Deterministic Reconstruction

Follow this topic Ask about this topic

Momentum

3 papers in the last four weeks, level with the four weeks before. 0.0% of all new papers.

Jul 6Week of Sep 21

Latest papers 28

All topics

XOR-Trellis: Ultra-Low-Complexity Dequantization and Curvature-Aware Hadamard-Free LLM Quantization
Sep 30, 2026Xiaofan Que, Nir Elkayam, Spandan Pyakurel +2Large Language Model Quantization Quantizer
Arm, Inc. · Rochester Institute of Technology
BVB: Benchmarking Agentic Video Understanding via Programmatic Reconstruction in Blender
Sep 14, 2026Yolo Y. Tang, Daiki Shimada, Jiayue Meng +14Video Agent Long-Video Benchmarks
University of Rochester · Sony Group Corporation · Carnegie Mellon University +1
Recurrent Dynamic Range Extension
Sep 14, 2026Sebastian Dille, Keru Fu, S. Mahdi H. Miangoleh +1High Dynamic Range Deterministic Reconstruction
Computational Photography Lab., Simon Fraser University, Canada
The Mechanics of a Swarm: A Reproducible External Reconstruction of an Unintended Agent-Coordination Episode on a Third-Party Wiki
Sep 14, 2026Philipp Lütje (Philflow, Schenefeld, Germany)Multi-Agent Coordination Swarms
Philflow, Schenefeld, Germany
Causal inference for group-contaminated structured outcomes: observable quotients, lossless reduction and exact randomization inference
Aug 12, 2026Usef Faghihi, Amir SakiCausal Inferences Partial Observability
D´epartement de math´ematiques et d’informatique Universit´e du Qu´ebec `a Trois-Rivi`eres Trois-Rivi`eres, Qu´ebec, Canada
Evidence-Calibrated Runtime Reconstruction for Agent Skills Across Heterogeneous Coding Agents
Aug 9, 2026Xueping GaoLifecycle Coding Agents
Alibaba Cloud, Hangzhou, China
FlexSplat: Flexible Feed-Forward 3D Gaussian Splatting without Point Cloud Correspondence
Aug 8, 2026Amir Sabbaghziarani, Hanting Ye, Maria Gorlatova +1Feed-Forward 3D Gaussian Splatting Novel View Synthesis
Tri-Institutional Georgia Institute of Technology/Georgia State University/Emory University Center for Translational Research in Data Science and Neuroimaging (TReNDS) · Georgia State University · Duke University +1
PTP: Previous-Token Prediction based LLM Inversion for Near-Exact Prompt Reconstruction
Jul 31, 2026Pirzada Suhail, Nagasai Saketh Naidu, Atanu R Sinha +1Prompt Engineering Natural Language Inference
IIT Bombay · Adobe Research
From Deterministic to Generative Deep Learning for Urban Air Quality Reconstruction from Sparse Observations
Jul 28, 2026Abhishek A. Sabnis, Mihai Mitrea, Lya Lugon +5Air Pollution Deterministic Reconstruction
CEREA, ENPC, Institut Polytechnique de Paris, Île-de-France, France. · Department of Computing, Imperial College London, London, UK. · Dynamic Systems Lab, University College London, London, UK. +1
Imaging-101: Benchmarking LLM Coding Agents on Scientific Computational Imaging
Jul 12, 2026Siyi Chen, Jiahe Ying, Yixuan Jia +9Deterministic Reconstruction Coding Agents
Key Laboratory of Spacecraft Design Optimization and Dynamic Simulation Technologies, Ministry of Education, Beijing, 102206, China
When Does High-CFG Diffusion Inversion Fail? A Controlled Study of Prompt--Latent Interactions
Jul 6, 2026Yan Zeng, Yusuke Hosoya, Huyen T. T. Tran +1Diffusion Inversion Diffusion-Based Image Editing
GSIS Tohoku University Sendai, Japan · RIKEN AIP JAPAN
Mixture-of-Gaussians-Guided Schedule Design for Brownian Bridge Diffusion Models
Jul 3, 2026Ron Levi, Michael EladDiffusion Bridges Schrödinger Bridges
Department of Computer Science Technion, Israel
Self-Auditing Residual Drifting for Pathology-Preserving Accelerated Knee MRI
Jul 2, 2026Qing Lyu, Jianxu Wang, Mohammad Kawas +2Magnetic Resonance Imaging Reconstruction Magnetic Resonance Imaging
Department of Radiology & Biomedical Imaging, Yale School of Medicine, New Haven, CT 06510 USA · Department of Biomedical Engineering, Rensselaer Polytechnic Institute, Troy, NY 12180 USA
Unsupervised Deep Learning for Limited-Angle STEM-EDX Tomography -- Application to 3D Chemical Analysis of Phase-Change Memory Devices
Jun 9, 2026Daniel del Pozo Bueno, Serge Brosset, Theo Monniez +3Electron Microscopy Cone-Beam Computed Tomography
1CEA, LETI, Univ. Grenoble Alpes, Grenoble, 38000, France. · 2CEA, Neurospin, Paris-Saclay University, Gif-sur-Yvette, F-91191, France. · 3Inria, MIND, Palaiseau, F-91210, France.
Hiding in Plain Floats: Steganographic Carriers for Indirect Prompt and Content Injection
Jun 7, 2026Mudit Sinha, Sanika ChavanAttacker Large Language Model Steganography
1Lineaje Inc. · 2Arizona State University.
Anchor PCA
Jun 4, 2026Benedikt Seiter, Anya Fries, Julius von Kügelgen +1Principal Component Analysis Dimensionality Reduction
ETH Zürich
SBP-Net: Learning Thin Structure Reconstruction with Sliding-Box Projections
Jun 2, 2026Ofir Gilad, Andrei Sharf3D Models Deterministic Reconstruction
Faculty of Computer and Information Science, Ben Gurion University of the Negev Beer Sheva, Israel
Richer Representations for Neural Algorithmic Reasoning via Auxiliary Reconstruction
May 30, 2026Jiafu Huang, Chao Peng, Chenyang Xu +7Representation Learning Encoders
Shanghai Key Laboratory of Trustworthy Computing, East China Normal University, China · Overseas Education College, Xiamen University, China · Dept. of Electrical and Electronic Engineering, The University of Melbourne, Australia
(HB-ARFM) History-Bootstrapped Flow Matching for Inverse Boiling Reconstruction
May 29, 2026Xianwei Zou, Sheikh Md Shakeel Hassan, Arthur Feeney +1Deterministic Reconstruction
Department of Electrical Engineering and Computer Science, University of California Irvine, USA.
Detecting Diffusion-Generated Time Series Under Generator Shift
May 27, 2026Zhi Wen Soi, Aditya Shankar, Gert Lek +4Time-Series Generation Time Series
TU Dortmund University · Delft University of Technology · University of Neuchâtel +1
Asynchronous Remote Sensing Time-Series Fusion for Cloud Removal and Anytime Reconstruction
May 26, 2026Forouzan Fallah, Chia Yu Hsu, Wenwen Li +2Sentinel-2 Remote Sensing
School of Computing and Augmented Intelligence, Arizona State University · School of Geographical Sciences and Urban Planning, Arizona State University · Woodwell Climate Research Center
Discontinuous Galerkin Neural Operator for Pathology Defocus Deblurring
May 22, 2026Shaoqing Duan, Haofei Song, Xintian Mao +2Gaussian Deblurring Motion Blur
Shanghai Key Laboratory of Multidimensional Information Processing, East China Normal University, Shanghai, China.
LCGuard: Latent Communication Guard for Safe KV Sharing in Multi-Agent Systems
May 21, 2026Sadia Asif, Mohammad Mohammadi Amiri, Momin Abbas +2Data Leakage Secure Aggregation
Rensselaer Polytechnic Institute · IBM Research
Reconstructing conformal field theoretical compositions with Transformers
May 1, 2026Haotian Cao, Garrett Merz, Kyle Cranmer +1Conformal Selection Transformer Architectures
a Department of Physics, University of Wisconsin-Madison · b Data Science Institute, University of Wisconsin-Madison
Physics-Informed Temporal U-Net for High-Fidelity Fluid Interpolation
Apr 25, 2026Eshwar R. A., Nevin Mathew Thomas, Nehal G +1Fluid Dynamics U-Net
Department of Computer Science Engineering, PES University - Electronic City Campus, Bangalore 560100, India.
Semi-Supervised Flow Matching for Mosaiced and Panchromatic Fusion Imaging
Apr 22, 2026Peiming Luo, Nan Wang, Litong Liu +4Visible Image Fusion Contrastive Flow Matching
Southeast University · Hunan University
GP-4DGS: Probabilistic 4D Gaussian Splatting from Monocular Video via Variational Gaussian Processes
Apr 3, 2026Mijeong Kim, Jungtaek Kim, Bohyung Han4D Reconstruction Gaussian Splatting
1ECE and 2IPAI, Seoul National University, Korea · University of Wisconsin–Madison, USA
Gaussians on Fire: High-Frequency Reconstruction of Flames
Nov 27, 2025Jakob Nazarenus, Dominik Michels, Wojtek Palubicki +43D Gaussian Deterministic Reconstruction
Kiel University · Germany · KAUST, CEMSE +5

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

XOR-Trellis: Ultra-Low-Complexity Dequantization and Curvature-Aware Hadamard-Free LLM Quantization

Xiaofan Que, Nir Elkayam, Spandan Pyakurel, Shuokai Pan+1

Arm, Inc. · Rochester Institute of Technology

Large Language Model Quantization Quantizer Deterministic Reconstruction

Open paper AskPDF arXiv

Trellis-coded quantization enables high-dimensional compression of large language model (LLM) weights at ultra-low bit widths without the exponentially large codebooks required by conventional vector quantization. Practical deployment, however, presents two challenges: reconstructing compressed weights at sufficient parallel throughput to avoid making dequantization an inference bottleneck, and maintaining quantization accuracy without costly incoherence transformations. We address these challenges with two complementary techniques. First, we introduce an ultra-low-complexity trellis dequantizer that uses a structured, hardware-efficient state-to-value mapping while preserving diverse reconstruction choices for trellis search. Second, we reformulate discrete trellis path optimization with a curvature-aware objective that reflects model sensitivity directly in the original coordinate space. Together, these techniques enable high-quality ultra-low-bit trellis quantization with inexpensive, highly parallel runtime reconstruction and without relying on Hadamard-based incoherence processing.

Momentum

Related topics

Latest papers 28