{"total":283,"rows":[{"id":"2510.26692","title":"Kimi Linear: An Expressive, Efficient Attention Architecture","created":"2025-10-30","cited_by_count":196,"area":"deeprl"},{"id":"2601.02780","title":"MiMo-V2-Flash Technical Report","created":"2026-01-06","cited_by_count":191,"area":"moe"},{"id":"2607.24653","title":"Kimi K3: Open Frontier Intelligence","created":"2026-07-27","cited_by_count":138,"area":"agents"},{"id":"2509.26645","title":"TTT3R: 3D Reconstruction as Test-Time Training","created":"2025-09-30","cited_by_count":129,"area":null},{"id":"2512.02010","title":"Four Over Six: More Accurate NVFP4 Quantization with Adaptive Block Scaling","created":"2025-12-01","cited_by_count":35,"area":null},{"id":"2608.30320","title":"On the Design of Qwen3.8-Next Architecture: Evaluation, Efficiency, and Training Stability","created":"2026-08-31","cited_by_count":35,"area":"moe"},{"id":"2603.09877","title":"InternVL-U: Democratizing Unified Multimodal Models for Understanding, Reasoning, Generation and Editing","created":"2026-03-10","cited_by_count":28,"area":"lr"},{"id":"2603.05498","title":"The Spike, the Sparse and the Sink: Anatomy of Massive Activations and Attention Sinks","created":"2026-03-05","cited_by_count":27,"area":null},{"id":"2603.04385","title":"ZipMap: Linear-Time Stateful 3D Reconstruction via Test-Time Training","created":"2026-03-04","cited_by_count":26,"area":null},{"id":"2507.20198","title":"A Survey of Token Compression for Efficient Multimodal Large Language Models","created":"2025-07-27","cited_by_count":25,"area":"mllm"},{"id":"2603.21986","title":"Speed by Simplicity: A Single-Stream Architecture for Fast Audio-Video Generative Foundation Model","created":"2026-03-23","cited_by_count":25,"area":null},{"id":"2601.22966","title":"A Unified View of Attention and Residual Sinks: Outlier-Driven Rescaling is Essential for Transformer Training","created":"2026-01-30","cited_by_count":23,"area":null},{"id":"2505.12215","title":"GMSA: Enhancing Context Compression via Group Merging and Layer Semantic Alignment","created":"2025-05-18","cited_by_count":21,"area":"inference"},{"id":"2601.22156","title":"Hybrid Linear Attention Done Right: Efficient Distillation and Effective Architectures for Extremely Long Contexts","created":"2026-01-29","cited_by_count":18,"area":null},{"id":"2609.01343","title":"SMELT: Scaling Laws for Compute-Matched MoE Looped Transformers","created":"2026-09-01","cited_by_count":18,"area":"moe"},{"id":"2507.23279","title":"Unveiling Super Experts in Mixture-of-Experts Large Language Models","created":"2025-07-31","cited_by_count":17,"area":"moe"},{"id":"2510.04800","title":"Hybrid Architectures for Language Models: Systematic Analysis and Design Insights","created":"2025-10-06","cited_by_count":14,"area":"ssm"},{"id":"2510.27527","title":"TetraJet-v2: Accurate NVFP4 Training for Large Language Models with Oscillation Suppression and Outlier Control","created":"2025-10-31","cited_by_count":14,"area":null},{"id":"2604.18933","title":"Gated Memory Policy: In-Context Memorization and Adaptation","created":"2026-04-21","cited_by_count":14,"area":null},{"id":"2512.12087","title":"BLASST: Dynamic BLocked Attention Sparsity via Softmax Thresholding","created":"2025-12-12","cited_by_count":13,"area":null},{"id":"2601.00671","title":"Fast-weight Product Key Memory","created":"2026-01-02","cited_by_count":13,"area":null},{"id":"2512.23343","title":"AI Meets Brain: Memory Systems from Cognitive Neuroscience to Autonomous Agents","created":"2025-12-29","cited_by_count":12,"area":"agents"},{"id":"2507.07814","title":"Pay Attention to Attention Distribution: A New Local Lipschitz Bound for Transformers","created":"2025-07-10","cited_by_count":11,"area":null},{"id":"2510.22603","title":"Mitigating Attention Sinks and Massive Activations in Audio-Visual Speech Recognition with LLMs","created":"2025-10-26","cited_by_count":11,"area":null},{"id":"2602.06570","title":"Baichuan-M3: Modeling Clinical Inquiry for Reliable Medical Decision-Making","created":"2026-02-06","cited_by_count":11,"area":null},{"id":"2602.14027","title":"Train Short, Inference Long: Training-free Horizon Extension for Autoregressive Video Generation","created":"2026-02-15","cited_by_count":11,"area":"diffusion"},{"id":"2602.17004","title":"Arcee Trinity Large Technical Report","created":"2026-02-19","cited_by_count":11,"area":"moe"},{"id":"2603.11487","title":"Attention Sinks Are Provably Necessary in Softmax Transformers: Evidence from Trigger-Conditional Tasks","created":"2026-03-12","cited_by_count":11,"area":null},{"id":"2510.08525","title":"Which Heads Matter for Reasoning? RL-Guided KV Cache Compression","created":"2025-10-09","cited_by_count":10,"area":"lr"},{"id":"2602.03560","title":"HySparse: A Hybrid Sparse Attention Architecture with Oracle Token Selection and KV Cache Sharing","created":"2026-02-03","cited_by_count":10,"area":"moe"},{"id":"2602.08064","title":"SiameseNorm: Breaking the Barrier to Reconciling Pre/Post-Norm","created":"2026-02-08","cited_by_count":10,"area":null},{"id":"2512.07737","title":"A scalable and real-time neural decoder for topological quantum codes","created":"2025-12-08","cited_by_count":9,"area":null},{"id":"2605.20613","title":"HRM-Text: Efficient Pretraining Beyond Scaling","created":"2026-05-20","cited_by_count":9,"area":null},{"id":"2605.23889","title":"HorizonStream: Long-Horizon Attention for Streaming 3D Reconstruction","created":"2026-05-22","cited_by_count":9,"area":null},{"id":"2607.07386","title":"Sparse Delta Memory: Scaling the State of Linear RNNs through Sparsity","created":"2026-07-08","cited_by_count":9,"area":null},{"id":"2510.09017","title":"Value-State Gated Attention for Mitigating Extreme-Token Phenomena in Transformers","created":"2025-10-10","cited_by_count":8,"area":null},{"id":"2511.07343","title":"TNT: Improving Chunkwise Training for Test-Time Memorization","created":"2025-11-10","cited_by_count":8,"area":null},{"id":"2512.21338","title":"HiStream: Efficient High-Resolution Video Generation via Redundancy-Eliminated Streaming","created":"2025-12-24","cited_by_count":8,"area":"diffusion"},{"id":"2604.09793","title":"GIANTS: Generative Insight Anticipation from Scientific Literature","created":"2026-04-10","cited_by_count":8,"area":null},{"id":"2604.10103","title":"Long-Horizon Streaming Video Generation via Hybrid Attention with Decoupled Distillation","created":"2026-04-11","cited_by_count":8,"area":"diffusion"},{"id":"2605.15336","title":"HoloMotion-1 Technical Report","created":"2026-05-14","cited_by_count":8,"area":null},{"id":"2606.07345","title":"TabSwift: An Efficient Tabular Foundation Model with Row-Wise Attention","created":"2026-06-05","cited_by_count":8,"area":null},{"id":"2601.03868","title":"What Matters For Safety Alignment?","created":"2026-01-07","cited_by_count":7,"area":"alignment"},{"id":"2601.14230","title":"MASCOT: Multi-Agent Socio-Collaborative Companion Systems","created":"2026-01-20","cited_by_count":7,"area":"agents"},{"id":"2605.08738","title":"SlimQwen: Exploring the Pruning and Distillation in Large MoE Model Pre-training","created":"2026-05-09","cited_by_count":7,"area":"moe"},{"id":"2507.23632","title":"On the Expressiveness of Softmax Attention: A Recurrent Neural Network Perspective","created":"2025-07-31","cited_by_count":6,"area":null},{"id":"2511.20102","title":"SSA: Sparse Sparse Attention by Aligning Full and Sparse Attention Outputs in Feature Space","created":"2025-11-25","cited_by_count":6,"area":null},{"id":"2511.23225","title":"TWEO: Transformers Without Extreme Outliers Enables FP8 Training And Quantization For Dummies","created":"2025-11-28","cited_by_count":6,"area":null},{"id":"2602.01519","title":"You Need an Encoder for Native Position-Independent Caching","created":"2026-02-02","cited_by_count":6,"area":null},{"id":"2602.11146","title":"Beyond VLM-Based Rewards: Diffusion-Native Latent Reward Modeling","created":"2026-02-11","cited_by_count":6,"area":"diffusion"},{"id":"2603.14337","title":"On the Nature of Attention Sink that Shapes Decoding Strategy in Omni-LLMs","created":"2026-03-15","cited_by_count":6,"area":"lr"},{"id":"2603.28740","title":"FocusVLA: Focused Visual Utilization for Vision-Language-Action Models","created":"2026-03-30","cited_by_count":6,"area":"vla"},{"id":"2605.26797","title":"Latent Recurrent Transformer: Architecture Exploration, Training Strategies, and Scaling Behavior","created":"2026-05-26","cited_by_count":6,"area":null},{"id":"2510.05862","title":"Revisiting Long-context Modeling from Context Denoising Perspective","created":"2025-10-07","cited_by_count":5,"area":null},{"id":"2510.22067","title":"Capturing Gaze Shifts for Guidance: Cross-Modal Fusion Enhancement for VLM Hallucination Mitigation","created":"2025-10-24","cited_by_count":5,"area":"mllm"},{"id":"2511.17127","title":"Training Foundation Models on a Full-Stack AMD Platform: Compute, Networking, and System Design","created":"2025-11-21","cited_by_count":5,"area":"moe"},{"id":"2601.12145","title":"Threshold Differential Attention for Sink-Free, Ultra-Sparse, and Non-Dispersive Language Modeling","created":"2026-01-17","cited_by_count":5,"area":null},{"id":"2601.14628","title":"NeuroVLA: A Brain-inspired Embodied Intelligence for Fluid and Fast Reflexive Robotics Control","created":"2026-01-21","cited_by_count":5,"area":null},{"id":"2602.01203","title":"Attention Sink Forges Native MoE in Attention Layers: Sink-Aware Training to Address Head Collapse","created":"2026-02-01","cited_by_count":5,"area":"moe"},{"id":"2602.10377","title":"Hardware Co-Design Scaling Laws via Roofline Modelling for On-Device LLMs","created":"2026-02-10","cited_by_count":5,"area":"vla"},{"id":"2602.11534","title":"Krause Synchronization Transformers","created":"2026-02-12","cited_by_count":5,"area":null},{"id":"2602.11761","title":"MiniCPM-SALA: Hybridizing Sparse and Linear Attention for Efficient Long-Context Modeling","created":"2026-02-12","cited_by_count":5,"area":null},{"id":"2603.06274","title":"Stem: Rethinking Causal Information Flow in Sparse Attention","created":"2026-03-06","cited_by_count":5,"area":"lr"},{"id":"2605.19660","title":"OScaR: The Occam's Razor for Extreme KV Cache Quantization in LLMs and Beyond","created":"2026-05-19","cited_by_count":5,"area":"inference"},{"id":"2606.23503","title":"UniverSat: Resolution- and Modality-Agnostic Transformers for Earth Observation","created":"2026-06-22","cited_by_count":5,"area":null},{"id":"2606.26560","title":"Erase-then-Delta Attention: Decoupling Erase and Write Addresses in Delta-Rule Linear Attention","created":"2026-06-25","cited_by_count":5,"area":"moe"},{"id":"2601.19657","title":"One Token Is Enough: Improving Diffusion Language Models with a Sink Token","created":"2026-01-27","cited_by_count":4,"area":"diffusion"},{"id":"2602.02180","title":"STILL: Selecting Tokens for Intra-Layer Hybrid Attention to Linearize LLMs","created":"2026-02-02","cited_by_count":4,"area":null},{"id":"2602.05228","title":"Surgery: Mitigating Harmful Fine-Tuning for Large Language Models via Attention Sink","created":"2026-02-05","cited_by_count":4,"area":"alignment"},{"id":"2602.07397","title":"Scout Before You Attend: Sketch-and-Walk Sparse Attention for Efficient LLM Inference","created":"2026-02-07","cited_by_count":4,"area":"inference"},{"id":"2603.05117","title":"SeedPolicy: Horizon Scaling via Self-Evolving Diffusion Policy for Robot Manipulation","created":"2026-03-05","cited_by_count":4,"area":"diffusion"},{"id":"2603.09573","title":"More than the Sum: Panorama-Language Models for Adverse Omni-Scenes","created":"2026-03-10","cited_by_count":4,"area":"mllm"},{"id":"2605.05365","title":"ZAYA1-8B Technical Report","created":"2026-05-06","cited_by_count":4,"area":"lr"},{"id":"2605.09992","title":"Attention Drift: What Autoregressive Speculative Decoding Models Learn","created":"2026-05-11","cited_by_count":4,"area":"inference"},{"id":"2601.15305","title":"Gated Sparse Attention: Combining Computational Efficiency with Training Stability for Long-Context Language Models","created":"2026-01-12","cited_by_count":3,"area":null},{"id":"2602.12601","title":"HyperMLP: An Integrated Perspective for Sequence Modeling","created":"2026-02-13","cited_by_count":3,"area":null},{"id":"2602.23057","title":"Affine-Scaled Attention: Towards Flexible and Stable Transformer Attention","created":"2026-02-26","cited_by_count":3,"area":null},{"id":"2603.06178","title":"Making Training-Free Diffusion Segmentors Scale with the Generative Power","created":"2026-03-06","cited_by_count":3,"area":"diffusion"},{"id":"2603.06591","title":"What Makes Position Zero Special? A Mechanistic Study of Position Zero Attention Sinks in LLMs","created":"2026-02-04","cited_by_count":3,"area":null},{"id":"2603.07461","title":"The Dual-Stream Transformer: Channelized Architecture for Interpretable Language Modeling","created":"2026-03-08","cited_by_count":3,"area":null},{"id":"2603.17771","title":"Attention Sinks Induce Gradient Sinks: Massive Activations as Gradient Regulators in Transformers","created":"2026-03-18","cited_by_count":3,"area":null},{"id":"2604.13737","title":"TokenFormer: Unify the Multi-Field and Sequential Recommendation Worlds","created":"2026-04-15","cited_by_count":3,"area":null},{"id":"2604.14191","title":"Attention to Mamba: A Recipe for Cross-Architecture Distillation","created":"2026-04-01","cited_by_count":3,"area":"ssm"},{"id":"2605.09196","title":"RigidFormer: Learning Rigid Dynamics using Transformers","created":"2026-05-09","cited_by_count":3,"area":null},{"id":"2606.03199","title":"Fast Organic Crystal Structure Prediction with Unit Cell Flow Matching","created":"2026-06-02","cited_by_count":3,"area":null},{"id":"2607.17419","title":"Kernelized Linear Attention: Breaking the Capacity Wall with Symmetric Cones","created":"2026-07-19","cited_by_count":3,"area":null},{"id":"2607.20062","title":"Solar Open 2 Technical Report","created":"2026-07-22","cited_by_count":3,"area":"agents"},{"id":"2608.13262","title":"Into the ORBIT for Time Series: Training Regimes for Foundation Models","created":"2026-08-13","cited_by_count":3,"area":null},{"id":"2512.00300","title":"TGSFormer: Scalable Temporal Gaussian Splatting for Embodied Semantic Scene Completion","created":"2025-11-29","cited_by_count":2,"area":null},{"id":"2601.12083","title":"Learning to Factorize and Adapt: A Versatile Approach Toward Universal Spatio-Temporal Foundation Models","created":"2026-01-17","cited_by_count":2,"area":null},{"id":"2601.19611","title":"Explicit Multi-head Attention for Inter-head Interaction in Large Language Models","created":"2026-01-27","cited_by_count":2,"area":"inference"},{"id":"2602.02680","title":"FlexRank: Nested Low-Rank Knowledge Decomposition for Adaptive Model Deployment","created":"2026-02-02","cited_by_count":2,"area":null},{"id":"2602.07106","title":"Ex-Omni: Enabling 3D Facial Animation Generation for Omni-modal Large Language Models","created":"2026-02-06","cited_by_count":2,"area":null},{"id":"2602.18196","title":"RAT+: Train Dense, Infer Sparse -- Recurrence Augmented Attention for Dilated Inference","created":"2026-02-20","cited_by_count":2,"area":"inference"},{"id":"2602.22479","title":"Efficient Continual Learning in Language Models via Thalamically Routed Cortical Columns","created":"2026-02-25","cited_by_count":2,"area":null},{"id":"2603.02188","title":"Multi-Head Low-Rank Attention","created":"2026-03-02","cited_by_count":2,"area":"inference"},{"id":"2603.03993","title":"Specialization of softmax attention heads: insights from the high-dimensional single-location model","created":"2026-03-04","cited_by_count":2,"area":null},{"id":"2603.13381","title":"Beyond Linearity in Attention Projections: The Case for Nonlinear Queries","created":"2026-03-11","cited_by_count":2,"area":null},{"id":"2603.24690","title":"UniICL: Systematizing Unified Multimodal In-context Learning through a Capability-Oriented Taxonomy","created":"2026-03-25","cited_by_count":2,"area":null},{"id":"2603.26539","title":"How Open Must Language Models be to Enable Reliable Scientific Inference?","created":"2026-03-27","cited_by_count":2,"area":null}],"next_cursor":"100"}