{"total":187,"rows":[{"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":"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":"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":"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":"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":"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":"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":"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":"2604.09793","title":"GIANTS: Generative Insight Anticipation from Scientific Literature","created":"2026-04-10","cited_by_count":8,"area":null},{"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":"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":"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":"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":"2602.11534","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":"2606.23503","title":"UniverSat: Resolution- and Modality-Agnostic Transformers for Earth Observation","created":"2026-06-22","cited_by_count":5,"area":null},{"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":"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":"2603.06591","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":"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":"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":"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":"2602.22479","title":"Efficient Continual Learning in Language Models via Thalamically Routed Cortical Columns","created":"2026-02-25","cited_by_count":2,"area":null},{"id":"2603.03993","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},{"id":"2603.27666","title":"Gated Condition Injection without Multimodal Attention: Towards Controllable Linear-Attention Transformers","created":"2026-03-29","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":"2604.05688","title":"Attention Editing: A Versatile Framework for Cross-Architecture Attention Conversion","created":"2026-04-07","cited_by_count":2,"area":null},{"id":"2604.17324","title":"Capacity-Controlled Global Attention for Graph Transformers","created":"2026-04-19","cited_by_count":2,"area":null},{"id":"2605.08504","title":"A Single Layer to Explain Them All:Understanding Massive Activations in Large Language Models","created":"2026-05-08","cited_by_count":2,"area":null},{"id":"2605.29891","title":"DVSM: Decoder-only View Synthesis Model Done Right","created":"2026-05-28","cited_by_count":2,"area":null},{"id":"2606.23670","title":"Tapered Language Models","created":"2026-06-22","cited_by_count":2,"area":null},{"id":"2606.30562","title":"Morphing into Hybrid Attention Models","created":"2026-06-29","cited_by_count":2,"area":null},{"id":"2607.14018","title":"Transforming Rank: How Architecture Navigates the Spectral Pathologies of Depth","created":"2026-07-15","cited_by_count":2,"area":null},{"id":"2607.27230","title":"Multi-Head Attention Residuals","created":"2026-07-22","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":"2506.08470","title":"MARMOT: Masked Autoencoder for Modeling Transient Imaging","created":"2025-06-10","cited_by_count":1,"area":null},{"id":"2509.15974","title":"BEFT: Bias-Efficient Fine-Tuning of Language Models in Low-Data Regimes","created":"2025-09-19","cited_by_count":1,"area":null},{"id":"2510.23052","title":"Knocking-Heads Attention","created":"2025-10-27","cited_by_count":1,"area":null},{"id":"2511.16378","title":"CAMS: Towards Compositional Zero-Shot Learning via Gated Cross-Attention and Multi-Space Disentanglement","created":"2025-11-20","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":"2512.15707","title":"GateFusion: Hierarchical Gated Cross-Modal Fusion for Active Speaker Detection","created":"2025-12-17","cited_by_count":1,"area":null},{"id":"2512.22562","title":"Learning When Not to Attend Globally","created":"2025-12-27","cited_by_count":1,"area":null},{"id":"2601.13768","title":"vLinear: A Powerful Linear Model for Multivariate Time Series Forecasting","created":"2026-01-20","cited_by_count":1,"area":null},{"id":"2602.02769","title":"BiTimeCrossNet: Time-Aware Self-Supervised Learning for Pediatric Sleep","created":"2026-02-02","cited_by_count":1,"area":null},{"id":"2602.07049","title":"Enhancing IMU-Based Online Handwriting Recognition via Contrastive Learning with Zero Inference Overhead","created":"2026-02-04","cited_by_count":1,"area":null},{"id":"2602.17387","title":"DRetHTR: Linear-Time Decoder-Only Retentive Network for Handwritten Text Recognition","created":"2026-02-19","cited_by_count":1,"area":null},{"id":"2603.06048","title":"GenHOI: Towards Object-Consistent Hand-Object Interaction with Temporally Balanced and Spatially Selective Object Injection","created":"2026-03-06","cited_by_count":1,"area":null},{"id":"2603.06738","title":"Rank-Factorized Implicit Neural Bias: Scaling Super-Resolution Transformer with FlashAttention","created":"2026-03-06","cited_by_count":1,"area":null},{"id":"2603.07916","title":"Rel-MOSS: Towards Imbalanced Relational Deep Learning on Relational Databases","created":"2026-03-09","cited_by_count":1,"area":null},{"id":"2604.01178","title":"Screening Is Enough","created":"2026-04-01","cited_by_count":1,"area":null},{"id":"2604.01683","title":"Invertible Query-Key Coupling Composes with Attention Mechanisms","created":"2026-04-02","cited_by_count":1,"area":null},{"id":"2605.02278","title":"HELIX: Hybrid Encoding with Learnable Identity and Cross-dimensional Synthesis for Time Series Imputation","created":"2026-05-04","cited_by_count":1,"area":null},{"id":"2605.04421","title":"FLUID: Continuous-Time Hyperconnected Sparse Transformer for Sink-Free Learning","created":"2026-05-06","cited_by_count":1,"area":null},{"id":"2605.06611","title":"The Structural Origin of Attention Sink: Variance Discrepancy, Super Neurons, and Dimension Disparity","created":"2026-05-07","cited_by_count":1,"area":null},{"id":"2605.08453","title":"Sink vs. diagonal patterns as mechanisms for attention switch and oversmoothing prevention","created":"2026-05-08","cited_by_count":1,"area":null},{"id":"2605.20798","title":"Most Transformer Modifications Still Do Not Transfer at 1-3B: A 2020-2026 Update to Narang et al. (2021) with Downstream Evaluation and a Noise Floor","created":"2026-05-20","cited_by_count":1,"area":null},{"id":"2606.09068","title":"Emergent Misalignment Can Be Induced by Sycophancy and Reversed via Alignment Gating","created":"2026-06-08","cited_by_count":1,"area":null},{"id":"2606.20027","title":"QG-MIL: A Gated Transformer Aggregator for Domain-Agnostic Multiple Instance Learning in Medical Imaging","created":"2026-06-18","cited_by_count":1,"area":null},{"id":"2606.26016","title":"MIMFlow: Integrating Masked Image Modeling with Normalizing Flows for End-to-End Image Generation","created":"2026-06-24","cited_by_count":1,"area":null},{"id":"2607.18363","title":"A Controlled Study of Attention-Only Transformers","created":"2026-07-20","cited_by_count":1,"area":null},{"id":"2607.19363","title":"AdaRoPE: Not All Attention Heads Should Rotate and Scale Equally","created":"2026-06-05","cited_by_count":1,"area":null},{"id":"2608.11805","title":"Hybrid Gated Attention","created":"2026-08-12","cited_by_count":1,"area":null},{"id":"2509.25606","title":"Effective Model Pruning: Measure The Redundancy of Model Components","created":"2025-09-30","cited_by_count":0,"area":null},{"id":"2512.22212","title":"Transformer Reconstructed with Dynamic Value Attention","created":"2025-12-22","cited_by_count":0,"area":null},{"id":"2512.23335","title":"Visual Language Hypothesis","created":"2025-12-29","cited_by_count":0,"area":null},{"id":"2601.06463","title":"Gecko: An Efficient Neural Architecture Inherently Processing Sequences with Arbitrary Lengths","created":"2026-01-10","cited_by_count":0,"area":null},{"id":"2601.08131","title":"Attention Projection Mixing with Exogenous Anchors","created":"2026-01-13","cited_by_count":0,"area":null}],"next_cursor":"100"}