: Evaluating the Reasoning Capabilities of LLMs and LVLMs with Controllable Puzzle Generation","created":"2025-03-30","cited_by_count":10},{"id":"2207.11901","title":"A Closed-Loop Perception, Decision-Making and Reasoning Mechanism for Human-Like Navigation","created":"2022-07-25","cited_by_count":6},{"id":"2408.13123","title":"Evidential Deep Partial Multi-View Classification With Discount Fusion","created":"2024-08-23","cited_by_count":6},{"id":"2410.02768","title":"Uncertainty-Guided Self-Questioning and Answering for Video-Language Alignment","created":"2024-09-17","cited_by_count":6},{"id":"2507.10432","title":"Text-Visual Semantic Constrained AI-Generated Image Quality Assessment","created":"2025-07-14","cited_by_count":6},{"id":"2111.08364","title":"Learning to Navigate in a VUCA Environment: Hierarchical Multi-expert Approach","created":"2021-11-16","cited_by_count":5},{"id":"2502.05907","title":"EvolvingAgent: Curriculum Self-evolving Agent with Continual World Model for Long-Horizon Tasks","created":"2025-02-09","cited_by_count":5},{"id":"2310.09619","title":"An Expression Tree Decoding Strategy for Mathematical Equation Generation","created":"2023-10-14","cited_by_count":4}],"next_cursor":null}