{"total":62,"rows":[{"id":"2507.06203","title":"A Survey on Latent Reasoning","created":"2025-07-08","cited_by_count":81,"area":"lr"},{"id":"2505.01618","title":"Don't be lazy: CompleteP enables compute-efficient deep transformers","created":"2025-05-02","cited_by_count":78,"area":null},{"id":"2503.10622","title":"Transformers without Normalization","created":"2025-03-13","cited_by_count":70,"area":null},{"id":"2507.11407","title":"EXAONE 4.0: Unified Large Language Models Integrating Non-reasoning and Reasoning Modes","created":"2025-07-15","cited_by_count":32,"area":"lr"},{"id":"2606.18206","title":"Fixed-Point Reasoners: Stable and Adaptive Deep Looped Transformers","created":"2026-06-16","cited_by_count":28,"area":null},{"id":"2602.10825","title":"Flow caching for autoregressive video generation","created":"2026-02-11","cited_by_count":25,"area":null},{"id":"2510.02091","title":"Demystifying the Roles of LLM Layers in Retrieval, Knowledge, and Reasoning","created":"2025-10-02","cited_by_count":15,"area":"lr"},{"id":"2504.00927","title":"Multi-Token Attention","created":"2025-04-01","cited_by_count":10,"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":"2510.22026","title":"Normalization in Attention Dynamics","created":"2025-10-24","cited_by_count":9,"area":null},{"id":"2602.05970","title":"Inverse Depth Scaling From Most Layers Being Similar","created":"2026-02-05","cited_by_count":9,"area":null},{"id":"2601.19895","title":"Post-LayerNorm Is Back: Stable, ExpressivE, and Deep","created":"2026-01-27","cited_by_count":7,"area":null},{"id":"2602.16490","title":"From Growing to Looping: A Unified View of Iterative Computation in LLMs","created":"2026-02-18","cited_by_count":7,"area":null},{"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":"2606.04980","title":"AlphaQ: Calibration-Free Bit Allocation for Mixture-of-Experts Quantization","created":"2026-06-03","cited_by_count":7,"area":"moe"},{"id":"2505.22014","title":"Learning in Compact Spaces with Approximately Normalized Transformer","created":"2025-05-28","cited_by_count":6,"area":null},{"id":"2505.23807","title":"DLP: Dynamic Layerwise Pruning in Large Language Models","created":"2025-05-27","cited_by_count":6,"area":null},{"id":"2505.24584","title":"AutoChemSchematic AI: Agentic Physics-Aware Automation for Chemical Manufacturing Scale-Up","created":"2025-05-30","cited_by_count":6,"area":"agents"},{"id":"2512.08819","title":"Do Depth-Grown Models Overcome the Curse of Depth? An In-Depth Analysis","created":"2025-12-09","cited_by_count":6,"area":null},{"id":"2605.12492","title":"Pion: A Spectrum-Preserving Optimizer via Orthogonal Equivalence Transformation","created":"2026-05-12","cited_by_count":6,"area":null},{"id":"2510.22228","title":"When Fewer Layers Break More Chains: Layer Pruning Harms Test-Time Scaling in LLMs","created":"2025-10-25","cited_by_count":5,"area":"lr"},{"id":"2606.25008","title":"Neural Scaling Universality: If Exponents Are Fixed, Time to Understand Coefficients","created":"2026-06-23","cited_by_count":5,"area":null},{"id":"2603.15389","title":"When Does Sparsity Mitigate the Curse of Depth in LLMs","created":"2026-03-16","cited_by_count":4,"area":null},{"id":"2602.01997","title":"On the Limits of Layer Pruning for Generative Reasoning in Large Language Models","created":"2026-02-02","cited_by_count":3,"area":"lr"},{"id":"2608.03624","title":"LoopMTP: A looped transformer guided by latent multi-token prediction","created":"2026-08-04","cited_by_count":3,"area":null},{"id":"2506.22049","title":"GPAS: Accelerating Convergence of LLM Pretraining via Gradient-Preserving Activation Scaling","created":"2025-06-27","cited_by_count":2,"area":null},{"id":"2508.10057","title":"Large Language Models Show Signs of Alignment with Human Neurocognition During Abstract Reasoning","created":"2025-08-12","cited_by_count":2,"area":"lr"},{"id":"2601.09719","title":"Bounded Hyperbolic Tangent: A Stable and Efficient Alternative to Pre-Layer Normalization in Large Language Models","created":"2025-12-26","cited_by_count":2,"area":null},{"id":"2601.22580","title":"SpanNorm: Reconciling Training Stability and Performance in Deep Transformers","created":"2026-01-30","cited_by_count":2,"area":"moe"},{"id":"2602.01167","title":"Do All Individual Layers Help? An Empirical Study of Task-Interfering Layers in Vision-Language Models","created":"2026-02-01","cited_by_count":2,"area":"mllm"},{"id":"2602.06702","title":"Explaining Grokking in Transformers through the Lens of Inductive Bias","created":"2026-02-06","cited_by_count":2,"area":null},{"id":"2602.08858","title":"FlattenGPT: Depth Compression for Transformer with Layer Flattening","created":"2026-02-09","cited_by_count":2,"area":null},{"id":"2602.21750","title":"From Words to Amino Acids: Does the Curse of Depth Persist?","created":"2026-02-25","cited_by_count":2,"area":null},{"id":"2605.06366","title":"Layer Collapse in Diffusion Language Models","created":"2026-05-07","cited_by_count":2,"area":"diffusion"},{"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":"2609.19107","title":"How Model Growth, Recursion, and Boundary Operators Influence Scaling Exponents","created":"2026-09-16","cited_by_count":2,"area":null},{"id":"2505.14467","title":"Void in Language Models","created":"2025-05-20","cited_by_count":1,"area":null},{"id":"2510.03246","title":"StructPrune: Structured Global Pruning asymptotics with $\\mathcal{O}(\\sqrt{N})$ GPU Memory","created":"2025-09-25","cited_by_count":1,"area":null},{"id":"2602.02522","title":"IMU-1: Sample-Efficient Pre-training of Small Language Models","created":"2026-01-25","cited_by_count":1,"area":null},{"id":"2602.06471","title":"Revisiting the Shape Convention of Transformer Language Models","created":"2026-02-06","cited_by_count":1,"area":"inference"},{"id":"2603.05369","title":"Progressive Residual Warmup for Language Model Pretraining","created":"2026-03-05","cited_by_count":1,"area":null},{"id":"2605.06183","title":"Rethinking Adapter Placement: A Dominant Adaptation Module Perspective","created":"2026-05-07","cited_by_count":1,"area":null},{"id":"2605.23259","title":"Multi-Gate Residuals","created":"2026-05-22","cited_by_count":1,"area":null},{"id":"2605.31220","title":"Shared Doubt: Zero-Shot Cross-Lingual Confidence Estimation for Language Models","created":"2026-05-29","cited_by_count":1,"area":null},{"id":"2608.00939","title":"Temperature-driven inversion and nonlinear dynamics in ChatGPT-like AIs","created":"2026-08-02","cited_by_count":1,"area":null},{"id":"2609.32534","title":"DepthBench: Measuring How Residual Connections Enable More Computational Depth","created":"2026-09-26","cited_by_count":1,"area":null},{"id":"2512.08475","title":"Solving Oversmoothing in GNNs via Nonlocal Message Passing: Algebraic Smoothing and Depth Scalability","created":"2025-12-09","cited_by_count":0,"area":null},{"id":"2605.14200","title":"How to Scale Mixture-of-Experts: From muP to the Maximally Scale-Stable Parameterization","created":"2026-05-13","cited_by_count":0,"area":"moe"},{"id":"2606.00732","title":"SHARP: Sleep-based Hierarchical Accelerated Replay for Long Range Non-Stationary Temporal Pattern Recognition","created":"2026-05-30","cited_by_count":0,"area":null},{"id":"2606.16112","title":"Scaling Adaptive Depth with Norm-Agnostic Residual Networks","created":"2026-06-15","cited_by_count":0,"area":null},{"id":"2606.26538","title":"CascadeFormer: Depth-Tapered Transformers Motivated by Gradient Fan-in Asymmetry","created":"2026-06-25","cited_by_count":0,"area":null},{"id":"2607.25279","title":"Many-body Tipping Dynamics of ChatGPT-like AIs","created":"2026-07-28","cited_by_count":0,"area":null},{"id":"2608.02668","title":"Sphere Retraction Normalizations","created":"2026-08-02","cited_by_count":0,"area":null},{"id":"2609.28850","title":"RECLAIM: Can Agents Reproduce the Claims of Machine Learning Papers?","created":"2026-09-23","cited_by_count":0,"area":"agents"},{"id":"2609.31098","title":"The Residual Stream's Effective Depth","created":"2026-09-25","cited_by_count":0,"area":null},{"id":"2609.32457","title":"Write Back the $\\Delta$: Revisiting the Same Tokens with Fresh Representations","created":"2026-09-26","cited_by_count":0,"area":null},{"id":"2609.36842","title":"Does the VGGT Family Need All Its Layers?","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2610.01153","title":"Looping Beyond Twice: A Scalable Recipe for Looped Mixture-of-Experts","created":"2026-10-01","cited_by_count":0,"area":"moe"},{"id":"2610.09179","title":"LayerRoPE: Dynamic Depth-wise Magnitude & Angular Superposition","created":"2026-10-06","cited_by_count":0,"area":null},{"id":"2610.13630","title":"Multi-Stream Attention Residuals","created":"2026-10-09","cited_by_count":0,"area":null},{"id":"2610.14277","title":"Echo: Error-Compensated 4-Bit Tensor-Parallel Communication for LLM Training and Inference","created":"2026-10-09","cited_by_count":0,"area":null},{"id":"2610.15159","title":"Beyond Adjacent Layers: Graph-Guided Layer Fusion for Compressing Large Language Models","created":"2026-10-10","cited_by_count":0,"area":null}],"next_cursor":null}