PaperScope
LIVE · 2026-09-23 05:40 UTC

quantization 17 papers this week · +125% WoW

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

Latestcs.CLcs.LGcs.AIcs.CV

Mentions per Day (30d)

Latest Papers

#TitleAuthorsCatDate
1StableVQ: Practical Guidelines for Stable Vector-Quantized Tokenizer TrainingBao Tang, Jiahao Guo, Haoxiang Cao +4cs.CV2026-09-22
2Train Where the Quantized Model Goes: On-Policy Distillation for Low-Bit ReasoningYuanteng Chen, Zhilei Liu, Peisong Wang +7cs.LG2026-09-22
3PP-Net: A Hybrid Physical-Prior Neural Network for Scattered Light Removal in Biomedical Images on Embedded DevicesYongfei Guo, Tingjin Chu, Mengzhuo Liu +2cs.CV2026-09-22
#4Latent Dataset Distillation for Human Motion PredictionGe Tian, Guang Li, Takahiro Ogawa +1cs.CV2026-09-22
#5QuantWM: Temporally Consistent 2-Bit KV Cache Quantization for World Models and Video GenerationJiaqi Zhao, Xiaobin Hu, Bo Yin +3cs.CV2026-09-22
#6Geometry-Aware Hyperbolic Residual QuantizationAlessio Colombo, Melika Ayoughics.LG2026-09-22
#7Disaggregated Quantization: Specializing LLM Prefill and DecodeAndrei Panferov, Maximilian Kleinegger, Sweta Priyadarshi +2cs.LG2026-09-22
#8Beyond Scalar Sensitivity: Activation-Aware Mixed-Precision LLM Quantization with Cross-Layer RefinementAkihiro Yoshida, Yuma Ichikawacs.LG2026-09-22
#9RGSQ: Riemannian Geometry-Sensitive Quantization for Large Vision-Language ModelsZhiping Wu, Dongdong Ren, Yangchengyu Zhou +4cs.CV2026-09-21
#10VLAQuantBench: Closed-Loop Evaluation of Post-Training Quantization for Vision-Language-Action ModelsJiuyi Xu, Qing Jin, Meida Chen +3cs.RO2026-09-21
#11SPHQuant: Efficient extreme low bit weight quantization for Vision-Language ModelsKewei Zhang, Zheng Chen, Haotong Qin +1cs.CV2026-09-21
#12When Quantization Preserves Accuracy but Not Evidence: Explanation-Aware Post-Training Quantization for Medical LLMsYeji Kim, Mi-Young Kim, Randy Goebelcs.CL2026-09-21
#13NPU Accelerator: Quantized Real-Time Vehicle Detection on PYNQ-Z1 Using FINNDaniel Gutierrez, Antonio Cuesta, Jorge Fe +2cs.AR2026-09-21
#14What Makes a Good Medical Image Tokenizer? Rethinking Reconstruction and Generation in Medical Image TokenizationNiklas Bubeck, Yundi Zhang, Vasiliki Sideri-Lampretsa +4cs.CV2026-09-21
#15QLoRA Fine-Tuning of Ministral LLM for Sequence-to-Function Protein AnnotationDemian Pavlyshenko, Bohdan Pavlyshenkocs.CL2026-09-21
#16ME-VLM:A Unified VLM for Embodied Cognition and Agent CoordinationFoundation Model, Li Auto Inccs.CV2026-09-21
#17FoldQuantVLA: Native Low-Bit Quantization of Vision-Language-Action Models via Consistent FoldingHung T. Ho, Khanh D. Nguyen, Quang D. Nguyen +5cs.RO2026-09-21
#18NAVIR: Neuromorphic Audio-Visual Speech Recognition for Robust Human-Robot Interaction on Edge HardwareLeonidas Delimpasis, Panagiota Moraiti, Antonis Porichis +2cs.LG2026-09-21
#19The Undetected Damage of Quantization on Retrieval and How to Fix ItLuca Zhou, Alessandro Zirilli, Daniele Solombrino +2cs.LG2026-09-21
#20KV-COBRA: KV Cache Compression via Co-Optimized Bit-Rank AllocationSihyeon Ha, Jaeho Lee, Yo-Seb Jeoncs.LG2026-09-21
#21From Bits to Beliefs: Recoverable Semantic Fingerprints for Black-Box Verification of Large Language ModelsJiaxin Hong, Yuxin Peng, Hongyao Yu +3cs.CR2026-09-21
#22Q-DEQ: Discrete Solving and Quantization for Deep Equilibrium Models in Time Series Forecasting under Edge Deployment Coding ConstraintsRuotong Yang, Hongdong Zhu, Qi Gao +3cs.LG2026-09-21
#23On the Efficiency-Safety Dilemma in Large Reasoning ModelsYifei Yang, Zouying Cao, Xingrui Wang +4cs.CL2026-09-20
#24Global Ranks Survive, Selected Heads Shift: BOS-Sink Topology under 4-bit Weight-Only QuantizationKuanlin Chen, Chen-Wei Kuo, Cheng-En Oucs.LG2026-09-20
#25WaveletECO: A Closed-Loop Physical ECO Platform and a Specialized Local Language ModelGuoxiang Xu, Guozhen Ji, Zijian Luo +3cs.AR2026-09-20
#26Neural Residual Modeling for Scientific Data Compression under Guaranteed Error BoundsSurya Majumder, Liangji Zhu, Sanjay Ranka +1cs.LG2026-09-19
#27SparkDiffusion: Mitigating the High-Sparsity Trap --- A Unified Framework for up to $265\times$ Single-GPU Acceleration of Visual GenerationYuxi Liu, Haoyu Li, Zekun Zhang +12cs.CV2026-09-19
#28Real-Time Plasma State Prediction via FPGA-Accelerated Quantized Recurrent Probabilistic Neural NetworksDaniel Gaytan-Villarreal, Aiken Xie, Tu Pham +5physics.plasm-ph2026-09-19
#29From Inference Engine to Inference Control Plane: Connecting vLLM, llm-d, and the Evolution of Efficient Distributed LLM ServingTwinkll Sisodiacs.AI2026-09-19
#30Dual-Locking Learned AI Models: A PIN-Based Sparse QIM Watermarking and Adaptive Index Permutation ApproachIva Vasic, Jesús Muñoz-Cádiz, Bata Vasiccs.CR2026-09-19
#31Towards Full Pipeline FP8 Reinforcement Learning for LLMsFanchao Chen, Ziheng Jiang, Ziyun Wei +5cs.LG2026-09-19
#32PointLAM: Local Attentive Mamba for Efficient Point-based 3D Object DetectionXuanming Shang, Weijia Zhang, Chao Macs.CV2026-09-18
#33ZYT-World: A Real-Time Controllable World Model for Closed-Loop Autonomous-Driving SimulationBoni Hu, Xiong Wei, Haoming Huang +19cs.CV2026-09-18
#34SpecQuant: Speculative Decoding with Multi-Parent Quantization for Adaptive LLM InferenceHarish KB, Jagadeeswaran M, Pradheep P +2cs.LG2026-09-18
#35Multi-Domain Clustering via Measure QuantizationRafael Pereira Eufrazio, Eduardo Fernandes Montesuma, Charles Casimiro Cavalcantecs.LG2026-09-18
#36Understanding LLM Quantization through Activation-Guided Compensation and Orthogonal ResidualsYamato Narita, Issei Satocs.LG2026-09-18
#37Quantization-Aware Kalman Estimation for Diffusion SamplingQitan Shi, Cheng Jin, Jiawei Zhang +1cs.CV2026-09-18
#38Score Centering Stabilizes Off-policy Reinforcement LearningMartin Marek, Max Ryabinincs.LG2026-09-17
#39Cross-Architecture Foundation-Model Distillation for Edge Flood SegmentationFabian Schmalstieg, Karsten Mueller, Wojciech Samekcs.CV2026-09-17
#40QUALS: Corpus Equilibrium for Universal Forecasting via Pattern Quantization and Learnability SynchronizationYujie Li, Zezhi Shao, Chengqing Yu +7cs.LG2026-09-17
#41D-Quant: Driftable Entropy Coding for KV Cache QuantizationYi Su, Hong Liu, Guanghua Yu +1cs.CL2026-09-17
#42MiX: Micro-Inverted-Scaling for End-to-End Low-Bit Vision-Language Model AccelerationYuan Liao, Jae-sun Seocs.AR2026-09-17
#43Predict Before You Deploy: Offline Prediction of Quantization-Induced Task Degradation for World Action ModelsJiuyi Xu, Jinjia Guo, Meida Chen +2cs.RO2026-09-16
#44ActionPiece: Rethinking Action Tokenization for Autoregressive Vision-Language-Action ModelsShijie Lian, Bin Yu, Zhaolong Shen +5cs.RO2026-09-16
#45REACT: A Fully Spiking State-Space Model for Real-Time Event-Driven Temporal PerceptionGeoffroy Keime, Nicolas Cuperlier, Benoit R. Cottereaucs.RO2026-09-16
#46${M}^2$Tok: Multi-head Multi-codebook Discrete Action Tokenization for Vision-Language-Action ModelsChunpu Xu, Zhixuan Liang, Yuhao Zhang +6cs.RO2026-09-16
#47CPR: Combining global composing, local performing and full-sequence refining in piano rendering with continuous autoregressive modellingChong Jing, Junan Zhang, Zhizheng Wucs.SD2026-09-16
#48Colla-Q: Toward Collaborative Experts in MoE Quantization via Minimax Precision BalancingEunju Shin, Jongbin Ryucs.LG2026-09-16
#49The Other Half of the Memory Wall: Serving 35B MoEs from SSD with Trained Routing PredictionYu Lin, Yiming Wang, Runyuan Cai +2cs.AI2026-09-16
#50A Calibrated Instrument for Measuring How Inference Optimizations Affect Output QualityJerry Kaplancs.CL2026-09-16

all trends · matching is case-insensitive substring after tokenization