PaperScope
LIVE · 2026-09-03 05:40 UTC

compression 18 papers this week · -27% WoW

papers mentioning "compression" in title/abstract · 30d window

Latestcs.CLcs.LGcs.AIcs.CV

Mentions per Day (30d)

Latest Papers

#TitleAuthorsCatDate
1Measurement-Driven Sub-Network Selection for On-Premise Retrieval-Augmented Factory AgentsVasileios Rizeakos, Georgios Paisios, Alexandros Machairas +2cs.AI2026-09-02
2H3DNAS: Hardware-Aware ONNX-Native 3D Point Cloud Model CompressionAnchit Mulye, Rhythm Baghel, Sujay Kumar Ingle +1cs.LG2026-09-02
3Debias-SparseGPT: Bias-Aware Pruning for Large Language ModelsIrina Proskurina, Guillaume Metzler, Antoine Gourru +1cs.CL2026-09-02
#4Scalable Kronecker-Fisher Approximation: Efficient Hessian Analysis for Billion-Parameter Language Models CompressionViacheslav Yusupov, Daria Cherniuk, Evgeny Frolovcs.LG2026-09-02
#5VoRTeC: Taming Foundation Flow for One-step Real time Video CompressionYichong Xia, Qinhong Wu, Qinhong Wu +3cs.CV2026-09-02
#6CC-4DGS: Computational Deformation and Point-Cloud Compression for Storage-Efficient Dynamic Gaussian SplattingKyungdae Park, Chae Eun Rheecs.CV2026-09-02
#7A Unified Rate-Distortion Perspective on Vector, Product, and Scalar QuantizationXianghong Fang, Wenlong Mou, Yuan Yuan +2cs.LG2026-09-02
#8XMerge: Cross-Axis Selection and Reconstructive Layer Merging for LLM Depth CompressionJundong Hu, Shekar Ramachandrancs.LG2026-09-02
#9Train What You Deploy: Closing the MLP Reachability Gap in Low-Rank Clone DistillationWenhui Chen, Zhifeng Li, Jie Zhou +5cs.LG2026-09-02
#10Post-Training Ternarization of Qwen3-4B Capability, Effective Bit Budget, Storage Compression, and DeploymentAnirudh Malik, M Sparsh Mehra, Poojith Devancs.AI2026-09-02
#11When Does Information Sharing Improve Decentralized Discovery? Aggregation, Independent Rescue, and Equilibrium SelectionYohei Nakajimacs.AI2026-09-01
#12Emergence of Fibrations, Compression, and Symmetry Breaking in Artificial Neural NetworksOsvaldo M Velarde, Lucas C Parra, Alireza Hashemi +1cs.LG2026-09-01
#13A Mathematical Theory of Reusable Neural Bases for Network CompressionBinshuai Wangcs.LG2026-09-01
#14Can LLMs Design Video Coding Tools? A Case Study on Planar ModeYingwen Zhang, Meng Wang, Liqiang He +1cs.MM2026-09-01
#15Benchmarking Spatial, Spectral, and Self-Supervised Cues for Face Forgery Detection under Realistic DegradationLucas Cunha, Lucas Sotomaior, Lucas Gasperin +3cs.CV2026-09-01
#16LatentPress: Context Compression Beyond Text and VisionZhengze Zhou, Hejian Sangcs.LG2026-09-01
#17Contribution-Aware Bandwidth Allocation for Multimodal Split LearningIason Ofeidis, Leandros Tassiulascs.LG2026-09-01
#18Exact Risk-Complexity Laws for Projective Boundaries in Scenario Optimization and Distribution-Free CertificationGiuseppe C. Calafioreeess.SY2026-09-01
#19One Prompt Is Enough: Watermark Laundering Through Foundation Image ModelsJidong Yang, Qi Li, Wei Zong +5cs.CV2026-09-01
#20Superposed Latent AutoencoderQuanling Zhao, Jiaying Yang, Tianqi Zhang +4cs.LG2026-09-01
#21On the Design Fundamentals of Pixel Text Representation LearningChaohao Yuan, Ruifeng Yuan, Zhuoxu Huang +4cs.CV2026-09-01
#22ClinTraceBench: Source-Verifiable Longitudinal Clinical Reasoning over EHR-Derived DialoguesHuimin Wang, Zhengyi Zhao, Yutian Zhaocs.CL2026-09-01
#23Stochastic Optimization of Tree Tensor NetworksMarius Willner, Maximilian Scharf, André Uschmajew +2math.OC2026-09-01
#24MemoryWalker: Stop Training Agents on Contexts They Never SawZinco J, Xunjie Zhu, Shen Huang +3cs.LG2026-09-01
#25Can Large Language Models Forecast What Researchers Study Next?Fenghai Li, Zihan Tang, Haofei Yu +2cs.CL2026-09-01
#26A Closed-Loop Evaluation of Capability Loss and Recovery in Compressed Driving PoliciesAhmad Alfan Alfian Irfan, Nur Ahmad Khatim, Mansur Ariefcs.AI2026-09-01
#27Residual Sparsification via Output Importance for Compressing Mixture-of-Experts LLMsSeungwoo Jung, Dohyeok Kwon, Seungmin Cha +4cs.AI2026-09-01
#28Manifold-Aware General Coded Computing for Straggler-Resilient Distributed ComputingParsa Moradi, Mohammad Ali Maddah-Alics.LG2026-09-01
#29A hybrid quantum-classical neural network for learning to routeMarcus Rolf Peter Ritt, Alexsandro Santos da Rosa Júnior, Marcos Vinicius Reballo +2cs.LG2026-08-31
#30Sharp Approximation Rates for Neural Networks with Affine Latent ParameterizationsShijun Zhangcs.LG2026-08-31
#31Good Memory Has ECC: Evaluating the Memory of Vision-Language Models Beyond AccuracyShmuel Berman, Jia Dengcs.LG2026-08-31
#32Every Token Leaves a Ripple in the Stream of Thought: Eliciting Model-Internal Token Saliency for Chain-of-Thought CompressionTianyi Zhao, Yinhan He, Wendy Zheng +1cs.CL2026-08-31
#33Measure Before You Manage: Evaluating Agent Working Memory in Coding AgentsLe Chen, Zishen Wan, Baixi Sun +6cs.AI2026-08-31
#34Faithfulness Is Not Free: Auditing Offline KV-Cache Quantization in Retrieval-Augmented GenerationAtta Ul Asad, Ahsan Bilal, Muhammad Ali +2cs.CL2026-08-31
#35LightNav-0: Eliciting VLM Spatial Intelligence for Generalist Embodied NavigationShaoan Wang, Aocheng Luo, Fei Huang +17cs.RO2026-08-31
#36VCAR: Training-Free 3DGS Segmentation via View Completeness and Axis-Aware Boundary RefinementKun Cao, Di Wang, Haibin Zhu +4cs.CV2026-08-31
#37TopoCompress: Long Context Compression via Graph-Wired Semantic TrajectoriesDaniel Agyei Asante, Yang Lics.CL2026-08-31
#38SkillZip Pro: Execution-Aware Dynamic Compression of Progressively Loaded Skills for Self-Evolving AgentsXiaofan Bai, Chao Liu, Hongqiang Lin +5cs.AI2026-08-31
#39Which Rules Matter Now? Policy-Centroid Routing Before an Intelligent System ActsThomson D. Nguycs.AI2026-08-31
#40Functional Degeneracy in Neural Networks: Measurement and PruningMaria Matveev, Pascal Esser, Ayush Bharadwaj +2cs.LG2026-08-31
#41What It Costs to Compose, Rebuild, and Correct Precomputed MemoryAsa Shepardcs.CL2026-08-31
#42Tensor Methods for Language Models: From Token Representation to Training, Adaptation, Inference, Compression, and InterpretabilityMatvei Tarasov, Salman Ahmadi-Asl, Andre L. F. de Almeida +1cs.LG2026-08-31
#43DASC: Decay-Aware State Compression for Hybrid Linear-Attention ServingYanqi Yu, Pingwei Sun, Jianchao Tan +4cs.LG2026-08-31
#44Tail-Replay: Escaping the Curse of Linear Attention in Prefix Caching for Hybrid LLMsYirui Liu, Ruoling Qi, Xuaner Wu +2cs.LG2026-08-31
#45Multivariate Scientific Data Compression with Learned Cross-Variable Latent Decorrelation and Autoregressive Entropy ModelingLiangji Zhu, Anand Rangarajan, Sanjay Rankacs.LG2026-08-31
#46Exact Recovery Thresholds for Weighted Data Selection in Vector-Valued Linear RegressionGuangjian Zhangcs.LG2026-08-31
#47LaMoC: Loss-Aware Modular Compression for LLMsMohanad Odema, Jacob Songcs.AI2026-08-31
#48Budget-Aware Compression Pipeline for Single-GPU LLM Inference: Methods, Trade-offs, and Coupling EffectsHongyu Yu, Yifei Shencs.CL2026-08-30
#49Spatial Matryoshka Training for Multi-Granularity Visual Document RetrievalTrishan Singha Roy, Arkadeep Acharya, Vishwajeet Kumar +2cs.AI2026-08-30
#50Compression-Aware Abstention: Teaching LLMs to Refuse When KV-Compression Masks Remove Answer EvidenceMohammadali Khodabandehlou, Bhaskar Krishnamacharics.CL2026-08-30

all trends · matching is case-insensitive substring after tokenization