Bounded-Memory

Follow this topic Ask about this topic

Momentum

10 papers in the last four weeks, up 100% on the four weeks before. 0.1% of all new papers.

Jul 6Week of Sep 21

Latest papers 47

All topics

Component-Weighted Centroid Search for Exact Incremental BPE
Sep 30, 2026Harshit Verma, Rex YingByte-Pair Encoding Bounded-Memory
Yale University
Low-Discrepancy Dither for Quantized Recurrent State Caches
Sep 30, 2026Snigdha Chandan KhilarRecurrent State Bounded-Memory
Independent Researcher
What Should an Agent Remember? Disentangling Retention from Retrieval in Bounded-Memory Evaluation
Sep 30, 2026Juli HuangRetention Bounded-Memory
Stanford University
MemEvo: Automatic Discovery of Streaming Video Memory Mechanisms
Sep 29, 2026Guohong Liu, Jialei Ye, Shanhui Zhao +2Streaming Video Understanding Bounded-Memory
Institute for AI Industry Research, Tsinghua University · Peking University
BRIDGE: Bilevel Retrieval-Credit-Aware Agentic Reinforcement Learning
Sep 29, 2026Quan Xiao, Mingda Liu, Gaowen Liu +2Agentic Reinforcement Learning Large Language Model Policy Optimization
Department of Electrical and Computer Engineering, Cornell University · Institute of Integrated Research, Institute of Science Tokyo · Cisco Research
SANTA++: Sampling Attention through Representative Keys
Sep 28, 2026Kyle Lee, Christian Z. Pratt, Ruoyu Fang +4Dynamic Sparse Attention Bounded-Memory
Department of Electrical and Computer Engineering University of California, Santa Barbara, CA, USA · Flucta, San Francisco, CA, USA
ReplayLens: Auditing Agents' Use of Outcomes
Sep 28, 2026Dong Xu, Zhangfan Yang, Jiantao Wu +5Replay Interaction History
School of Artificial Intelligence, Shenzhen University · EasternDawn · School of Computer Science, University of Nottingham Ningbo
When to Evict, Not What to Keep: Draft-Guided Eviction for Training-Free KV-Cache Compression
Sep 27, 2026Haeyong Kang, Chang D. YooEviction Key-Value Cache Compression
Duksung Women’s University · KAIST
DeltaS: Reading the Gated Linear Attention State for KV Cache Eviction in Streaming Video
Sep 23, 2026Taeyoun Kwon, Seungjin Kim, Hyeonyu Kim +1Kimi Delta Attention Linear Attention
Maum AI Inc. · Seoul National University · Yonsei University
MORSE: Multi-Context Ordering via Reverse Scoring for Evidence-Preserving Compression
Sep 23, 2026Ke Wan, Yifan Wang, Liheng Lai +1Data Compression Methods Bounded-Memory
Department of Computer Science University of Virginia Charlottesville, VA, USA · AfterQuery
CliffCompaction: Cost-Efficient Compaction for Long-Horizon Coding Agents
Sep 22, 2026Trang Nguyen, Eulrang Cho, Bingqing Chen +1Compaction Bounded-Memory
Carnegie Mellon University · Bosch Center for AI
Beyond Class Marginals: Bounding Rehearsal Gaps without Freezing Class Co-occurrence
Sep 22, 2026Congren Dai, Nat Roongjirarat, Fei YeLayer-Selective Rehearsal Strategy Deterministic Replay
Imperial College London · King’s College London · University of Electronic Science and Technology of China
Temporal Recurrence Favors Fewer Layers
Sep 14, 2026Ivan Anokhin, Johan Obando-Ceron, Irina Rish +1Recurrent Model Recurrence
Mila – Qu´ebec AI Institute · Universit´e de Montr´eal · Sakana AI
Sparse Weight and Edge Circuit Discovery in Transformer-based Acoustic Models
Sep 11, 2026Jiankun Wei, Ewan Dunbar, Gerald PennTransformer Encoder Neural Audio
Department of Computer Science University of Toronto Toronto, Canada
Superposed Latent Autoencoder
Sep 1, 2026Quanling Zhao, Jiaying Yang, Tianqi Zhang +4Autoencoder Architectures Future Latent Representations
University of California San Diego · Georgia Institute of Technology · University of California Riverside +1
StreamScout: Learning When to Look Deeper for Streaming Video Understanding
Aug 31, 2026Ce Zhang, Jing Bi, Jinxi He +9Streaming Video Understanding Bounded-Memory
Carnegie Mellon University · TikTok · University of Rochester +2
DASC: Decay-Aware State Compression for Hybrid Linear-Attention Serving
Aug 31, 2026Yanqi Yu, Pingwei Sun, Jianchao Tan +4Kimi Delta Attention Recurrent State
East China Normal University · Meituan · South China University of Technology
SubZero+: Memory-Efficient Adaptive Zeroth-Order LLM Fine-Tuning in Random Subspaces
Aug 16, 2026Ziming Yu, Shuyao Xiao, Xingyu Zhao +6Zeroth-Order Large Language Model Fine-Tuning
Beijing Normal University · Singapore Management University · Xiaomi Inc. +2
Quantum Coordination Advantages in AI State-Tracking Tasks: Semantic Compilation and Latent Memory
Aug 11, 2026Ming YangState-Tracking Tractability
Batch Size or Negatives? A Selection Rule for Memory-Constrained Recommender Training
Aug 11, 2026Artyom Sabitov, Daniil Volkov, Alexey ZaytsevReal-World Content Recommendation Problem Bounded-Memory
Applied AI Institute, Moscow, Russia Risk department
Memory-Efficient Activation Checkpointing with Sliding Window and Hirschberg's Algorithm for 0/1 Knapsack Solving in PyTorch
Aug 9, 2026Jędrzej MaczanKnapsack Constraint Pytorch
Cohere Labs Community Poland
MESH: Memory-Efficient Sinkhorn Optimization for Mixture-of-Experts Training
Aug 5, 2026Masato FujitakeMixture-Of-Experts Adam
FA Research, Fast Accounting Co., Ltd.
FlashTrie: A GPU-Accelerated Constrained Beam Search for Generative Retrieval
Jul 10, 2026Dakshitha Anandakumar, Anurag Mukkara, Wenxiang Hu +5Beam Search Constrained Decoding
Microsoft, Redmond, WA, USA · Nvidia, Santa Clara, CA, USA
KVpop -- Key-Value Cache Compression with Predictive Online Pruning
Jul 6, 2026Lukas Hauzenberger, Niklas Schmidinger, Anamaria-Roberta Hartl +5Key-Value Cache Eviction Key-Value Cache Compression
1NXAI · 2Johannes Kepler University Linz, Austria
AgenticSTS: A Bounded-Memory Testbed for Long-Horizon LLM Agents
Jul 2, 2026Xiangchen Cheng, Yunwei Jiang, Jianwen Sun +7Long-Term Agent Memory Strategic Reasoning
Alaya Lab · Shanghai Jiao Tong University · Shanghai Innovation Institute +2
CARVE: Content-Aware Recurrent with Value Efficiency for Chunk-Parallel Linear Attention
Jun 25, 2026Sayak DuttaRecurrent Model Kimi Delta Attention
Space-Efficient Language Generation in the Limit
Jun 24, 2026Nicolas Flammarion, Chirag Pabbaraju, Hristo Papazov +2Bounded-Memory Optimal Sample Complexity
EPFL, Switzerland · Stanford University, USA
Unifying Data, Memory, and Compute Efficiency in LLM training: A Survey
Jun 9, 2026Vanessa Schmidt, Huy Hoang Nguyen, Cédric Jung +2Alignment-Aware Selection Large Language Model Training
Chair of Information Theory and Data Analytics (INDA), RWTH Aachen University, 52074 Aachen, Germany · AIT Austrian Institute of Technology GmbH, 1210 Vienna, Austria · Automation and Control Institute, Technische Universität Wien (TUW), 1040 Vienna, Austria
On Language Generation in the Limit with Bounded Memory
May 28, 2026Jon Kleinberg, Anay Mehrotra, Amin Saberi +1Bounded-Memory Learnability
Cornell University · Stanford University · Google Research
Approaching I/O-optimality for Approximate Attention
May 22, 2026Pál András Papp, Aleksandros Sobczyk, Anastasios ZouziasKimi Delta Attention Matrix Multiplication
Computing Systems Lab, Huawei Technologies, Zurich, Switzerland
Memory-Efficient Partitioned DNN Inference on Resource-Constrained Android Crowds
May 20, 2026Lakshani Manamperi, Disumi Pathirana, Thiwanka Pathirana +2Resource-Constrained Edge Devices Neural Network Inference
Department of Computer Science and Engineering, University of Moratuwa, Moratuwa, Sri Lanka.
Minimal-Intervention KV Retention via Set-Conditioned Diversity
May 14, 2026Libo Sun, Po-wei Harn, Peixiong He +1Key-Value Cache Compression Cache
Department of Computer Science and Software Engineering Auburn University, Auburn, AL, USA · Department of Information Management National Central University, Taoyuan, Taiwan
KV-Fold: One-Step KV-Cache Recurrence for Long-Context Inference
May 12, 2026Alireza Nadali, Patrick Cooper, Ashutosh Trivedi +1Efficient Long-Context Inference Kv-Cache Management
Department of Computer Science University of Colorado Boulder Boulder, Colorado, 80301
Navigating LLM Valley: From AdamW to Memory-Efficient and Matrix-Based Optimizers
May 9, 2026Aditya RanganathOptimizer Design Large Language Model Training
Center for Applied Scientific Computing Lawrence Livermore National Laboratory Livermore, CA, USA
Effective and Memory-Efficient Alternatives to ECC for Reliable Large-Scale DNNs
May 8, 2026Mohammad Hasan Ahmadilivani, Marten Roots, Marco Restifo +3Error Correction Neural Network Inference
Tallinn University of Technology, Tallinn, Estonia · ARM Ltd., Cambridge, United Kingdom
Nearly Optimal Attention Coresets
May 7, 2026Edo Liberty, Alexandr Andoni, Eldar KleinerGeometry-Aware Uncertainty Coresets Bounded-Memory
The Impossibility Triangle of Long-Context Modeling
May 6, 2026Yan ZhouSequence Modeling Bounded-Memory
School of Mathematics and Statistics Changsha University of Science and Technology Changsha, Hunan 410114, China
Budget-aware Auto Optimizer Configurator
May 6, 2026Kang Liu, Wei Peng, Jianchen HuOptimizer Design Graphics Processing Unit Memory
School of Future Technology Xi’an Jiaotong University Xi’an, China · School of Automation Science and Engineering Xi’an Jiaotong University Xi’an, China
Memory-Efficient Continual Learning with CLIP Models
May 5, 2026Ryan King, Gang Li, Bobak Mortazavi +1Contrastive Language-Image Pre-Training Model Replay-Based Continual Learning
Department of Computer Science Texas A&M University College Station, TX 77843 · Texas A&M University College Station, TX 77843
Activation Compression in LLMs: Theoretical Analysis and Efficient Algorithm
May 2, 2026Wen-Da Wei, Han-Bin Fang, Yang-Di Liu +3Large Language Model Compression Task-Aware Compression
Nanjing University, Nanjing, China · Tsinghua University, Beijing, China · Huazhong University of Science and Technology, Wuhan, China +1
Syntactically-guided Information Maintenance in Sentence Comprehension
Apr 30, 2026Shinnosuke Isono, Kohei KajikawaSyntactic Structure Bounded-Memory
NINJAL · Georgetown University
Universal Transformers Need Memory: Depth-State Trade-offs in Adaptive Recursive Reasoning
Apr 23, 2026Grigory SapunovBounded-Memory Transformer Architectures
Intento
Onyx: Cost-Efficient Disk-Oblivious ANN Search
Apr 22, 2026Deevashwer Rathee, Jean-Luc Watson, Zirui Neil Zhao +2Approximate Nearest-Neighbor Search Neural Architecture Search
UC Berkeley, NVIDIA · NVIDIA · UT Austin, NVIDIA +1
RELOAD: A Robust and Efficient Learned Query Optimizer for Database Systems
Apr 16, 2026Seokwon Lee, Jaeyoung Sim, Sihyun Kim +3Prompt Optimization Queries
Yonsei University BDAI Lab, Seoul 03722, South Korea · Microsoft Gray Systems Lab, Redmond, USA
Rheos: Modelling Continuous Motion Dynamics in Hierarchical 3D Scene Graphs
Mar 9, 2026Iacopo Catalano, Francesco Verdoja, Javier Civera +23D Scene Graphs Motion Model
University of Turku, Finland · School of Electrical Engineering, Aalto University, Finland · University of Zaragoza, Spain +2
ButterflyMoE: Compression-Scalable Ternary Experts via Structured Butterfly Orbits
Jan 20, 2026Aryan KarmoreExperts Bounded-Memory
Indian Institute of Information Technology, Nagpur
Poincaré Meets Bellman: Revisable Memory, Operational Quotients, and Evidence-Supported Learning in Changing Environments
Nov 28, 2025Xin LiBellman Equation Bounded-Memory
Department of Computer Science University at Albany

Sep 30, 2026, cs.DSJ/K move · Enter open · S save

Component-Weighted Centroid Search for Exact Incremental BPE

Harshit Verma, Rex Ying

Yale University

Byte-Pair Encoding Bounded-Memory O(\Bar{K}\Log N)$

Open paper AskPDF arXiv

Exact incremental BPE maintains the canonical tokenization state after every appended byte. The recent algorithm of Jiang and Gong (2026) does this in

O(\log^2 t)

worst-case time, where

t

is the maximum canonical token length. Its centroid search visits

O(\log t)

components and can pay another

O(\log t)

for ordered point location at each one. Within Jiang and Gong's normalized/proper merge-stage model, we change only that local search. Each interval is weighted by the size of the recursive component it selects, so a move from size

m

to size

m'

costs

O(1+\log(m/m'))

. These charges telescope, giving

O(\log t)

time per append and

O(n\log t)

over an

n

-byte stream, with the same BPE semantics and asymptotic space. We also construct a normalized proper BPE family over a fixed alphabet where count-balanced search uses

Θ(\log^2 t)

probes on a reachable update, while the weighted search uses

Θ(\log t)

. A Rust implementation matches the predicted probe counts on every tested instance. On ordinary vocabularies the queried degrees are small, however, and the improvement is a worst-case guarantee rather than an average-speed result.

Momentum

Related topics

Latest papers 47