Overview

Adaptive computation studies how models can spend more processing on difficult or uncertain inputs and skip redundant work on easier ones, improving efficiency without giving up accuracy. Common approaches include early-exit networks, token routing, recurrent and latent reasoning with learned halting, and difficulty- or uncertainty-based compute routers; related methods adapt visual observation and planning budgets. These techniques are tested in settings such as mathematical reasoning, language modeling, multimodal video, edge vision, and robotics, with efficiency measured in FLOPs, tokens, latency, memory, or energy. A central challenge is making predicted compute needs reliable while ensuring savings translate into real speedups, and evaluating gains against strong fixed-compute baselines across changing tasks and hardware.

Latest papers

CardsList

117 papers16 papers in the last four weeks, down 38% on the four weeks before. 0.1% of all new papers.

  1. Conformally Calibrated Adaptive Computation in Neural Operators

    Nov 17, 2026Abdul Qadir Ibrahim, Martin Burger, Abel Maviano JonathanAdaptive ComputationCost-Aware Inference

  2. Probabilistic State Space Enumeration in Neural Network Computation

    Nov 11, 2026Victor O. K. Li, Yang Han, Jacqueline C. K. LamEfficient Neural Network InferenceAdaptive Computation

  3. Branch-and-Commit for Frozen RL Agents: When and Where to Spend Test-Time Compute

    Nov 8, 2026Sahar Admoni, Assaf Hallak, Yftah Ziser +1Reinforcement LearningTest-Time RL

  4. Learning When to Think: Adaptive Internal Computation for Reinforcement Learning

    Nov 7, 2026Rohit Kumar Salla, Simon StepputtisReinforcement LearningAdaptive Computation

  5. LooM: Loop-Invariant Memory for Causal Encoder-Decoder Language Models

    Nov 4, 2026Lele Yang, Muxi Diao, Zhonghao Yan +7Adaptive ComputationRecurrent Transformers

  6. Dory1.0-4B: A Looped Normalized-GPT

    Nov 2, 2026Maxim Fishman, Simeng Sun, Shantanu Acharya +6LLM InferenceRecurrent Language Models

  7. DEQ-Stereo: Deep Euilibrium Video Stereo Matching via Adaptive Convergence

    Oct 29, 2026Kiljoon Han, Kyumin Hwang, Wonhyeok Choi +2Stereo MatchingAdaptive Computation

  8. Does Scaling Toward AGI Depend on What System-1 Lets System-2 Execute?

    Oct 29, 2026Qi Wang, Yun Qu, Lizhou Cai +10AI Agent ArchitectureLLM Agent Efficiency

  9. Beyond Causal Masks: Auditing and Localizing Hidden Future-Token Leakage in Adaptive Sequence Models

    Oct 22, 2026Huiting Liu, Jinsong WuLook-Ahead Bias in Language ModelsLLM Auditing

  10. Think Harder Where It Matters: Item-Level Adaptive Recursion for Sequential Recommendation

    Oct 21, 2026Zhanshuo Cao, Jiakai Tang, Yuqi Zhou +2Sequential RecommendationAdaptive Computation

  11. Adaptive Replay Refinement: Allocating Test-Time Compute Between Revision and Resampling

    Oct 20, 2026Ahsan Bilal, Muhammad Ahmed Mohsin, Muhammad Umer +3Inference-Time Compute AllocationTest-Time Scaling

  12. recAMPLIFY: Large-Scale Pretraining of Recursive Protein Language Models

    Oct 19, 2026Saurav Jha, Qianli Liao, Robert Vernon +2Protein Language ModelsRecursive Language Models

  13. Sep-Latent: Separator Tokens as Natural Compression Anchors for Implicit Reasoning

    Oct 16, 2026Yinlong Xu, Jianfeng Huang, Zhengdong Zhou +5Efficient Language Model ReasoningImplicit Reasoning in Language Models

  14. LEV: Thinking Fast and Deep with Looped Decision Models

    Oct 14, 2026Dingjie Song, Zhiling Yan, Yuxuan Zhang +1Efficient Language Model InferenceAdaptive Computation

  15. Adaptive Observation Control for Active Visual Recognition

    Oct 14, 2026Dikai Li, Weijia Wang, Yuan-Gen WangActive Visual PerceptionAdaptive Computation

  16. Adaptive Computation with Conformal Certification

    Oct 13, 2026Shehtab Zaman, Aneesh Rangnekar, Nancy Lee +1Adaptive ComputationConformal Risk Control

  17. Resample the Answer: Where to Spend Test-Time Compute in Recursive Reasoning

    Oct 12, 2026Maxime IllouzRecursive Reasoning ModelsInference-Time Search

  18. SpikCTU: A Compact Spiking Network with Adaptive Recurrent Computation for Speech Command Recognition

    Oct 10, 2026Jin Li, Wenbin Jiang, Tao Chen +1Spiking Neural NetworksEfficient Neural Network Inference

  19. Phonology-Aware Speaker Extraction Frontend for Audio LLMs

    Oct 9, 2026Yanxiang Chen, Haoyuan Deng, Jinyu Wang +4Target Speaker ExtractionSpeech Processing

  20. Enabling Dynamic Computation in Looped LMs

    Oct 6, 2026Aayush Mishra, Arnau Padrés Masdemont, Victor Conchello Vendrell +3LLM Inference AccelerationAdaptive Computation

  21. AdaLoop: Adaptive-Depth Latent Reasoning for Audio Language Models

    Oct 3, 2026Lee Seung-woo, Bowen QiAudio-Language ModelsAudio Reasoning