{"list":"other","total":69,"rows":[{"id":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"id":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"2402.03300","title":"DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models","created":"2024-02-05","cited_by_count":9379},{"id":"2304.08485","title":"Visual Instruction Tuning","created":"2023-04-17","cited_by_count":7869},{"id":"2309.06180","title":"Efficient Memory Management for Large Language Model Serving with PagedAttention","created":"2023-09-12","cited_by_count":5944},{"id":"2310.03744","title":"Improved Baselines with Visual Instruction Tuning","created":"2023-10-05","cited_by_count":4418},{"id":"2408.03326","title":"LLaVA-OneVision: Easy Visual Task Transfer","created":"2024-08-06","cited_by_count":2719},{"id":"2203.10244","title":"ChartQA: A Benchmark for Question Answering about Charts with Visual and Logical Reasoning","created":"2022-03-19","cited_by_count":1479},{"id":"2403.13372","title":"LlamaFactory: Unified Efficient Fine-Tuning of 100+ Language Models","created":"2024-03-20","cited_by_count":1464},{"id":"2503.20783","title":"Understanding R1-Zero-Like Training: A Critical Perspective","created":"2025-03-26","cited_by_count":1345},{"id":"2007.00398","title":"DocVQA: A Dataset for VQA on Document Images","created":"2020-07-01","cited_by_count":1317},{"id":"1910.02054","title":"ZeRO: Memory Optimizations Toward Training Trillion Parameter Models","created":"2019-10-04","cited_by_count":1301},{"id":"1909.06146","title":"PubMedQA: A Dataset for Biomedical Research Question Answering","created":"2019-09-13","cited_by_count":1288},{"id":"1905.12265","title":"Strategies for Pre-training Graph Neural Networks","created":"2019-05-29","cited_by_count":971},{"id":"2406.16860","title":"Cambrian-1: A Fully Open, Vision-Centric Exploration of Multimodal LLMs","created":"2024-06-24","cited_by_count":838},{"id":"2507.18071","title":"Group Sequence Policy Optimization","created":"2025-07-24","cited_by_count":835},{"id":"2511.10647","title":"Depth Anything 3: Recovering the Visual Space from Any Views","created":"2025-11-13","cited_by_count":692},{"id":"1912.13318","title":"LayoutLM: Pre-training of Text and Layout for Document Image Understanding","created":"2019-12-31","cited_by_count":553},{"id":"1906.11300","title":"Benign Overfitting in Linear Regression","created":"2019-06-26","cited_by_count":549},{"id":"2602.02276","title":"Kimi K2.5: Visual Agentic Intelligence","created":"2026-02-02","cited_by_count":501},{"id":"2105.03011","title":"A Dataset of Information-Seeking Questions and Answers Anchored in Research Papers","created":"2021-05-07","cited_by_count":486},{"id":"2407.11691","title":"VLMEvalKit: An Open-Source Toolkit for Evaluating Large Multi-Modality Models","created":"2024-07-16","cited_by_count":455},{"id":"2411.10440","title":"LLaVA-CoT: Let Vision Language Models Reason Step-by-Step","created":"2024-11-15","cited_by_count":454},{"id":"2104.12756","title":"InfographicVQA","created":"2021-04-26","cited_by_count":437},{"id":"2408.05517","title":"SWIFT:A Scalable lightWeight Infrastructure for Fine-Tuning","created":"2024-08-10","cited_by_count":355},{"id":"1908.07836","title":"PubLayNet: largest dataset ever for document layout analysis","created":"2019-08-16","cited_by_count":351},{"id":"2404.16994","title":"PLLaVA : Parameter-free LLaVA Extension from Images to Videos for Video Dense Captioning","created":"2024-04-25","cited_by_count":322},{"id":"1909.00997","title":"PlotQA: Reasoning over Scientific Plots","created":"2019-09-03","cited_by_count":321},{"id":"2504.01848","title":"PaperBench: Evaluating AI's Ability to Replicate AI Research","created":"2025-04-02","cited_by_count":321},{"id":"2506.13585","title":"MiniMax-M1: Scaling Test-Time Compute Efficiently with Lightning Attention","created":"2025-06-16","cited_by_count":263},{"id":"2106.06130","title":"ChemRL-GEM: Geometry Enhanced Molecular Representation Learning for Property Prediction","created":"2021-06-11","cited_by_count":204},{"id":"2407.01523","title":"MMLongBench-Doc: Benchmarking Long-context Document Understanding with Visualizations","created":"2024-07-01","cited_by_count":183},{"id":"2206.13517","title":"ProGen2: Exploring the Boundaries of Protein Language Models","created":"2022-06-27","cited_by_count":159},{"id":"2412.05237","title":"MAmmoTH-VL: Eliciting Multimodal Reasoning with Instruction Tuning at Scale","created":"2024-12-06","cited_by_count":127},{"id":"2510.08531","title":"SpatialLadder: Progressive Training for Spatial Reasoning in Vision-Language Models","created":"2025-10-09","cited_by_count":90},{"id":"2402.09268","title":"Transformers, parallel computation, and logarithmic depth","created":"2024-02-14","cited_by_count":79},{"id":"1405.3267","title":"Exact Recovery in the Stochastic Block Model","created":"2014-05-13","cited_by_count":78},{"id":"2504.15271","title":"Eagle 2.5: Boosting Long-Context Post-Training for Frontier Vision-Language Models","created":"2025-04-21","cited_by_count":64},{"id":"2305.13186","title":"SCITAB: A Challenging Benchmark for Compositional Reasoning and Claim Verification on Scientific Tables","created":"2023-05-22","cited_by_count":51},{"id":"2210.09184","title":"Packed-Ensembles for Efficient Uncertainty Estimation","created":"2022-10-17","cited_by_count":49},{"id":"2410.06833","title":"Dynamic metastability in the self-attention model","created":"2024-10-09","cited_by_count":46},{"id":"2504.07957","title":"MM-IFEngine: Towards Multimodal Instruction Following","created":"2025-04-10","cited_by_count":42},{"id":"2510.27606","title":"Spatial-SSRL: Enhancing Spatial Understanding via Self-Supervised Reinforcement Learning","created":"2025-10-31","cited_by_count":41},{"id":"2509.22647","title":"CapRL: Stimulating Dense Image Caption Capabilities via Reinforcement Learning","created":"2025-09-26","cited_by_count":38},{"id":"2406.11633","title":"DocGenome: An Open Large-scale Scientific Document Benchmark for Training and Testing Multi-modal Large Language Models","created":"2024-06-17","cited_by_count":36},{"id":"2505.23683","title":"Learning Compositional Functions with Transformers from Easy-to-Hard Data","created":"2025-05-29","cited_by_count":36},{"id":"2501.18322","title":"A Unified Perspective on the Dynamics of Deep Transformers","created":"2025-01-30","cited_by_count":32},{"id":"2306.06156","title":"PoET: A generative model of protein families as sequences-of-sequences","created":"2023-06-09","cited_by_count":29},{"id":"2411.04075","title":"M3SciQA: A Multi-Modal Multi-Document Scientific QA Benchmark for Evaluating Foundation Models","created":"2024-11-06","cited_by_count":27},{"id":"2602.23166","title":"AgentVista: Evaluating Multimodal Agents in Ultra-Challenging Realistic Visual Scenarios","created":"2026-02-26","cited_by_count":23},{"id":"2501.03226","title":"BoostStep: Boosting mathematical capability of Large Language Models via improved single-step reasoning","created":"2025-01-06","cited_by_count":21},{"id":"2010.15559","title":"Quantum Computing: A Taxonomy, Systematic Review and Future Directions","created":"2020-09-28","cited_by_count":16},{"id":"2506.19848","title":"ScaleCap: Inference-Time Scalable Image Captioning via Dual-Modality Debiasing","created":"2025-06-24","cited_by_count":15},{"id":"2512.07733","title":"SpatialDreamer: Incentivizing Spatial Reasoning via Active Mental Imagery","created":"2025-12-08","cited_by_count":11},{"id":"2411.11066","title":"TS-LLaVA: Constructing Visual Tokens through Thumbnail-and-Sampling for Training-Free Video Large Language Models","created":"2024-11-17","cited_by_count":9},{"id":"2504.04702","title":"Provable Failure of Language Models in Learning Majority Boolean Logic via Gradient Descent","created":"2025-04-07","cited_by_count":8},{"id":"2603.03198","title":"ACE-Brain-0: Spatial Intelligence as a Shared Scaffold for Universal Embodiments","created":"2026-03-03","cited_by_count":7},{"id":"2508.04724","title":"Understanding protein function with a multimodal retrieval-augmented foundation model","created":"2025-08-05","cited_by_count":6},{"id":"2602.21186","title":"Spa3R: Predictive Spatial Field Modeling for 3D Visual Reasoning","created":"2026-02-24","cited_by_count":6},{"id":"2604.12812","title":"DocSeeker: Structured Visual Reasoning with Evidence Grounding for Long Document Understanding","created":"2026-04-14","cited_by_count":6},{"id":"2602.10675","title":"TwiFF (Think With Future Frames): A Large-Scale Dataset for Dynamic Visual Reasoning","created":"2026-02-11","cited_by_count":3},{"id":"2409.05751","title":"Design of a Variable Stiffness Quasi-Direct Drive Cable-Actuated Tensegrity Robot","created":"2024-09-09","cited_by_count":2},{"id":"2501.15078","title":"Impact-resistant, autonomous robots inspired by tensegrity architecture","created":"2025-01-25","cited_by_count":1},{"id":"2509.20284","title":"Biologically Plausible Learning via Bidirectional Spike-Based Distillation","created":"2025-09-24","cited_by_count":1},{"id":"2602.07494","title":"Hyperparameter Transfer Laws for Non-Recurrent Multi-Path Neural Networks","created":"2026-02-07","cited_by_count":1},{"id":"2603.03045","title":"QFlowNet: Fast, Diverse, and Efficient Unitary Synthesis with Generative Flow Networks","created":"2026-03-03","cited_by_count":1},{"id":"2604.11307","title":"PaperScope: A Multi-Modal Multi-Document Benchmark for Agentic Deep Research Across Massive Scientific Papers","created":"2026-04-13","cited_by_count":1},{"id":"2604.12867","title":"QuarkMedSearch: A Long-Horizon Deep Search Agent for Exploring Medical Intelligence","created":"2026-04-14","cited_by_count":1},{"id":"2604.18508","title":"Document-as-Image Representations Fall Short for Scientific Retrieval","created":"2026-04-20","cited_by_count":1}],"next_cursor":null}