{"total":23,"rows":[{"id":"2511.18903","title":"How Learning Rate Decay Wastes Your Best Data in Curriculum-Based LLM Pretraining","created":"2025-11-24","cited_by_count":14,"area":null},{"id":"2604.26256","title":"DORA: A Scalable Asynchronous Reinforcement Learning System for Language Model Training","created":"2026-04-29","cited_by_count":14,"area":null},{"id":"2601.10355","title":"Unlocking Implicit Experience: Synthesizing Tool-Use Trajectories from Text","created":"2026-01-15","cited_by_count":13,"area":null},{"id":"2602.11287","title":"HiFloat4 Format for Language Model Inference","created":"2026-02-11","cited_by_count":11,"area":null},{"id":"2604.10098","title":"Attention Sink in Transformers: A Survey on Utilization, Interpretation, and Mitigation","created":"2026-04-11","cited_by_count":11,"area":null},{"id":"2510.13291","title":"Higher Satisfaction, Lower Cost: A Technical Report on How LLMs Revolutionize Meituan's Intelligent Interaction Systems","created":"2025-10-15","cited_by_count":7,"area":null},{"id":"2602.03584","title":"$V_0$: A Generalist Value Model for Any Policy at State Zero","created":"2026-02-03","cited_by_count":7,"area":null},{"id":"2602.14208","title":"Fast Catch-Up, Late Switching: Optimal Batch Size Scheduling via Functional Scaling Laws","created":"2026-02-15","cited_by_count":6,"area":null},{"id":"2606.14502","title":"From Chatbot to Digital Colleague: The Paradigm Shift Toward Persistent Autonomous AI","created":"2026-06-12","cited_by_count":6,"area":null},{"id":"2602.10718","title":"SnapMLA: Efficient Long-Context MLA Decoding via Hardware-Aware FP8 Quantized Pipelining","created":"2026-02-11","cited_by_count":4,"area":null},{"id":"2607.14952","title":"LongStraw: Long-Context RL Beyond 2M Tokens under a Fixed GPU Budget","created":"2026-07-16","cited_by_count":3,"area":null},{"id":"2608.01662","title":"LongCat Sparse Attention: Taming the Lightning via Streaming-aware Hierarchical Cross-Layer Indexing","created":"2026-08-03","cited_by_count":2,"area":null},{"id":"2608.12149","title":"Massive Activations in Hybrid Linear Attention Large Language Models: Pre-Attention Spikes and Inter-Spike Plateaus","created":"2026-08-12","cited_by_count":2,"area":null},{"id":"2601.20255","title":"HE-SNR: Uncovering Latent Logic via Entropy for Guiding Mid-Training on SWE-bench","created":"2026-01-28","cited_by_count":1,"area":null},{"id":"2602.13185","title":"FlexAM: Flexible Appearance-Motion Decomposition for Versatile Video Generation Control","created":"2026-02-13","cited_by_count":1,"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":"2512.22455","title":"AFA-LoRA: Enabling Non-Linear Adaptations in LoRA with Activation Function Annealing","created":"2025-12-27","cited_by_count":0,"area":null},{"id":"2605.21603","title":"DynaFlow: Transparent and Flexible Intra-Device Parallelism via Programmable Operator Scheduling","created":"2026-05-20","cited_by_count":0,"area":null},{"id":"2606.04048","title":"Unlocking Feature Learning in Gated Delta Networks at Scale","created":"2026-06-02","cited_by_count":0,"area":null},{"id":"2607.10387","title":"GigaChat Audio: Time-aware Large Audio Language Model","created":"2026-07-11","cited_by_count":0,"area":null},{"id":"2607.22662","title":"CuraWeb: Joint Optimization of Quality, Redundancy, and Diversity for Web-Scale Pretraining Data","created":"2026-06-29","cited_by_count":0,"area":null},{"id":"2609.36760","title":"QuantMLA: Function-Aligned Dual-Path Quantization for Low-Bit MLA KV Caching","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2609.39661","title":"The Evolution of Attention in Large Language Models: Mechanisms, Trade-offs, and Emerging Trends","created":"2026-09-30","cited_by_count":0,"area":null}],"next_cursor":null}