{"list":"other","total":99,"rows":[{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459},{"id":"2005.11401","title":"Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks","created":"2020-05-22","cited_by_count":9297},{"id":"2505.09388","title":"Qwen3 Technical Report","created":"2025-05-14","cited_by_count":8820},{"id":"2210.03629","title":"ReAct: Synergizing Reasoning and Acting in Language Models","created":"2022-10-06","cited_by_count":8695},{"id":"2304.07193","title":"DINOv2: Learning Robust Visual Features without Supervision","created":"2023-04-14","cited_by_count":7974},{"id":"2410.21276","title":"GPT-4o System Card","created":"2024-10-25","cited_by_count":4588},{"id":"2205.11916","title":"Large Language Models are Zero-Shot Reasoners","created":"2022-05-24","cited_by_count":4374},{"id":"2307.03172","title":"Lost in the Middle: How Language Models Use Long Contexts","created":"2023-07-06","cited_by_count":3455},{"id":"2403.05530","title":"Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context","created":"2024-03-08","cited_by_count":3224},{"id":"2406.09246","title":"OpenVLA: An Open-Source Vision-Language-Action Model","created":"2024-06-13","cited_by_count":2887},{"id":"2408.00714","title":"SAM 2: Segment Anything in Images and Videos","created":"2024-08-01","cited_by_count":2863},{"id":"2303.04137","title":"Diffusion Policy: Visuomotor Policy Learning via Action Diffusion","created":"2023-03-07","cited_by_count":2838},{"id":"2410.24164","title":"$\\pi_0$: A Vision-Language-Action Flow Model for General Robot Control","created":"2024-10-31","cited_by_count":2407},{"id":"2308.11432","title":"A Survey on Large Language Model based Autonomous Agents","created":"2023-08-22","cited_by_count":2242},{"id":"1910.03771","title":"HuggingFace's Transformers: State-of-the-art Natural Language Processing","created":"2019-10-09","cited_by_count":2218},{"id":"2312.10997","title":"Retrieval-Augmented Generation for Large Language Models: A Survey","created":"2023-12-18","cited_by_count":2212},{"id":"2305.16291","title":"Voyager: An Open-Ended Embodied Agent with Large Language Models","created":"2023-05-25","cited_by_count":2191},{"id":"2002.08909","title":"REALM: Retrieval-Augmented Language Model Pre-Training","created":"2020-02-10","cited_by_count":2141},{"id":"2307.13854","title":"WebArena: A Realistic Web Environment for Building Autonomous Agents","created":"2023-07-25","cited_by_count":2006},{"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":"2304.13705","title":"Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardware","created":"2023-04-23","cited_by_count":1568},{"id":"2209.07753","title":"Code as Policies: Language Model Programs for Embodied Control","created":"2022-09-16","cited_by_count":1210},{"id":"2307.05973","title":"VoxPoser: Composable 3D Value Maps for Robotic Manipulation with Language Models","created":"2023-07-12","cited_by_count":750},{"id":"2410.07864","title":"RDT-1B: a Diffusion Foundation Model for Bimanual Manipulation","created":"2024-10-10","cited_by_count":691},{"id":"2109.02846","title":"Datasets: A Community Library for Natural Language Processing","created":"2021-09-07","cited_by_count":530},{"id":"2506.01844","title":"SmolVLA: A Vision-Language-Action Model for Affordable and Efficient Robotics","created":"2025-06-02","cited_by_count":530},{"id":"2506.18088","title":"RoboTwin 2.0: A Scalable Data Generator and Benchmark with Strong Domain Randomization for Robust Bimanual Robotic Manipulation","created":"2025-06-22","cited_by_count":518},{"id":"2411.19650","title":"CogACT: A Foundational Vision-Language-Action Model for Synergizing Cognition and Action in Robotic Manipulation","created":"2024-11-29","cited_by_count":422},{"id":"2505.06111","title":"UniVLA: Learning to Act Anywhere with Task-centric Latent Actions","created":"2025-05-09","cited_by_count":410},{"id":"2510.04618","title":"Agentic Context Engineering: Evolving Contexts for Self-Improving Language Models","created":"2025-10-06","cited_by_count":398},{"id":"2411.04983","title":"DINO-WM: World Models on Pre-trained Visual Features enable Zero-shot Planning","created":"2024-11-07","cited_by_count":386},{"id":"2409.01652","title":"ReKep: Spatio-Temporal Reasoning of Relational Keypoint Constraints for Robotic Manipulation","created":"2024-09-03","cited_by_count":315},{"id":"2410.05779","title":"LightRAG: Simple and Fast Retrieval-Augmented Generation","created":"2024-10-08","cited_by_count":315},{"id":"2507.02259","title":"MemAgent: Reshaping Long-Context LLM with Multi-Conv RL-based Memory Agent","created":"2025-07-03","cited_by_count":246},{"id":"2509.02547","title":"The Landscape of Agentic Reinforcement Learning for LLMs: A Survey","created":"2025-09-02","cited_by_count":205},{"id":"2510.03827","title":"LIBERO-PRO: Towards Robust and Fair Evaluation of Vision-Language-Action Models Beyond Memorization","created":"2025-10-04","cited_by_count":179},{"id":"2410.03834","title":"GraphRouter: A Graph-based Router for LLM Selections","created":"2024-10-04","cited_by_count":165},{"id":"2309.07870","title":"Agents: An Open-source Framework for Autonomous Language Agents","created":"2023-09-14","cited_by_count":116},{"id":"2403.03954","title":"3D Diffusion Policy: Generalizable Visuomotor Policy Learning via Simple 3D Representations","created":"2024-03-06","cited_by_count":116},{"id":"2410.02761","title":"FakeShield: Explainable Image Forgery Detection and Localization via Multi-modal Large Language Models","created":"2024-10-03","cited_by_count":113},{"id":"2503.02881","title":"Reactive Diffusion Policy: Slow-Fast Visual-Tactile Policy Learning for Contact-Rich Manipulation","created":"2025-03-04","cited_by_count":108},{"id":"2602.11236","title":"ABot-M0: VLA Foundation Model for Robotic Manipulation with Action Manifold Learning","created":"2026-02-11","cited_by_count":103},{"id":"2310.01427","title":"Attention Sorting Combats Recency Bias In Long Context Language Models","created":"2023-09-28","cited_by_count":90},{"id":"2310.10108","title":"On Generative Agents in Recommendation","created":"2023-10-16","cited_by_count":90},{"id":"2509.22548","title":"JanusVLN: Decoupling Semantics and Spatiality with Dual Implicit Memory for Vision-Language Navigation","created":"2025-09-26","cited_by_count":89},{"id":"2502.08773","title":"Universal Model Routing for Efficient LLM Inference","created":"2025-02-12","cited_by_count":86},{"id":"2506.07961","title":"BridgeVLA: Input-Output Alignment for Efficient 3D Manipulation Learning with Vision-Language Models","created":"2025-06-09","cited_by_count":80},{"id":"2508.21046","title":"CogVLA: Cognition-Aligned Vision-Language-Action Model via Instruction-Driven Routing & Sparsification","created":"2025-08-28","cited_by_count":74},{"id":"2405.11106","title":"LLM-based Multi-Agent Reinforcement Learning: Current and Future Directions","created":"2024-05-17","cited_by_count":67},{"id":"2506.22716","title":"BEST-Route: Adaptive LLM Routing with Test-Time Optimal Compute","created":"2025-06-28","cited_by_count":67},{"id":"2510.18632","title":"Think with 3D: Geometric Imagination Grounded Spatial Reasoning from Limited Views","created":"2025-10-21","cited_by_count":65},{"id":"2507.12898","title":"Vidar: Embodied Video Diffusion Model for Generalist Manipulation","created":"2025-07-17","cited_by_count":62},{"id":"2501.03841","title":"OmniManip: Towards General Robotic Manipulation via Object-Centric Interaction Primitives as Spatial Constraints","created":"2025-01-07","cited_by_count":59},{"id":"2509.25911","title":"Mem-{\\alpha}: Learning Memory Construction via Reinforcement Learning","created":"2025-09-30","cited_by_count":55},{"id":"2410.02223","title":"EmbedLLM: Learning Compact Representations of Large Language Models","created":"2024-10-03","cited_by_count":48},{"id":"2404.12281","title":"RISE: 3D Perception Makes Real-World Robot Imitation Simple and Effective","created":"2024-04-18","cited_by_count":41},{"id":"2503.07523","title":"VisRL: Intention-Driven Visual Perception via Reinforced Reasoning","created":"2025-03-10","cited_by_count":39},{"id":"2409.15518","title":"Eagle: Efficient Training-Free Router for Multi-LLM Inference","created":"2024-09-23","cited_by_count":35},{"id":"2411.18369","title":"G3Flow: Generative 3D Semantic Flow for Pose-aware and Generalizable Object Manipulation","created":"2024-11-27","cited_by_count":35},{"id":"2502.00425","title":"MQuant: Unleashing the Inference Potential of Multimodal Large Language Models via Full Static Quantization","created":"2025-02-01","cited_by_count":35},{"id":"2306.03900","title":"Model Spider: Learning to Rank Pre-Trained Models Efficiently","created":"2023-06-06","cited_by_count":32},{"id":"2412.04616","title":"Assessing and Learning Alignment of Unimodal Vision and Language Models","created":"2024-12-05","cited_by_count":32},{"id":"2505.16122","title":"Plan and Budget: Effective and Efficient Test-Time Scaling on Reasoning Large Language Models","created":"2025-05-22","cited_by_count":32},{"id":"2510.09719","title":"ICL-Router: In-Context Learned Model Representations for LLM Routing","created":"2025-10-10","cited_by_count":28},{"id":"2512.00903","title":"SwiftVLA: Unlocking Spatiotemporal Dynamics for Lightweight VLA Models at Minimal Overhead","created":"2025-11-30","cited_by_count":26},{"id":"2508.06259","title":"SIFThinker: Spatially-Aware Image Focus for Visual Reasoning","created":"2025-08-08","cited_by_count":25},{"id":"2505.20046","title":"REARANK: Reasoning Re-ranking Agent via Reinforcement Learning","created":"2025-05-26","cited_by_count":24},{"id":"2507.12768","title":"AnyPos: Automated Task-Agnostic Actions for Bimanual Manipulation","created":"2025-07-17","cited_by_count":23},{"id":"2512.12812","title":"Does Tone Change the Answer? Evaluating Prompt Politeness Effects on Modern LLMs: GPT, Gemini, and LLaMA","created":"2025-12-14","cited_by_count":23},{"id":"2502.12913","title":"GSQ-Tuning: Group-Shared Exponents Integer in Fully Quantized Training for LLMs On-Device Fine-tuning","created":"2025-02-18","cited_by_count":21},{"id":"2511.10518","title":"SemanticVLA: Semantic-Aligned Sparsification and Enhancement for Efficient Robotic Manipulation","created":"2025-11-13","cited_by_count":21},{"id":"2503.13217","title":"Dense Policy: Bidirectional Autoregressive Learning of Actions","created":"2025-03-17","cited_by_count":19},{"id":"2509.12446","title":"PromptSculptor: Multi-Agent Based Text-to-Image Prompt Optimization","created":"2025-09-15","cited_by_count":19},{"id":"2503.03081","title":"AirExo-2: Scaling up Generalizable Robotic Imitation Learning with Low-Cost Exoskeletons","created":"2025-03-05","cited_by_count":18},{"id":"2506.09990","title":"Chain-of-Action: Trajectory Autoregressive Modeling for Robotic Manipulation","created":"2025-06-11","cited_by_count":17},{"id":"2411.09658","title":"Motion Before Action: Diffusing Object Motion as Manipulation Condition","created":"2024-11-14","cited_by_count":16},{"id":"2503.16535","title":"Vision-Language Embodiment for Monocular Depth Estimation","created":"2025-03-18","cited_by_count":16},{"id":"2509.21486","title":"Reasoning-Enhanced Domain-Adaptive Pretraining of Multimodal Large Language Models for Short Video Content Governance","created":"2025-09-25","cited_by_count":16},{"id":"2504.05782","title":"MDK12-Bench: A Multi-Discipline Benchmark for Evaluating Reasoning in Multimodal Large Language Models","created":"2025-04-08","cited_by_count":15},{"id":"2302.06891","title":"UKnow: A Unified Knowledge Protocol with Multimodal Knowledge Graph Datasets for Reasoning and Vision-Language Pre-Training","created":"2023-02-14","cited_by_count":14},{"id":"2410.14974","title":"CAGE: Causal Attention Enables Data-Efficient Generalizable Robotic Manipulation","created":"2024-10-19","cited_by_count":14},{"id":"2508.00697","title":"On-Device Diffusion Transformer Policy for Efficient Robot Manipulation","created":"2025-08-01","cited_by_count":13},{"id":"2602.14662","title":"Advances in Global Solvers for 3D Vision","created":"2026-02-16","cited_by_count":13},{"id":"2602.02995","title":"Agent Alpha: Tree Search Unifying Generation, Exploration and Evaluation for Computer-Use Agents","created":"2026-02-03","cited_by_count":12},{"id":"2603.01195","title":"VisNec: Measuring and Leveraging Visual Necessity for Multimodal Instruction Tuning","created":"2026-03-01","cited_by_count":8},{"id":"2502.10705","title":"CoPEFT: Fast Adaptation Framework for Multi-Agent Collaborative Perception with Parameter-Efficient Fine-Tuning","created":"2025-02-15","cited_by_count":7},{"id":"2511.18123","title":"Bias Is a Subspace, Not a Coordinate: A Geometric Rethinking of Post-hoc Debiasing in Vision-Language Models","created":"2025-11-22","cited_by_count":7},{"id":"2601.09518","title":"Learning Whole-Body Human-Humanoid Interaction from Human-Human Demonstrations","created":"2026-01-14","cited_by_count":6},{"id":"2508.10672","title":"Hybrid Generative Fusion for Efficient and Privacy-Preserving Face Recognition Dataset Generation","created":"2025-08-14","cited_by_count":5},{"id":"2601.18753","title":"HalluGuard: Demystifying Data-Driven and Reasoning-Driven Hallucinations in LLMs","created":"2026-01-26","cited_by_count":5},{"id":"2507.04680","title":"Identify, Isolate, and Purge: Mitigating Hallucinations in LVLMs via Self-Evolving Distillation","created":"2025-07-07","cited_by_count":4},{"id":"2511.20468","title":"DRAFT-RL: Multi-Agent Chain-of-Draft Reasoning for Reinforcement Learning-Enhanced LLMs","created":"2025-11-25","cited_by_count":4},{"id":"2512.00694","title":"Affordance-First Decomposition for Continual Learning in Video-Language Understanding","created":"2025-11-30","cited_by_count":4},{"id":"2508.11898","title":"OmniD: Generalizable Robot Manipulation Policy via Image-Based BEV Representation","created":"2025-08-16","cited_by_count":3},{"id":"2507.04294","title":"BiFair: A Fairness-aware Training Framework for LLM-enhanced Recommender Systems via Bi-level Optimization","created":"2025-07-06","cited_by_count":2},{"id":"2603.07822","title":"Knowing When to Ask: Resolving Uncertainty in Human-Robot Joint Planning via Explicit Dialogue and Implicit Intent Cues","created":"2026-03-08","cited_by_count":2},{"id":"2603.07824","title":"Reasoning Knowledge-Gap in Drone Planning via LLM-based Active Elicitation","created":"2026-03-08","cited_by_count":1}],"next_cursor":null}