{"total":35,"rows":[{"id":"2507.10524","title":"Mixture-of-Recursions: Learning Dynamic Recursive Depths for Adaptive Token-Level Computation","created":"2025-07-14","cited_by_count":133,"area":null},{"id":"2512.24880","title":"mHC: Manifold-Constrained Hyper-Connections","created":"2025-12-31","cited_by_count":88,"area":null},{"id":"2607.08639","title":"Native Video-Action Pretraining for Generalizable Robot Control","created":"2026-07-09","cited_by_count":36,"area":null},{"id":"2507.20776","title":"RingMo-Agent: A Unified Remote Sensing Foundation Model for Multi-Platform and Multi-Modal Reasoning","created":"2025-07-28","cited_by_count":20,"area":null},{"id":"2507.16577","title":"Scaling Linear Attention with Sparse State Expansion","created":"2025-07-22","cited_by_count":13,"area":null},{"id":"2601.10639","title":"STEM: Scaling Transformers with Embedding Modules","created":"2026-01-15","cited_by_count":12,"area":null},{"id":"2505.20524","title":"Towards Fully FP8 GEMM LLM Training at Scale","created":"2025-05-26","cited_by_count":11,"area":null},{"id":"2508.15281","title":"MMQ: Multimodal Mixture-of-Quantization Tokenization for Semantic ID Generation and User Behavioral Adaptation","created":"2025-08-21","cited_by_count":10,"area":null},{"id":"2510.19338","title":"Every Attention Matters: An Efficient Hybrid Architecture for Long-Context Reasoning","created":"2025-10-22","cited_by_count":10,"area":null},{"id":"2505.21364","title":"Towards Interpretability Without Sacrifice: Faithful Dense Layer Decomposition with Mixture of Decoders","created":"2025-05-27","cited_by_count":5,"area":null},{"id":"2512.07628","title":"MoCA: Mixture-of-Components Attention for Scalable Compositional 3D Generation","created":"2025-12-08","cited_by_count":5,"area":null},{"id":"2606.14957","title":"Learning Sparse Latent Predictive Foundation Model for Multimodal Neuroimaging","created":"2026-06-12","cited_by_count":4,"area":null},{"id":"2511.23319","title":"Every Token Counts: Generalizing 16M Ultra-Long Context in Large Language Models","created":"2025-11-28","cited_by_count":3,"area":null},{"id":"2603.17484","title":"Learning When to Attend: Conditional Memory Access for Long-Context LLMs","created":"2026-03-18","cited_by_count":3,"area":null},{"id":"2507.10618","title":"Compute Requirements for Algorithmic Innovation in Frontier AI Models","created":"2025-07-13","cited_by_count":2,"area":null},{"id":"2602.02400","title":"An Empirical Study on Noisy Data and LLM Pretraining Loss Divergence","created":"2026-02-02","cited_by_count":2,"area":null},{"id":"2602.23410","title":"Brain-OF: An Omnifunctional Foundation Model for fMRI, EEG and MEG","created":"2026-02-26","cited_by_count":2,"area":null},{"id":"2606.28116","title":"Mechanism-Driven Monitors for Preemptive Detection of LLM Training Instability","created":"2026-06-26","cited_by_count":2,"area":null},{"id":"2510.23052","title":"Knocking-Heads Attention","created":"2025-10-27","cited_by_count":1,"area":null},{"id":"2511.12945","title":"APT: Affine Prototype-Timestamp For Time Series Forecasting Under Distribution Shift","created":"2025-11-17","cited_by_count":1,"area":null},{"id":"2512.09723","title":"Mixture of Lookup Key-Value Experts","created":"2025-12-10","cited_by_count":1,"area":null},{"id":"2605.17879","title":"Guard: Scalable Straggler Detection and Node Health Management for Large-Scale Training","created":"2026-05-18","cited_by_count":1,"area":null},{"id":"2605.28769","title":"Multi-Mixer Models: Flexible Sequence Modeling with Shared Representations","created":"2026-05-27","cited_by_count":1,"area":null},{"id":"2608.29539","title":"LoGo: Token-Level Dynamic Local-Global Attention","created":"2026-08-30","cited_by_count":1,"area":null},{"id":"2507.11085","title":"Atmos-Bench: 3D Atmospheric Structures for Climate Insight","created":"2025-07-15","cited_by_count":0,"area":null},{"id":"2507.21372","title":"Load Balancing for AI Training Workloads","created":"2025-07-28","cited_by_count":0,"area":null},{"id":"2510.14819","title":"Capturing Context-Aware Route Choice Semantics for Trajectory Representation Learning","created":"2025-10-16","cited_by_count":0,"area":null},{"id":"2510.18425","title":"Automated urban waterlogging assessment and early warning through a mixture of foundation models","created":"2025-10-21","cited_by_count":0,"area":null},{"id":"2512.15600","title":"How Smoothing is N-simplicial Attention?","created":"2025-12-17","cited_by_count":0,"area":null},{"id":"2604.17228","title":"Revisiting Auxiliary Losses for Conditional Depth Routing: An Empirical Study","created":"2026-04-19","cited_by_count":0,"area":null},{"id":"2605.08171","title":"Communication Dynamics Neural Networks: FFT-Diagonalized Layers for Improved Hessian Conditioning at Reduced Parameter Count","created":"2026-05-04","cited_by_count":0,"area":null},{"id":"2607.02049","title":"SPLIT: Cross-Lingual Empathy and Cultural Grounding in English and Ukrainian LLM Responses","created":"2026-07-02","cited_by_count":0,"area":null},{"id":"2607.05198","title":"Noisy-Channel Minimum Bayes Risk Decoding","created":"2026-07-06","cited_by_count":0,"area":null},{"id":"2609.34556","title":"RoPE is Dead, Long Live RoPE: Towards Scalable Data-aware Positional Encodings","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2609.38832","title":"Scaling Parameter and Context in Attention: Native Sparse Attention from Mixture-of-Head","created":"2026-09-30","cited_by_count":0,"area":null}],"next_cursor":null}