{"total":118,"rows":[{"id":"2310.06770","title":"SWE-bench: Can Language Models Resolve Real-World GitHub Issues?","created":"2023-10-10","cited_by_count":3373,"area":null},{"id":"2403.13372","title":"LlamaFactory: Unified Efficient Fine-Tuning of 100+ Language Models","created":"2024-03-20","cited_by_count":1464,"area":null},{"id":"2404.06654","title":"RULER: What's the Real Context Size of Your Long-Context Language Models?","created":"2024-04-09","cited_by_count":1346,"area":null},{"id":"2310.01889","title":"Ring Attention with Blockwise Transformers for Near-Infinite Context","created":"2023-10-03","cited_by_count":457,"area":null},{"id":"2407.02490","title":"MInference 1.0: Accelerating Pre-filling for Long-Context LLMs via Dynamic Sparse Attention","created":"2024-07-02","cited_by_count":383,"area":null},{"id":"2402.10171","title":"Data Engineering for Scaling Language Models to 128K Context","created":"2024-02-15","cited_by_count":186,"area":null},{"id":"2502.10248","title":"Step-Video-T2V Technical Report: The Practice, Challenges, and Future of Video Foundation Model","created":"2025-02-14","cited_by_count":168,"area":null},{"id":"2408.12588","title":"Real-Time Video Generation with Pyramid Attention Broadcast","created":"2024-08-22","cited_by_count":149,"area":null},{"id":"2410.02660","title":"How to Train Long-Context Language Models (Effectively)","created":"2024-10-03","cited_by_count":146,"area":null},{"id":"2310.05209","title":"Scaling Laws of RoPE-based Extrapolation","created":"2023-10-08","cited_by_count":125,"area":null},{"id":"2409.10516","title":"RetrievalAttention: Accelerating Long-Context LLM Inference via Vector Retrieval","created":"2024-09-16","cited_by_count":116,"area":null},{"id":"2401.08671","title":"DeepSpeed-FastGen: High-throughput Text Generation for LLMs via MII and DeepSpeed-Inference","created":"2024-01-09","cited_by_count":106,"area":null},{"id":"2506.09350","title":"Autoregressive Adversarial Post-Training for Real-Time Interactive Video Generation","created":"2025-06-11","cited_by_count":90,"area":null},{"id":"2504.08685","title":"Seaweed-7B: Cost-Effective Training of Video Generation Foundation Model","created":"2025-04-11","cited_by_count":82,"area":null},{"id":"2412.03568","title":"The Matrix: Infinite-Horizon World Generation with Real-Time Moving Control","created":"2024-12-04","cited_by_count":80,"area":null},{"id":"2403.04797","title":"Found in the Middle: How Language Models Use Long Contexts Better via Plug-and-Play Positional Encoding","created":"2024-03-05","cited_by_count":72,"area":null},{"id":"2512.16776","title":"Kling-Omni Technical Report","created":"2025-12-18","cited_by_count":71,"area":null},{"id":"2410.15458","title":"Allegro: Open the Black Box of Commercial-Level Video Generation Model","created":"2024-10-20","cited_by_count":70,"area":null},{"id":"2405.07719","title":"USP: A Unified Sequence Parallelism Approach for Long Context Generative AI","created":"2024-05-13","cited_by_count":61,"area":null},{"id":"2508.15761","title":"Waver: Wave Your Way to Lifelike Video Generation","created":"2025-08-21","cited_by_count":52,"area":null},{"id":"2501.18795","title":"Rope to Nope and Back Again: A New Hybrid Attention Strategy","created":"2025-01-30","cited_by_count":47,"area":null},{"id":"2512.08765","title":"Wan-Move: Motion-controllable Video Generation via Latent Trajectory Guidance","created":"2025-12-09","cited_by_count":45,"area":null},{"id":"2604.14141","title":"LingBot-Map: Geometric Context Transformer for Streaming 3D Reconstruction","created":"2026-04-15","cited_by_count":37,"area":null},{"id":"2510.14648","title":"In-Context Learning with Unpaired Clips for Instruction-based Video Editing","created":"2025-10-16","cited_by_count":35,"area":null},{"id":"2310.03294","title":"DISTFLASHATTN: Distributed Memory-efficient Attention for Long-context LLMs Training","created":"2023-10-05","cited_by_count":29,"area":null},{"id":"2410.04199","title":"LongGenBench: Long-context Generation Benchmark","created":"2024-10-05","cited_by_count":28,"area":null},{"id":"2412.18619","title":"Next Token Prediction Towards Multimodal Intelligence: A Comprehensive Survey","created":"2024-12-16","cited_by_count":27,"area":null},{"id":"2411.01783","title":"Context Parallelism for Scalable Million-Token Inference","created":"2024-11-04","cited_by_count":26,"area":null},{"id":"2409.00509","title":"LongRecipe: Recipe for Efficient Long Context Generalization in Large Language Models","created":"2024-08-31","cited_by_count":23,"area":null},{"id":"2604.03444","title":"Olmo Hybrid: From Theory to Practice and Back","created":"2026-04-03","cited_by_count":22,"area":null},{"id":"2411.16102","title":"BlendServe: Optimizing Offline Inference for Auto-regressive Large Models with Resource-aware Batching","created":"2024-11-25","cited_by_count":19,"area":null},{"id":"2412.01523","title":"FlexSP: Accelerating Large Language Model Training via Flexible Sequence Parallelism","created":"2024-12-02","cited_by_count":19,"area":null},{"id":"2604.10905","title":"Audio Flamingo Next: Next-Generation Open Audio-Language Models for Speech, Sound, and Music","created":"2026-04-13","cited_by_count":19,"area":null},{"id":"2602.23361","title":"VGG-T$^3$: Offline Feed-Forward 3D Reconstruction at Scale","created":"2026-02-26","cited_by_count":18,"area":null},{"id":"2503.17924","title":"WLB-LLM: Workload-Balanced 4D Parallelism for Large Language Model Training","created":"2025-03-23","cited_by_count":17,"area":null},{"id":"2509.16293","title":"Robust LLM Training Infrastructure at ByteDance","created":"2025-09-19","cited_by_count":16,"area":null},{"id":"2411.13476","title":"When Precision Meets Position: BFloat16 Breaks Down RoPE in Long-Context Training","created":"2024-11-20","cited_by_count":15,"area":null},{"id":"2411.02142","title":"Training Compute-Optimal Protein Language Models","created":"2024-11-04","cited_by_count":12,"area":null},{"id":"2503.01868","title":"Systems and Algorithms for Convolutional Multi-Hybrid Language Models at Scale","created":"2025-02-25","cited_by_count":12,"area":null},{"id":"2604.07823","title":"LPM 1.0: Video-based Character Performance Model","created":"2026-04-09","cited_by_count":11,"area":null},{"id":"2412.19191","title":"Biology-Instructions: A Dataset and Benchmark for Multi-Omics Sequence Understanding Capability of Large Language Models","created":"2024-12-26","cited_by_count":10,"area":null},{"id":"2502.21231","title":"ByteScale: Efficient Scaling of LLM Training with a 2048K Context Length on More Than 12,000 GPUs","created":"2025-02-28","cited_by_count":10,"area":null},{"id":"2505.04802","title":"ORBIT-2: Scaling Exascale Vision Foundation Models for Weather and Climate Downscaling","created":"2025-05-07","cited_by_count":10,"area":null},{"id":"2605.12496","title":"CausalCine: Real-Time Autoregressive Generation for Multi-Shot Video Narratives","created":"2026-05-12","cited_by_count":10,"area":null},{"id":"2402.18789","title":"FlexLLM: Token-Level Co-Serving of LLM Inference and Finetuning with SLO Guarantees","created":"2024-02-29","cited_by_count":9,"area":null},{"id":"2406.18820","title":"Universal Checkpointing: A Flexible and Efficient Distributed Checkpointing System for Large-Scale DNN Training with Reconfigurable Parallelis","created":"2024-06-27","cited_by_count":9,"area":null},{"id":"2311.05610","title":"Efficient Parallelization Layouts for Large-Scale Distributed Model Training","created":"2023-11-09","cited_by_count":8,"area":null},{"id":"2411.13055","title":"Hardware Scaling Trends and Diminishing Returns in Large-Scale Distributed Training","created":"2024-11-20","cited_by_count":8,"area":null},{"id":"2604.11804","title":"OmniShow: Unifying Multimodal Conditions for Human-Object Interaction Video Generation","created":"2026-04-13","cited_by_count":8,"area":null},{"id":"2504.09307","title":"Lumos: Efficient Performance Modeling and Estimation for Large-scale LLM Training","created":"2025-04-12","cited_by_count":7,"area":null},{"id":"2510.10620","title":"DCP: Addressing Input Dynamism In Long-Context Training via Dynamic Context Parallelism","created":"2025-10-12","cited_by_count":7,"area":null},{"id":"2404.09707","title":"Adaptive Patching for High-resolution Image Segmentation with Transformers","created":"2024-04-15","cited_by_count":6,"area":null},{"id":"2407.15892","title":"Mini-Sequence Transformer: Optimizing Intermediate Memory for Long Sequences Training","created":"2024-07-22","cited_by_count":6,"area":null},{"id":"2408.16978","title":"Training Ultra Long Context Language Model with Fully Pipelined Distributed Transformer","created":"2024-08-30","cited_by_count":6,"area":null},{"id":"2509.21271","title":"SuperOffload: Unleashing the Power of Large-Scale LLM Training on Superchips","created":"2025-09-25","cited_by_count":6,"area":null},{"id":"2407.12117","title":"MEMO: Fine-grained Tensor Management For Ultra-long Context LLM Training","created":"2024-07-16","cited_by_count":5,"area":null},{"id":"2407.14106","title":"TorchGT: A Holistic System for Large-scale Graph Transformer Training","created":"2024-07-19","cited_by_count":5,"area":null},{"id":"2412.20601","title":"MATEY: multiscale adaptive foundation models for spatiotemporal physical systems","created":"2024-12-29","cited_by_count":5,"area":null},{"id":"2506.05343","title":"ContentV: Efficient Training of Video Generation Models with Limited Compute","created":"2025-06-05","cited_by_count":5,"area":null},{"id":"2509.05276","title":"SpikingBrain: Spiking Brain-inspired Large Models","created":"2025-09-05","cited_by_count":5,"area":null},{"id":"2605.08301","title":"Priming: Hybrid State Space Models From Pre-trained Transformers","created":"2026-05-08","cited_by_count":5,"area":null},{"id":"2606.03972","title":"AAD-1: Asymmetric Adversarial Distillation for One-Step Autoregressive Video Generation","created":"2026-06-02","cited_by_count":5,"area":null},{"id":"2609.11638","title":"Vidu S2: Real-Time Interactive, Editable, and Spatial Video Generation","created":"2026-09-10","cited_by_count":5,"area":null},{"id":"2409.15104","title":"PecSched: Preemptive and Efficient Cluster Scheduling for LLM Inference","created":"2024-09-23","cited_by_count":4,"area":null},{"id":"2505.22296","title":"360-LLaMA-Factory: Plug & Play Sequence Parallelism for Long Post-Training","created":"2025-05-28","cited_by_count":4,"area":null},{"id":"2607.03118","title":"Vidu S1: A Real-Time Interactive Video Generation Model","created":"2026-07-03","cited_by_count":4,"area":null},{"id":"2411.14458","title":"Improving training time and GPU utilization in geo-distributed language model training","created":"2024-11-16","cited_by_count":3,"area":null},{"id":"2412.07894","title":"Hydraulis: Balancing Large Transformer Model Training via Co-designing Parallel Strategies and Data Assignment","created":"2024-12-10","cited_by_count":3,"area":null},{"id":"2502.12085","title":"APB: Accelerating Distributed Long-Context Inference by Passing Compressed Context Blocks across GPUs","created":"2025-02-17","cited_by_count":3,"area":null},{"id":"2506.13996","title":"Arctic Long Sequence Training: Scalable And Efficient Training For Multi-Million Token Sequences","created":"2025-06-16","cited_by_count":3,"area":null},{"id":"2603.07236","title":"HY-WU (Part I): An Extensible Functional Neural Memory Framework and An Instantiation in Text-Guided Image Editing","created":"2026-03-07","cited_by_count":3,"area":null},{"id":"2503.07680","title":"Hierarchical Balance Packing: Towards Efficient Supervised Fine-tuning for Long-Context LLM","created":"2025-03-10","cited_by_count":2,"area":null},{"id":"2504.13125","title":"LLMs Meet Finance: Fine-Tuning Foundation Models for the Open FinLLM Leaderboard","created":"2025-04-17","cited_by_count":2,"area":null},{"id":"2505.08651","title":"Scaling Context, Not Parameters: Training a Compact 7B Language Model for Efficient Long-Context Processing","created":"2025-05-13","cited_by_count":2,"area":null},{"id":"2505.10584","title":"Aquarius: A Family of Industry-Level Video Generation Models for Marketing Scenarios","created":"2025-05-14","cited_by_count":2,"area":null},{"id":"2506.03077","title":"StreamBP: Memory-Efficient Exact Backpropagation for Long Sequence Training of LLMs","created":"2025-06-03","cited_by_count":2,"area":null},{"id":"2506.05229","title":"Diagonal Batching Unlocks Parallelism in Recurrent Memory Transformers for Long Contexts","created":"2025-06-05","cited_by_count":2,"area":null},{"id":"2507.01004","title":"ZeCO: Zero Communication Overhead Sequence Parallelism for Linear Attention","created":"2025-07-01","cited_by_count":2,"area":null},{"id":"2509.23722","title":"OctoPipe: Reducing Pipeline Bubbles for Heterogeneous Models via Co-Optimizing Partitioning, Placement, and Scheduling","created":"2025-09-28","cited_by_count":2,"area":null},{"id":"2604.05182","title":"LSRM: High-Fidelity Object-Centric Reconstruction via Scaled Context Windows","created":"2026-04-06","cited_by_count":2,"area":null},{"id":"2604.22575","title":"SpikingBrain2.0: Brain-Inspired Foundation Models for Efficient Long-Context and Cross-Platform Inference","created":"2026-04-24","cited_by_count":2,"area":null},{"id":"2606.22932","title":"FORGE: Fused On-Register Gradient Elimination for Memory-Efficient LLM Training","created":"2026-06-22","cited_by_count":2,"area":null},{"id":"2607.04443","title":"Wan-Streamer v0.2: Higher Resolution, Same Latency","created":"2026-07-05","cited_by_count":2,"area":null},{"id":"2607.15038","title":"Video = World + Event Stream","created":"2026-07-16","cited_by_count":2,"area":null},{"id":"2607.26694","title":"Visko Orbis 1.0: A Live Model for Real-Time Interactive Long Video Generation","created":"2026-07-29","cited_by_count":2,"area":null},{"id":"2405.15780","title":"Sequence Length Scaling in Vision Transformers for Scientific Images on Frontier","created":"2024-04-17","cited_by_count":1,"area":null},{"id":"2502.01659","title":"Longer Attention Span: Increasing Transformer Context Length with Sparse Graph Processing Techniques","created":"2025-01-31","cited_by_count":1,"area":null},{"id":"2503.01873","title":"Online Pseudo-average Shifting Attention(PASA) for Robust Low-precision LLM Inference: Algorithms and Numerical Analysis","created":"2025-02-26","cited_by_count":1,"area":null},{"id":"2509.07003","title":"veScale: Consistent and Efficient Tensor Programming with Eager-Mode SPMD","created":"2025-09-05","cited_by_count":1,"area":null},{"id":"2604.19741","title":"CityRAG: Stepping Into a City via Spatially-Grounded Video Generation","created":"2026-04-21","cited_by_count":1,"area":null},{"id":"2606.08476","title":"FlashCP: Load-Balanced Communication-Efficient Context Parallelism for LLM Training","created":"2026-06-07","cited_by_count":1,"area":null},{"id":"2606.24780","title":"BluTrain: A C++/CUDA Framework for AI Systems","created":"2026-06-23","cited_by_count":1,"area":null},{"id":"2607.28144","title":"ReGenVC: End-to-End Real-Time Generative Video Coding at Ultra-Low Bitrate","created":"2026-07-30","cited_by_count":1,"area":null},{"id":"2503.12964","title":"Training Video Foundation Models with NVIDIA NeMo","created":"2025-03-17","cited_by_count":0,"area":null},{"id":"2503.15758","title":"ATTENTION2D: Communication Efficient Distributed Self-Attention Mechanism","created":"2025-03-20","cited_by_count":0,"area":null},{"id":"2504.21411","title":"Galvatron: An Automatic Distributed System for Efficient Foundation Model Training","created":"2025-04-30","cited_by_count":0,"area":null},{"id":"2509.21081","title":"TyphoonMLA: A Mixed Naive-Absorb MLA Kernel For Shared Prefix","created":"2025-09-25","cited_by_count":0,"area":null},{"id":"2509.21275","title":"Concertina: Data-Centric Adaptive Pipeline Parallelism for Efficient Heterogeneous Long-Context LLM Training","created":"2025-09-25","cited_by_count":0,"area":null},{"id":"2509.26541","title":"TASP: Topology-aware Sequence Parallelism","created":"2025-09-30","cited_by_count":0,"area":null},{"id":"2510.18121","title":"Efficient Long-context Language Model Training by Core Attention Disaggregation","created":"2025-10-20","cited_by_count":0,"area":null}],"next_cursor":"100"}