Token Budget Allocation

Ask about this topic

Momentum

38 papers in the last four weeks, up 23% on the four weeks before. 0.4% of all new papers.

Jul 13Week of Sep 28
View on map

Latest papers 267

All topics
CardsList

  1. Dynamic Budget Allocation for LLM Evaluation under Hard Resource Constraints

    Oct 5, 2026Shai Feldman, Yaniv RomanoToken Budget AllocationLarge Language Model Evaluation

    Department of Computer Science, Technion IIT, Israel · Department of Electrical and Computer Engineering, Technion IIT, Israel

  2. Interaction-Stiffness-Guided Basis Allocation in Dynamic Movement Primitives for Efficient Skill Transfer

    Oct 1, 2026Chan Xu, Silu Chen, Dehao Wang +6Motion PrimitivesLearning Dynamics

    Zhejiang Key Laboratory of Precision Actuation and Intelligent Robotics, Ningbo Institute of Materials Technology and Engineering, Chinese Academy of Sciences, Ningbo 315201, China · University of Chinese Academy of Sciences, Beijing 100049, China · Department of Computing, The Hong Kong Polytechnic University, HKSAR, China

  3. Learning to Ask: Information Acquisition for SLM-LLM Collaboration, under a budget

    Oct 1, 2026Yongjun Kim, Xiaoxiao Li, Jaeho LeeLLM Reasoning StrategiesCollaboration

    Pohang University of Science and Technology (POSTECH) · Department of Electrical and Computer Engineering, University of British Columbia · Vector Institute

  4. Can AI Scientists Coordinate at Runtime?

    Oct 1, 2026Zijian Liu, Yangzhixin Luo, Junyu Lu +6Artificial Intelligence ScientistsMulti-Agent Orchestration

    University of Oxford · King Abdullah University of Science and Technology · University of Sydney +1

  5. Don't Waste the Noise: Importance-Guided Perturbation Allocation under Joint Global and Local Constraints

    Oct 1, 2026Melika Shirian, Kianoosh VadaeiAdversarial TrainingQuadratic Slack Penalty

    Independent Researcher

  6. Beyond Uniform Compression: Budgeted Transmission Allocation for Extreme Federated Learning

    Sep 30, 2026Pengfei Li, Mohammad KhalilFederated LearningPower Allocation

    Centre for the Science of Learning & Technology (SLATE), University of Bergen, Bergen, Norway

  7. Signal-Routed Temperature Scaling: Low-Capacity Risk-Conditioned Calibration for Small Validation Budgets

    Sep 30, 2026Wenhao Liang, Liangwei Nathan Zheng, Lin Yue +4RecalibrationCalibrated Uncertainty

    Adelaide University, Adelaide, Australia

  8. Risk-Aware Adaptive Evaluation: Finding High-Impact Failures Under Limited Budgets

    Sep 30, 2026Priyanath Maji, Spandan Ghose ChowdhuryThompson SamplingToken Budget Allocation

    Georgia Institute of Technology Atlanta, GA 30332

  9. A Competing-Hazards Systematization of Loss of Control in Autonomous Agents

    Sep 29, 2026Mohamed Aly BoukeArtificial Intelligence ControlAutonomous Agents

    Centre for Intelligent Cloud Computing, CoE for Advanced Cloud, Faculty of Information Science and Technology, Multimedia University, Jalan Ayer Keroh Lama, Bukit Beruang, 75450, Melaka, Malaysia

  10. How Many Labels Does a Language Need? Annotation Budgets and Cross-Lingual Pooling for African-Language Text Classification

    Sep 29, 2026Bhanu Prakash Vangala, Sowmya Guda, Navya VangalaAfrican LanguagesLarge Language Model Classification

    University of Missouri · Amar Bio Tech Pvt Ltd

  11. Active Budget Can Kill Sensitivity: Diagnosing and Repairing TopK Sparse Autoencoder Reliability

    Sep 29, 2026Zhenting Huang, Bo Jiang, Junnan Liu +2Improving Sparse AutoencodersTop-K

    Beihang University · Monash University · Zhongguancun Laboratory

  12. HiRAE: Hierarchical Representation Autoencoding with Residual Budgets

    Sep 29, 2026Xuanyu Zhu, Yan Bai, Yang Shi +5Autoregressive Image GenerationAutoencoder Architectures

    Peking University · Agibot Research · Tsinghua University +1

  13. WISE-ATTA: When to Ask for Labels in Budgeted Active Test-Time Adaptation

    Sep 29, 2026Muhammad Huzaifa, Lea Schönherr, Thorsten EisenhoferTest-Time AdaptationPool-Based Active Learning

    CISPA Helmholtz Center for Information Security

  14. When Should Agents Check External State? Budgeting Observations for Stored Intentions

    Sep 29, 2026Zhengkun Di, Bin Shi, Kai Sun +2Token Budget AllocationLong-Term Agent Memory

    School of Computer Science and Technology, Xi’an Jiaotong University, Xi’an, China · School of Distance Education, Xi’an Jiaotong University, Xi’an, China

  15. ModalFidelity: Routing Modalities for Deepfake Detection on a Budget

    Sep 29, 2026Oguzhan Baser, Kaan Kale, Sriram Vishwanath +1Deepfake DetectionDigital Forensics

    The University of Texas at Austin, Austin, TX, USA · Georgia Institute of Technology, Atlanta, GA, USA

  16. From Checkpoint Variation to Selection Gains in Supervised Fine-Tuning

    Sep 29, 2026Yupeng Chang, Wenxuan Zhang, Yuan WuSupervised FinetuningAlignment-Aware Selection

    School of Artificial Intelligence, Jilin University · Singapore University of Technology and Design · Key Laboratory of Symbolic Computation and Knowledge Engineering, Jilin University

  17. Paired Multimodal Scaling Laws

    Sep 28, 2026Marcus Ma, Shrikanth NarayananUnimodal MetricsScaling Laws

    University of Southern California

  18. When Less Data Favors Smaller Teachers: Rethinking Teacher Capacity and Data Selection for Knowledge Distillation

    Sep 28, 2026Minjae Park, Taesun Yeom, Jaeho LeeKnowledge DistillationTeacher

    Pohang University of Science and Technology (POSTECH)

  19. Reciprocal Guidance: Orchestrating Draft and Verify Budgets for Advancing the Diffusion-AR Self-Speculation Frontier

    Sep 28, 2026Linye Wei, Shutian Zheng, Haoyu Zeng +1Block-Diffusion DrafterSpeculative Decoding

    Institute for Artificial Intelligence, Peking University · School of Integrated Circuits, Peking University · College of Engineering, Peking University +2

  20. Test-Time Scaling via Budgeted Multi-Attribute Verification

    Sep 28, 2026Bo Xue, Ji Cheng, Shen-Huan Lyu +2Token Budget AllocationLarge Language Model Responses

    City University of Hong Kong · Hohai University · Zhejiang University

  21. When Privacy Moves ML-Mediated Decisions On Device: Information and Incentive Misalignment in Auctions

    Sep 27, 2026Dipankar SarkarBiddingIncentives

    Skelf Research

  22. Adaptive Consistency Graph for Long-Horizon Agents

    Sep 26, 2026Jiecong Wang, Hao Peng, Zhanyi WangLong-Horizon AgentsLong-Horizon Task Planning

    Beihang University · QI-ANXIN GROUP

  23. LLM Judge Validation Under Sparse Overlap: From Inference to Design

    Sep 25, 2026Junxuan Li, Arko Mukherjee, Soumyabrata PalLarge Language Model JudgesToken Budget Allocation

    Adobe · Adobe Research

  24. A General Framework for Budgeted Threshold Incentives on Request

    Sep 24, 2026Zhuolin Wu, Chengrui Zhu, Wenhua Nie +9Bike-Sharing SystemsIncentives

    Meituan · National Taiwan University · Tsinghua University +1

  25. BAS-OPD: Budget-Aware Selective On-Policy Self-Distillation for Fine-Grained Multimodal Perception

    Sep 22, 2026Zihan Chen, Hengguang Zhou, Yuan Kang +5Unsupervised On-Policy Self-DistillationRecent Vision-Language Models

    HFIPS, Chinese Academy of Sciences · University of Science and Technology of China · University of California, Los Angeles

  26. Statistical Gains from Looped Estimation under Parameter Budgets

    Sep 22, 2026Xinyu Tian, Xiaotong ShenMaximum LikelihoodStructural Complexity

    School of Statistics, University of Minnesota

  27. MatcherCompass: A Deployment-Aware Benchmark to Guide Image Matcher Selection in the Wild

    Sep 22, 2026Hyunwoo Kim, Giseop KimHarder Better Faster Denser Feature MatchingRobotic Perception

    Department of Robotics and Mechatronics Engineering, DGIST, Daegu, Republic of Korea

  28. Are Coreset Selection Methods Worth Their Cost?

    Sep 19, 2026Yangze Liu, Zhongyi HanGeometry-Aware Uncertainty CoresetsToken Budget Allocation

    Shandong University

  29. An Empirical Study of Harness Design for Coding Agents

    Sep 17, 2026Run-Ze Fan, Zihao Zhang, Simin Ma +6Coding AgentsAgent Harness

    UMass Amherst · Emory University · UNC Charlotte

  30. Evolution or Illusion? Rethinking Evaluation in LLM Evolutionary Search

    Sep 17, 2026Tal Oved, Roi Pony, Oshri Naparstek +1Evolutionary SearchGeneral Grid Search Framework

    IBM Research

  31. How Many Labels Does Model Choice Need? Certificates and Budgets for Selective Prediction

    Sep 16, 2026Tetsuji KuboyamaModel SelectionConfidence Intervals

    Computer Centre, Gakushuin University

  32. Learning-Guided Planning in Large Dynamic Action Spaces: Budgeted Tree Search for One-to-Many Mobile Charging

    Sep 15, 2026Liang-Ching Tao, Pi-Chung WangClassical PlanningLearning Policy

    Department of Computer Science and Engineering, National Chung Hsing University · Xingda Rd., South District, Taichung 402, Taiwan

  33. Corrupt Plans, Clean Traces: Evading Chain-of-Thought Monitoring with Plan Injection

    Sep 14, 2026Keertana Chidambaram, Andrew Ilyas, Vasilis SyrgkanisAdversarial RobustnessChain-of-Thought Reasoning

    Stanford University · CMU

  34. VRL-Bench: Benchmarking agents on computer control tasks under finite trial budgets

    Sep 14, 2026Yu Bai, Yukai Miao, Dawei Wang +8Offline Reinforcement LearningStochastic Exploration

    Zhongguancun Laboratory · Tsinghua University · Network Management Center, China Mobile

  35. Tone on a Budget: A Reference-Free Metric for Lexical Tone in Massively Multilingual Text-to-Speech

    Sep 13, 2026Moses Daudu, Adeola Enitan Bamidele, Honor-Jesus BezaleelSeed-Tts-Eval BenchmarkCharacter Error Rate

    Landmark University, Omu-Aran, Nigeria · Federal University of Agriculture, Abeokuta, Nigeria · Independent Researcher

  36. Component-Aware Differential Privacy for Federated Multilingual Speech-LLMs

    Sep 11, 2026Jordi Luque, Fernando López, Aleix SantStandard Differential-PrivacyGradient-Based Attacks

    Scientific Research Telef´onica Innovaci´on Digital Barcelona, Spain · Telef´onica Innovaci´on Digital Universidad Aut´onoma de Madrid Madrid, Spain · Scientific Research Telef´onica Innovaci´on Digital Universitat Polit`ecnica de Catalunya Barcelona, Spain

  37. Caption-once, Frames-on-Demand: Visual-Need Routing for Budget-Aware Agentic Long Video Understanding

    Sep 11, 2026Weitong Cai, Hang Zhang, Yukai Huang +6Video UnderstandingStreaming Video Understanding

    Queen Mary University of London · Independent Researcher · Durham University +2

  38. What Eviction Destroys: A Restore-Counterfactual Audit of Forgetting in Agent Memory

    Sep 8, 2026Chen ShenEvictionForgetting

    Megagon Labs

  39. Train What You Deploy:Token-Faithful Post-Training of a Production Coding

    Sep 7, 2026Cheng Li, Jiexiong Liu, Yixuan Chen +1Post-TrainingSingle-Token Output Distributions

    KunlunMeta

  40. A Group-Based Resource Allocation Model for the Fractional Knapsack Problem

    Sep 6, 2026Abhinaba ChakrabortyKnapsack ConstraintToken Budget Allocation

    ID Lab, University of Ghent-imec, Ghent, Belgium

  41. GrowPage: On-Demand KV Budgeting for Efficient LLM Reasoning Serving

    Sep 3, 2026Qiankun Ma, Yanjiang Zhou, Zinan Xiong +5LLM Reasoning StrategiesEfficient Large Language Model

    Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences · Pengcheng Laboratory · University of Chinese Academy of Sciences

  42. It's the Problem, Not the Path: Budget and Difficulty Confounds in LLM Reasoning Trajectories

    Sep 3, 2026Yigit Utku BulutLLM Reasoning StrategiesReasoning Traces

    Johannes Kepler University Linz

  43. HeadWiseKV: Budgeted Per-Head Cache Residency for Hybrid Long-Context Language Models

    Sep 2, 2026Renjie Xie, Juncheng Yang, Aoting Hu +4Efficient Long-Context InferenceKey-Value Cache

    Nanjing University of Posts and Telecommunications · Tylogi AI Lab / TAIL · Anhui University of Technology +2

  44. Post-Training Ternarization of Qwen3-4B Capability, Effective Bit Budget, Storage Compression, and Deployment

    Sep 2, 2026Anirudh Malik, M Sparsh Mehra, Poojith DevanQwen3Small Large Language Models

    OneBit AI

  45. The Structure of Quantization Damage in LLMs: Why the Next Bit Should Be Spent Globally

    Sep 1, 2026Jundong Hu, Shekar RamachandranLarge Language Model QuantizationQuantized

    PayPal AI

  46. Scaling Near-Optimal SFT-RL Annotation Budget Allocation from Small to Large LLMs

    Sep 1, 2026Jingtan Wang, Arun Verma, Xiaoqiang Lin +4Token Budget AllocationSmall Models

    Department of Computer Science, National University of Singapore, Republic of Singapore · Singapore-MIT Alliance for Research and Technology Centre, Republic of Singapore · Agency for Science, Technology, and Research (A*STAR), Republic of Singapore +1

  47. Parsing the Stream: A Live Trace Model for Long-Horizon Agents and Their Observers

    Sep 1, 2026Egor Pakhomov, Erik NijkampTracesLong-Horizon Agents

    Salesforce AI Research

  48. Where the Verifier Fails: A Category-Level Audit of Reward Signals in RLVR

    Sep 1, 2026Esther XinVerifiable RewardsReinforcement Learning With Verifiable Reward

    Independent Researcher

  49. One Policy, Any Budget: Internalizing Budget-Aware Search via Reinforcement Learning

    Sep 1, 2026Xiaowei Sun, Jin Li, Yili Hong +2Token Budget Allocation

    College of Computer Science and Artificial Intelligence, Fudan University · College of Software Engineering, Southeast University · School of Artificial Intelligence, Shanghai Jiao Tong University

  50. Frozen Cores Need Task Signal: Fisher-Whitened Cross-Covariance for Low-Resource LLM Adaptation

    Sep 1, 2026Wentao Ye, Zhanming Shen, Zhiqing Xiao +3Large Language Model AdaptationFrozen

    Zhejiang University · Hunyuan, Tencent

  51. Drift-Aware LLM Routing with Sparse Contexts and Shared Budgets

    Sep 1, 2026Cheung Hao Lee, Patrick WongLarge Language Model RoutingToken Budget Allocation

  52. Exact Recovery Thresholds for Weighted Data Selection in Vector-Valued Linear Regression

    Aug 31, 2026Guangjian ZhangAlignment-Aware SelectionSpectral Norm

  53. Repeatability Characterisation and Error Budget of a Consumer Structured-Light Scanner for 3-D Wound Geometry:A Rigid-Phantom Study

    Aug 31, 2026Pushkal Kumar, Aadit Aggarwal, Karlen AleksanyanReproducibilityRigid Objects

    independent researchers in the USA

  54. Budget-Aware Compression Pipeline for Single-GPU LLM Inference: Methods, Trade-offs, and Coupling Effects

    Aug 30, 2026Hongyu Yu, Yifei ShenLarge Language Model CompressionLLM Inference Optimization

    Lenovo Research · University of Washington

  55. When History Is Multimodal: Rethinking Context Management for Long-Horizon Agents

    Aug 30, 2026Jiaqi Su, Cong Pang, Jiawei Hong +4Multimodal MemoryLong-Horizon Agents

    National University of Singapore · SenseTime Research · ShanghaiTech University

  56. EVAR: Evidence-Validated Hypothesis Admission for Budget-Aware Narrative Reasoning

    Aug 30, 2026Peilin Liu, Zhiquan Ji, Jinglong PingLLM Reasoning StrategiesEvidence-Grounded Questions

    College of Software, Jilin University · School of Urban Planning and Design, Peking University

  57. PAGE-RAG: Provenance-Aware Graph Evidence Promotion for Fixed-Budget Multi-hop Retrieval-Augmented Generation

    Aug 30, 2026Haokun Deng, Xunkai Li, Hongchao Qin +1Graph-Based Retrieval Augmented GenerationHievi-Rag

    Department of Computer Science, Beijing Institute of Technology

  58. Puro-2B: Poor Lab's Qwen2-1.5B Trained on RTX 5090 within $5090

    Aug 27, 2026Kairong Luo, Jiarui Cui, Yaorui Yin +8Large Language Model PretrainingQwen3

    Tsinghua University · Pengcheng Laboratory

  59. The Axiomatic Trader: Latent Regularity, Information Budgets, and the Canonical Form of a Quantitative Investment System

    Aug 24, 2026Jiayu LiAlgorithmic TradingAxiom

  60. Coordination on a Budget: Federated Active Learning with Few Labels

    Aug 19, 2026Liam Mohr, Daphna WeinshallPool-Based Active LearningToken Budget Allocation

    School of Computer Science and Engineering The Hebrew University of Jerusalem, Jerusalem 91904, Israel