{"total":168,"rows":[{"id":"2112.00114","title":"Show Your Work: Scratchpads for Intermediate Computation with Language Models","created":"2021-11-30","cited_by_count":886,"area":"lr"},{"id":"2211.09085","title":"Galactica: A Large Language Model for Science","created":"2022-11-16","cited_by_count":744,"area":null},{"id":"2112.07658","title":"AdaViT: Adaptive Tokens for Efficient Vision Transformer","created":"2021-12-14","cited_by_count":362,"area":null},{"id":"2310.02226","title":"Think before you speak: Training Language Models With Pause Tokens","created":"2023-10-03","cited_by_count":264,"area":"lr"},{"id":"2506.21734","title":"Hierarchical Reasoning Model","created":"2025-06-26","cited_by_count":177,"area":"lr"},{"id":"2510.25741","title":"Scaling Latent Reasoning via Looped Language Models","created":"2025-10-29","cited_by_count":165,"area":"lr"},{"id":"2208.14271","title":"Faithful Reasoning Using Large Language Models","created":"2022-08-30","cited_by_count":130,"area":"lr"},{"id":"2205.15659","title":"The CLRS Algorithmic Reasoning Benchmark","created":"2022-05-31","cited_by_count":106,"area":null},{"id":"2410.04707","title":"Learning How Hard to Think: Input-Adaptive Allocation of LM Computation","created":"2024-10-07","cited_by_count":70,"area":"lr"},{"id":"2110.07732","title":"The Neural Data Router: Adaptive Control Flow in Transformers Improves Systematic Generalization","created":"2021-10-14","cited_by_count":62,"area":null},{"id":"2505.13898","title":"Do Language Models Use Their Depth Efficiently?","created":"2025-05-20","cited_by_count":50,"area":null},{"id":"2211.09961","title":"Path Independent Equilibrium Models Can Better Exploit Test-Time Computation","created":"2022-11-18","cited_by_count":38,"area":null},{"id":"2406.11179","title":"Learning Iterative Reasoning through Energy Diffusion","created":"2024-06-17","cited_by_count":36,"area":null},{"id":"2202.05826","title":"End-to-end Algorithm Synthesis with Recurrent Networks: Logical Extrapolation Without Overthinking","created":"2022-02-11","cited_by_count":33,"area":"lr"},{"id":"2604.11791","title":"A Mechanistic Analysis of Looped Reasoning Language Models","created":"2026-04-13","cited_by_count":33,"area":"lr"},{"id":"2206.15448","title":"Learning Iterative Reasoning through Energy Minimization","created":"2022-06-30","cited_by_count":32,"area":null},{"id":"2305.00833","title":"Learning to Reason and Memorize with Self-Notes","created":"2023-05-01","cited_by_count":30,"area":"lr"},{"id":"2502.01615","title":"Large Language Models Are Human-Like Internally","created":"2025-02-03","cited_by_count":29,"area":"mechinterp"},{"id":"2606.18206","title":"Fixed-Point Reasoners: Stable and Adaptive Deep Looped Transformers","created":"2026-06-16","cited_by_count":28,"area":null},{"id":"2407.19985","title":"Mixture of Nested Experts: Adaptive Processing of Visual Tokens","created":"2024-07-29","cited_by_count":25,"area":"moe"},{"id":"2301.13195","title":"Adaptive Computation with Elastic Input Sequence","created":"2023-01-30","cited_by_count":22,"area":null},{"id":"2502.07827","title":"Implicit Language Models are RNNs: Balancing Parallelization and Expressivity","created":"2025-02-10","cited_by_count":22,"area":"lr"},{"id":"2505.05522","title":"Continuous Thought Machines","created":"2025-05-08","cited_by_count":22,"area":null},{"id":"2410.05563","title":"Rational Metareasoning for Large Language Models","created":"2024-10-07","cited_by_count":20,"area":"lr"},{"id":"2205.11269","title":"Dynamic Split Computing for Efficient Deep Edge Intelligence","created":"2022-05-23","cited_by_count":18,"area":null},{"id":"2303.07735","title":"Can neural networks do arithmetic? A survey on the elementary numerical skills of state-of-the-art deep learning models","created":"2023-03-14","cited_by_count":18,"area":"lr"},{"id":"2306.04640","title":"ModuleFormer: Modularity Emerges from Mixture-of-Experts","created":"2023-06-07","cited_by_count":17,"area":"moe"},{"id":"2605.23872","title":"Training-Free Looped Transformers","created":"2026-05-22","cited_by_count":15,"area":"moe"},{"id":"2203.13573","title":"Unsupervised Learning of Temporal Abstractions with Slot-based Transformers","created":"2022-03-25","cited_by_count":14,"area":null},{"id":"2402.05785","title":"Limits of Transformer Language Models on Learning to Compose Algorithms","created":"2024-02-08","cited_by_count":13,"area":null},{"id":"2410.17980","title":"Scaling Stick-Breaking Attention: An Efficient Implementation and In-depth Study","created":"2024-10-23","cited_by_count":13,"area":null},{"id":"2501.06751","title":"Padding Tone: A Mechanistic Analysis of Padding Tokens in T2I Models","created":"2025-01-12","cited_by_count":13,"area":"diffusion"},{"id":"2405.15039","title":"CEEBERT: Cross-Domain Inference in Early Exit BERT","created":"2024-05-23","cited_by_count":12,"area":"inference"},{"id":"2607.20519","title":"Adaptive Depth in Looped Transformers: Diagnosing Learned Halting Gates and Trajectory Readouts","created":"2026-07-08","cited_by_count":12,"area":null},{"id":"2603.08391","title":"Adaptive Loops and Memory in Transformers: Think Harder or Know More?","created":"2026-03-09","cited_by_count":11,"area":"lr"},{"id":"2603.01914","title":"AdaPonderLM: Gated Pondering Language Models with Token-Wise Adaptive Depth","created":"2026-03-02","cited_by_count":10,"area":"lr"},{"id":"2604.15259","title":"Stability and Generalization in Looped Transformers","created":"2026-04-16","cited_by_count":10,"area":"lr"},{"id":"2111.14576","title":"Recurrent Vision Transformer for Solving Visual Reasoning Problems","created":"2021-11-29","cited_by_count":9,"area":null},{"id":"2207.13050","title":"Efficient High-Resolution Deep Learning: A Survey","created":"2022-07-26","cited_by_count":9,"area":null},{"id":"2305.20019","title":"Monotonic Location Attention for Length Generalization","created":"2023-05-31","cited_by_count":9,"area":null},{"id":"2608.18222","title":"Think Shallow, Solve Deep: Controlling Recurrent Dynamics for Reliable Test-Time Depth","created":"2026-08-18","cited_by_count":9,"area":null},{"id":"2511.02360","title":"LaRe: Latent Refocusing for Multimodal Reasoning","created":"2025-11-04","cited_by_count":8,"area":"lr"},{"id":"2112.00086","title":"Dyna-bAbI: unlocking bAbI's potential with dynamic synthetic benchmarking","created":"2021-11-30","cited_by_count":7,"area":null},{"id":"2207.02536","title":"Transformers discover an elementary calculation system exploiting local attention and grid-like problem representation","created":"2022-07-06","cited_by_count":7,"area":"lr"},{"id":"2310.08866","title":"Adaptivity and Modularity for Efficient Generalization Over Task Complexity","created":"2023-10-13","cited_by_count":7,"area":null},{"id":"2607.13491","title":"DeepLoop: Depth Scaling for Looped Transformers","created":"2026-07-15","cited_by_count":7,"area":null},{"id":"2110.04169","title":"Iterative Decoding for Compositional Generalization in Transformers","created":"2021-10-08","cited_by_count":6,"area":null},{"id":"2204.03276","title":"PALBERT: Teaching ALBERT to Ponder","created":"2022-04-07","cited_by_count":6,"area":"inference"},{"id":"2206.14048","title":"Short-Term Plasticity Neurons Learning to Learn and Forget","created":"2022-06-28","cited_by_count":6,"area":null},{"id":"2211.09937","title":"Explainability Via Causal Self-Talk","created":"2022-11-17","cited_by_count":6,"area":null},{"id":"2311.06964","title":"Adaptive recurrent vision performs zero-shot computation scaling to unseen difficulty levels","created":"2023-11-12","cited_by_count":6,"area":null},{"id":"2502.00745","title":"BEEM: Boosting Performance of Early Exit DNNs using Multi-Exit Classifiers as Experts","created":"2025-02-02","cited_by_count":6,"area":"inference"},{"id":"2510.14095","title":"Unlocking Out-of-Distribution Generalization in Transformers via Recursive Latent Space Reasoning","created":"2025-10-15","cited_by_count":6,"area":"lr"},{"id":"2602.08864","title":"Understanding Dynamic Compute Allocation in Recurrent Transformers","created":"2026-02-09","cited_by_count":6,"area":null},{"id":"2603.08082","title":"Tiny Autoregressive Recursive Models","created":"2026-03-09","cited_by_count":6,"area":null},{"id":"2608.09444","title":"Depth-adaptive Inference of Looped Language Models via Continuous Depth Batching","created":"2026-08-10","cited_by_count":6,"area":null},{"id":"2608.11233","title":"Retrofitting Recurrent Depth into a Pretrained Language Model: Installation, Extrapolation, Transfer, and Retention at Two Parameter Budgets","created":"2026-07-31","cited_by_count":6,"area":null},{"id":"2110.02865","title":"Spike-inspired Rank Coding for Fast and Accurate Recurrent Neural Networks","created":"2021-10-06","cited_by_count":5,"area":null},{"id":"2410.04424","title":"DAdEE: Unsupervised Domain Adaptation in Early Exit PLMs","created":"2024-10-06","cited_by_count":5,"area":"inference"},{"id":"2502.12214","title":"Zero Token-Driven Deep Thinking in LLMs: Unlocking the Full Potential of Existing Parameters via Cyclic Refinement","created":"2025-02-17","cited_by_count":5,"area":"lr"},{"id":"2511.08653","title":"Accelerating Training Speed of Tiny Recursive Models with Curriculum Guided Adaptive Recursion","created":"2025-11-11","cited_by_count":5,"area":"lr"},{"id":"2604.21999","title":"Universal Transformers Need Memory: Depth-State Trade-offs in Adaptive Recursive Reasoning","created":"2026-04-23","cited_by_count":5,"area":null},{"id":"2606.24898","title":"Dense Supervision Is Not Enough: The Readout Blind Spot in Looped Language Models","created":"2026-06-12","cited_by_count":5,"area":null},{"id":"2307.10779","title":"Efficient Beam Tree Recursion","created":"2023-07-20","cited_by_count":4,"area":null},{"id":"2602.08220","title":"Pretraining with Token-Level Adaptive Latent Chain-of-Thought","created":"2026-02-09","cited_by_count":4,"area":"lr"},{"id":"2603.02023","title":"PonderLM-3: Adaptive Token-Wise Pondering with Differentiable Masking","created":"2026-03-02","cited_by_count":4,"area":"lr"},{"id":"2205.12787","title":"Impartial Games: A Challenge for Reinforcement Learning","created":"2022-05-25","cited_by_count":3,"area":null},{"id":"2211.07727","title":"Logical Tasks for Measuring Extrapolation and Rule Comprehension","created":"2022-11-14","cited_by_count":3,"area":"lr"},{"id":"2302.10506","title":"Diffusion Probabilistic Models for Structured Node Classification","created":"2023-02-21","cited_by_count":3,"area":"diffusion"},{"id":"2509.23666","title":"Beyond Greedy Exits: Improved Early Exit Decisions for Risk Control and Reliability","created":"2025-09-28","cited_by_count":3,"area":"inference"},{"id":"2602.13215","title":"When to Think Fast and Slow? AMOR: Adaptive Entropy Gate for Hybrid Models","created":"2026-01-22","cited_by_count":3,"area":null},{"id":"2607.21670","title":"Ordered Action Tokens for Visuomotor Policy Learning","created":"2026-07-23","cited_by_count":3,"area":null},{"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":"2209.00735","title":"Recurrent Convolutional Neural Networks Learn Succinct Learning Algorithms","created":"2022-09-01","cited_by_count":2,"area":null},{"id":"2401.01470","title":"TPC-ViT: Token Propagation Controller for Efficient Vision Transformer","created":"2024-01-03","cited_by_count":2,"area":null},{"id":"2501.07440","title":"Attention when you need","created":"2025-01-13","cited_by_count":2,"area":null},{"id":"2502.11646","title":"Hyper-SET: Designing Transformers via Hyperspherical Energy Minimization","created":"2025-02-17","cited_by_count":2,"area":null},{"id":"2509.00079","title":"Entropy-Guided Loop: Achieving Reasoning through Uncertainty-Aware Generation","created":"2025-08-26","cited_by_count":2,"area":"lr"},{"id":"2604.25299","title":"The Thinking Pixel: Recursive Sparse Reasoning in Multimodal Diffusion Latents","created":"2026-04-28","cited_by_count":2,"area":"lr"},{"id":"2605.30202","title":"A Dual-Path Architecture for Scaling Compute and Capacity in LLMs","created":"2026-05-28","cited_by_count":2,"area":null},{"id":"2606.26463","title":"Finding the Time to Think: Learning Planning Budgets in Real-Time RL","created":"2026-06-24","cited_by_count":2,"area":null},{"id":"2607.14427","title":"Per-Token Fixed-Point Convergence in Depth-Recurrent Transformers","created":"2026-07-15","cited_by_count":2,"area":null},{"id":"2608.05084","title":"Learning When to Stop: Prefix-Optimal Dynamic Diffusion Policies for Continuous Control","created":"2026-08-05","cited_by_count":2,"area":"diffusion"},{"id":"2608.18171","title":"Looped Language Models Improve Compositional Tool Calling","created":"2026-08-17","cited_by_count":2,"area":"agents"},{"id":"2609.01449","title":"Diffusion as a Training Curriculum for Timestep-Free Iterative Reasoning","created":"2026-09-01","cited_by_count":2,"area":"diffusion"},{"id":"2201.09377","title":"An Application of Pseudo-Log-Likelihoods to Natural Language Scoring","created":"2022-01-23","cited_by_count":1,"area":null},{"id":"2309.07513","title":"RecycleNet: Latent Feature Recycling Leads to Iterative Decision Refinement","created":"2023-09-14","cited_by_count":1,"area":null},{"id":"2312.05379","title":"Exploring Parity Challenges in Reinforcement Learning through Curriculum Learning with Noisy Labels","created":"2023-12-08","cited_by_count":1,"area":null},{"id":"2407.02060","title":"Terminating Differentiable Tree Experts","created":"2024-07-02","cited_by_count":1,"area":null},{"id":"2505.14467","title":"Void in Language Models","created":"2025-05-20","cited_by_count":1,"area":null},{"id":"2601.00894","title":"When to Ponder: Adaptive Compute Allocation for Code Generation via Test-Time Training","created":"2025-12-31","cited_by_count":1,"area":null},{"id":"2601.19085","title":"Speed is Confidence","created":"2026-01-27","cited_by_count":1,"area":null},{"id":"2602.12204","title":"Learning to Forget Attention: Memory Consolidation for Adaptive Compute Reduction","created":"2026-02-12","cited_by_count":1,"area":null},{"id":"2602.17993","title":"Turbo Connection: Reasoning as Information Flow from Higher to Lower Layers","created":"2026-02-20","cited_by_count":1,"area":"lr"},{"id":"2602.24100","title":"Artificial Agency Program: Curiosity, compression, and communication in agents","created":"2026-02-27","cited_by_count":1,"area":"deeprl"},{"id":"2603.04688","title":"Why the Brain Consolidates: Predictive Forgetting for Optimal Generalisation","created":"2026-03-05","cited_by_count":1,"area":null},{"id":"2603.22570","title":"CanViT: Toward Active-Vision Foundation Models","created":"2026-03-23","cited_by_count":1,"area":null},{"id":"2605.05511","title":"Non-Myopic Active Feature Acquisition via Pathwise Policy Gradients","created":"2026-05-06","cited_by_count":1,"area":"deeprl"},{"id":"2605.09630","title":"Scratchpad Patching: Decoupling Compute from Patch Size in Byte-Level Language Models","created":"2026-05-10","cited_by_count":1,"area":"inference"},{"id":"2605.28919","title":"CosmicFish-HRM: Adaptive Reasoning via Hierarchical Recurrent Mechanisms in Compact Language Models","created":"2026-05-27","cited_by_count":1,"area":"lr"}],"next_cursor":"100"}