Pavlo Molchanov

Affiliations:

Nvidia Corporation, Santa Clara, CA, USA

According to our database¹, Pavlo Molchanov authored at least 131 papers between 2013 and 2026.

Collaborative distances:

Dijkstra number² of four.
Erdős number³ of three.

Timeline

Legend:

Book In proceedings Article PhD thesis Dataset Other

Bibliography

2026

Grounded 3D-Aware Spatial Vision-Language Modeling.

[BibT_eX]

[DOI]

Vidya Nariyambut Murali

CoRR, May, 2026

Agent Explorative Policy Optimization for Multimodal Agentic Reasoning.

[BibT_eX]

[DOI]

CoRR, May, 2026

X-Token: Projection-Guided Cross-Tokenizer Knowledge Distillation.

[BibT_eX]

[DOI]

Sharath Turuvekere Sreenivas

Adithyakrishna Venkatesh Hanasoge

CoRR, May, 2026

Star Elastic: Many-in-One Reasoning LLMs with Efficient Budget Control.

[BibT_eX]

[DOI]

CoRR, May, 2026

R<sup>2</sup>-dLLM: Accelerating Diffusion Large Language Models via Spatio-Temporal Redundancy Reduction.

[BibT_eX]

[DOI]

CoRR, April, 2026

Fast-dVLM: Efficient Block-Diffusion VLM via Direct Conversion from Autoregressive VLM.

[BibT_eX]

[DOI]

CoRR, April, 2026

Attend Before Attention: Efficient and Scalable Video Understanding via Autoregressive Gazing.

[BibT_eX]

[DOI]

CoRR, March, 2026

Stateful Token Reduction for Long-Video Hybrid VLMs.

[BibT_eX]

[DOI]

Jindong Jiang

Amala Sanjay Deshmukh

CoRR, March, 2026

Extending Puzzle for Mixture-of-Experts Reasoning Models with Application to GPT-OSS Acceleration.

[BibT_eX]

[DOI]

CoRR, February, 2026

C-RADIOv4 (Tech Report).

[BibT_eX]

[DOI]

CoRR, January, 2026

GDPO: Group reward-Decoupled Normalization Policy Optimization for Multi-reward RL Optimization.

[BibT_eX]

[DOI]

CoRR, January, 2026

2025

Efficient-DLM: From Autoregressive to Diffusion Language Models, and Beyond in Speed.

[BibT_eX]

[DOI]

Yonggan Fu

Lexington Allen Whalen

CoRR, December, 2025

GSPN-2: Efficient Parallel Sequence Modeling.

[BibT_eX]

[DOI]

CoRR, December, 2025

ToolOrchestra: Elevating Intelligence via Efficient Model and Tool Orchestration.

[BibT_eX]

[DOI]

CoRR, November, 2025

Nemotron-Flash: Towards Latency-Optimal Hybrid Small Language Models.

[BibT_eX]

[DOI]

Yonggan Fu

Xin Dong

Shizhe Diao

Matthijs Van Keirsbilck

CoRR, November, 2025

Nemotron Elastic: Towards Efficient Many-in-One Reasoning LLMs.

[BibT_eX]

[DOI]

Ali Taghibakhshi

Sharath Turuvekere Sreenivas

Saurav Muralidharan

Ruisi Cai

Marcin Chochowski

Ameya Sunil Mahabaleshwarkar

CoRR, November, 2025

TiDAR: Think in Diffusion, Talk in Autoregression.

[BibT_eX]

[DOI]

CoRR, November, 2025

Reasoning Visual Language Model for Chest X-Ray Analysis.

[BibT_eX]

[DOI]

CoRR, October, 2025

ProfBench: Multi-Domain Rubrics requiring Professional Knowledge to Answer and Judge.

[BibT_eX]

[DOI]

CoRR, October, 2025

OmniVinci: Enhancing Architecture and Data for Omni-Modal Understanding LLM.

[BibT_eX]

[DOI]

CoRR, October, 2025

DLER: Doing Length pEnalty Right - Incentivizing More Intelligence per Token via Reinforcement Learning.

[BibT_eX]

[DOI]

CoRR, October, 2025

BroRL: Scaling Reinforcement Learning via Broadened Exploration.

[BibT_eX]

[DOI]

CoRR, October, 2025

Fast-dLLM v2: Efficient Block-Diffusion LLM.

[BibT_eX]

[DOI]

CoRR, September, 2025

3D Aware Region Prompted Vision Language Model.

[BibT_eX]

[DOI]

Subhashree Radhakrishnan

CoRR, September, 2025

Universal Deep Research: Bring Your Own Model and Strategy.

[BibT_eX]

[DOI]

Peter Belcak

Pavlo Molchanov

CoRR, September, 2025

Scaling Up RL: Unlocking Diverse Reasoning in LLMs via Prolonged Training.

[BibT_eX]

[DOI]

CoRR, July, 2025

Minifinetuning: Low-Data Generation Domain Adaptation through Corrective Self-Distillation.

[BibT_eX]

[DOI]

CoRR, June, 2025

Small Language Models are the Future of Agentic AI.

[BibT_eX]

[DOI]

CoRR, June, 2025

CLIMB: CLustering-based Iterative Data Mixture Bootstrapping for Language Model Pre-training.

[BibT_eX]

[DOI]

CoRR, April, 2025

TwinTURBO: Semi-Supervised Fine-Tuning of Foundation Models via Mutual Information Decompositions for Downstream Task and Latent Spaces.

[BibT_eX]

[DOI]

Guillaume Quétant

Pavlo Molchanov

Slava Voloshynovskiy

CoRR, March, 2025

FeatSharp: Your Vision Model Features, Sharper.

[BibT_eX]

[DOI]

CoRR, February, 2025

Entropy-Regularized Process Reward Model.

[BibT_eX]

[DOI]

Trans. Mach. Learn. Res., 2025

Advancing Weight and Channel Sparsification with Enhanced Saliency.

[BibT_eX]

[DOI]

Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, 2025

Efficient Hybrid Language Model Compression through Group-Aware SSM Pruning.

[BibT_eX]

[DOI]

Ali Taghibakhshi

Sharath Turuvekere Sreenivas

Ameya Mahabaleshwarkar

Proceedings of the Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2025, 2025

Nemotron-Flash: Towards Latency-Optimal Hybrid Small Language Models.

[BibT_eX]

[DOI]

Yonggan Fu

Xin Dong

Shizhe Diao

Matthijs Van Keirsbilck

Proceedings of the Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2025, 2025

Scaling RL to Long Videos.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2025, 2025

LaCache: Ladder-Shaped KV Caching for Efficient Long-Context Modeling of Large Language Models.

[BibT_eX]

[DOI]

Proceedings of the Forty-second International Conference on Machine Learning, 2025

FeatSharp: Your Vision Model Features, Sharper.

[BibT_eX]

[DOI]

Proceedings of the Forty-second International Conference on Machine Learning, 2025

Puzzle: Distillation-Based NAS for Inference-Optimized LLMs.

[BibT_eX]

[DOI]

Proceedings of the Forty-second International Conference on Machine Learning, 2025

LongMamba: Enhancing Mamba's Long-Context Capabilities via Training-Free Receptive Field Enlargement.

[BibT_eX]

[DOI]

Proceedings of the Thirteenth International Conference on Learning Representations, 2025

LongVILA: Scaling Long-Context Visual Language Models for Long Videos.

[BibT_eX]

[DOI]

Proceedings of the Thirteenth International Conference on Learning Representations, 2025

LLaMaFlex: Many-in-one LLMs via Generalized Pruning and Weight Sharing.

[BibT_eX]

[DOI]

Proceedings of the Thirteenth International Conference on Learning Representations, 2025

Hymba: A Hybrid-head Architecture for Small Language Models.

[BibT_eX]

[DOI]

Ameya Sunil Mahabaleshwarkar

Shih-Yang Liu

Matthijs Van Keirsbilck

Proceedings of the Thirteenth International Conference on Learning Representations, 2025

Token-Efficient VLM: High-Resolution Image Understanding Via Dynamic Region Proposal.

[BibT_eX]

[DOI]

Proceedings of the IEEE/CVF International Conference on Computer Vision, 2025

Scaling Vision Pre-Training to 4K Resolution.

[BibT_eX]

[DOI]

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2025

VILA-M3: Enhancing Vision-Language Models with Medical Expert Knowledge.

[BibT_eX]

[DOI]

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2025

NVILA: Efficient Frontier Visual Language Models.

[BibT_eX]

[DOI]

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2025

FlexGS: Train Once, Deploy Everywhere with Many-in-One Flexible 3D Gaussian Splatting.

[BibT_eX]

[DOI]

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2025

RADIOv2.5: Improved Baselines for Agglomerative Vision Foundation Models.

[BibT_eX]

[DOI]

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2025

2024

RADIO Amplified: Improved Baselines for Agglomerative Vision Foundation Models.

[BibT_eX]

[DOI]

CoRR, 2024

NVILA: Efficient Frontier Visual Language Models.

[BibT_eX]

[DOI]

CoRR, 2024

VILA-M3: Enhancing Vision-Language Models with Medical Expert Knowledge.

[BibT_eX]

[DOI]

CoRR, 2024

EoRA: Training-free Compensation for Compressed LLM with Eigenspace Low-Rank Approximation.

[BibT_eX]

[DOI]

CoRR, 2024

PHI-S: Distribution Balancing for Label-Free Multi-Teacher Distillation.

[BibT_eX]

[DOI]

CoRR, 2024

LLM Pruning and Distillation in Practice: The Minitron Approach.

[BibT_eX]

[DOI]

Sharath Turuvekere Sreenivas

CoRR, 2024

LongVILA: Scaling Long-Context Visual Language Models for Long Videos.

[BibT_eX]

[DOI]

CoRR, 2024

VILA<sup>2</sup>: VILA Augmented VILA.

[BibT_eX]

[DOI]

CoRR, 2024

A deeper look at depth pruning of LLMs.

[BibT_eX]

[DOI]

Shoaib Ahmed Siddiqui

CoRR, 2024

Step Out and Seek Around: On Warm-Start Training with Incremental Data.

[BibT_eX]

[DOI]

CoRR, 2024

X-VILA: Cross-Modality Alignment for Large Language Model.

[BibT_eX]

[DOI]

CoRR, 2024

Multi-Antenna Array for All Space Communications.

[BibT_eX]

[DOI]

Pavlo Molchanov

Proceedings of the IEEE Radio and Wireless Symposium, 2024

Compact Language Models via Pruning and Knowledge Distillation.

[BibT_eX]

[DOI]

Saurav Muralidharan

Sharath Turuvekere Sreenivas

Proceedings of the Advances in Neural Information Processing Systems 37: Annual Conference on Neural Information Processing Systems 2024, 2024

MaskLLM: Learnable Semi-Structured Sparsity for Large Language Models.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 37: Annual Conference on Neural Information Processing Systems 2024, 2024

DoRA: Weight-Decomposed Low-Rank Adaptation.

[BibT_eX]

[DOI]

Proceedings of the Forty-first International Conference on Machine Learning, 2024

Flextron: Many-in-One Flexible Large Language Model.

[BibT_eX]

[DOI]

Proceedings of the Forty-first International Conference on Machine Learning, 2024

FasterViT: Fast Vision Transformers with Hierarchical Attention.

[BibT_eX]

[DOI]

Proceedings of the Twelfth International Conference on Learning Representations, 2024

Adaptive Sharpness-Aware Pruning for Robust Sparse Networks.

[BibT_eX]

[DOI]

Proceedings of the Twelfth International Conference on Learning Representations, 2024

COIN: Control-Inpainting Diffusion Prior for Human and Camera Motion Estimation.

[BibT_eX]

[DOI]

Proceedings of the Computer Vision - ECCV 2024, 2024

LITA: Language Instructed Temporal-Localization Assistant.

[BibT_eX]

[DOI]

De-An Huang

Shijia Liao

Subhashree Radhakrishnan

Proceedings of the Computer Vision - ECCV 2024, 2024

AM-RADIO: Agglomerative Vision Foundation Model Reduce All Domains Into One.

[BibT_eX]

[DOI]

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2024

VILA: On Pre-training for Visual Language Models.

[BibT_eX]

[DOI]

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2024

PACE: Human and Camera Motion Estimation from in-the-wild Videos.

[BibT_eX]

[DOI]

Proceedings of the International Conference on 3D Vision, 2024

2023

Do Gradient Inversion Attacks Make Federated Learning Unsafe?

[BibT_eX]

[DOI]

IEEE Trans. Medical Imaging, 2023

VILA: On Pre-training for Visual Language Models.

[BibT_eX]

[DOI]

CoRR, 2023

AM-RADIO: Agglomerative Model - Reduce All Domains Into One.

[BibT_eX]

[DOI]

CoRR, 2023

Global Context Vision Transformers.

[BibT_eX]

[DOI]

Proceedings of the International Conference on Machine Learning, 2023

RANA: Relightable Articulated Neural Avatars.

[BibT_eX]

[DOI]

Proceedings of the IEEE/CVF International Conference on Computer Vision, 2023

Global Vision Transformer Pruning with Hessian-Aware Saliency.

[BibT_eX]

[DOI]

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023

Recurrence without Recurrence: Stable Video Landmark Detection with Deep Equilibrium Models.

[BibT_eX]

[DOI]

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023

Heterogeneous Continual Learning.

[BibT_eX]

[DOI]

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023

2022

Towards annotation-efficient segmentation via image-to-image translation.

[BibT_eX]

[DOI]

Medical Image Anal., 2022

Global Context Vision Transformers.

[BibT_eX]

[DOI]

CoRR, 2022

DRaCoN - Differentiable Rasterization Conditioned Neural Radiance Fields for Articulated Avatars.

[BibT_eX]

[DOI]

CoRR, 2022

Structural Pruning via Latency-Saliency Knapsack.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

LANA: Latency Aware Network Acceleration.

[BibT_eX]

[DOI]

Proceedings of the Computer Vision - ECCV 2022, 2022

A-ViT: Adaptive Tokens for Efficient Vision Transformer.

[BibT_eX]

[DOI]

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022

When to Prune? A Policy towards Early Structural Pruning.

[BibT_eX]

[DOI]

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022

GradViT: Gradient Inversion of Vision Transformers.

[BibT_eX]

[DOI]

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022

GLAMR: Global Occlusion-Aware Human Mesh Recovery with Dynamic Cameras.

[BibT_eX]

[DOI]

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022

Privacy Vulnerability of Split Computing to Data-Free Model Inversion Attacks.

[BibT_eX]

[DOI]

Proceedings of the 33rd British Machine Vision Conference 2022, 2022

2021

AdaViT: Adaptive Tokens for Efficient Vision Transformer.

[BibT_eX]

[DOI]

CoRR, 2021

HALP: Hardware-Aware Latency Pruning.

[BibT_eX]

[DOI]

CoRR, 2021

NViT: Vision Transformer Compression and Parameter Redistribution.

[BibT_eX]

[DOI]

CoRR, 2021

HANT: Hardware-Aware Network Transformation.

[BibT_eX]

[DOI]

CoRR, 2021

Deep Neural Networks are Surprisingly Reversible: A Baseline for Zero-Shot Inversion.

[BibT_eX]

[DOI]

CoRR, 2021

Adversarial Motion Modelling helps Semi-supervised Hand Pose Estimation.

[BibT_eX]

[DOI]

CoRR, 2021

Data-free Knowledge Distillation for Object Detection.

[BibT_eX]

[DOI]

Proceedings of the IEEE Winter Conference on Applications of Computer Vision, 2021

Optimizing Selective Protection for CNN Resilience.

[BibT_eX]

[DOI]

Abdulrahman Mahmoud

Siva Kumar Sastry Hari

Christopher W. Fletcher

Proceedings of the 32nd IEEE International Symposium on Software Reliability Engineering, 2021

See Through Gradients: Image Batch Recovery via GradInversion.

[BibT_eX]

[DOI]

Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2021

Optimal Quantization Using Scaled Codebook.

[BibT_eX]

[DOI]

Miguel Á. Carreira-Perpiñán

José M. Álvarez

Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2021

DexYCB: A Benchmark for Capturing Hand Grasping of Objects.

[BibT_eX]

[DOI]

Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2021

KAMA: 3D Keypoint Aware Body Mesh Articulation.

[BibT_eX]

[DOI]

Proceedings of the International Conference on 3D Vision, 2021

2020

HarDNN: Feature Map Vulnerability Evaluation in CNNs.

[BibT_eX]

[DOI]

Abdulrahman Mahmoud

Siva Kumar Sastry Hari

Christopher W. Fletcher

CoRR, 2020

Weakly Supervised 3D Hand Pose Estimation via Biomechanical Constraints.

[BibT_eX]

[DOI]

Proceedings of the Computer Vision - ECCV 2020, 2020

Measuring Generalisation to Unseen Viewpoints, Articulations, Shapes and Objects for 3D Hand Pose Estimation Under Hand-Object Interaction.

[BibT_eX]

[DOI]

Proceedings of the Computer Vision - ECCV 2020, 2020

Dreaming to Distill: Data-Free Knowledge Transfer via DeepInversion.

[BibT_eX]

[DOI]

Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020

Weakly-Supervised 3D Human Pose Learning via Multi-View Images in the Wild.

[BibT_eX]

[DOI]

Umar Iqbal

Pavlo Molchanov

Jan Kautz

Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020

2019

Boosting segmentation with weak supervision from image-to-image translation.

[BibT_eX]

[DOI]

CoRR, 2019

Few-Shot Adaptive Gaze Estimation.

[BibT_eX]

[DOI]

Proceedings of the 2019 IEEE/CVF International Conference on Computer Vision, 2019

Importance Estimation for Neural Network Pruning.

[BibT_eX]

[DOI]

Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2019

SCOPS: Self-Supervised Co-Part Segmentation.

[BibT_eX]

[DOI]

Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2019

2018

IamNN: Iterative and Adaptive Mobile Neural Network for efficient image classification.

[BibT_eX]

[DOI]

Proceedings of the 6th International Conference on Learning Representations, 2018

Hand Pose Estimation via Latent 2.5D Heatmap Regression.

[BibT_eX]

[DOI]

Proceedings of the Computer Vision - ECCV 2018, 2018

Depth-Based 3D Hand Pose Estimation: From Current Achievements to Future Goals.

[BibT_eX]

[DOI]

Proceedings of the 2018 IEEE Conference on Computer Vision and Pattern Recognition, 2018

Making Convolutional Networks Recurrent for Visual Sequence Learning.

[BibT_eX]

[DOI]

Xiaodong Yang

Pavlo Molchanov

Jan Kautz

Proceedings of the 2018 IEEE Conference on Computer Vision and Pattern Recognition, 2018

Improving Landmark Localization With Semi-Supervised Learning.

[BibT_eX]

[DOI]

Proceedings of the 2018 IEEE Conference on Computer Vision and Pattern Recognition, 2018

Budget-Aware Activity Detection with A Recurrent Policy Network.

[BibT_eX]

[DOI]

Proceedings of the British Machine Vision Conference 2018, 2018

2017

3D Hand Pose Estimation: From Current Achievements to Future Goals.

[BibT_eX]

[DOI]

CoRR, 2017

Pruning Convolutional Neural Networks for Resource Efficient Inference.

[BibT_eX]

[DOI]

Proceedings of the 5th International Conference on Learning Representations, 2017

A Lightweight Approach for On-the-Fly Reflectance Estimation.

[BibT_eX]

[DOI]

Proceedings of the IEEE International Conference on Computer Vision, 2017

2016

Pruning Convolutional Neural Networks for Resource Efficient Transfer Learning.

[BibT_eX]

[DOI]

CoRR, 2016

Multilayer and Multimodal Fusion of Deep Neural Networks for Video Classification.

[BibT_eX]

[DOI]

Xiaodong Yang

Pavlo Molchanov

Jan Kautz

Proceedings of the 2016 ACM Conference on Multimedia Conference, 2016

Towards selecting robust hand gestures for automotive interfaces.

[BibT_eX]

[DOI]

Proceedings of the 2016 IEEE Intelligent Vehicles Symposium, 2016

Online Detection and Classification of Dynamic Hand Gestures with Recurrent 3D Convolutional Neural Networks.

[BibT_eX]

[DOI]

Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition, 2016

2015

Multi-sensor system for driver's hand-gesture recognition.

[BibT_eX]

[DOI]

Proceedings of the 11th IEEE International Conference and Workshops on Automatic Face and Gesture Recognition, 2015

Hand gesture recognition with 3D convolutional neural networks.

[BibT_eX]

[DOI]

Proceedings of the 2015 IEEE Conference on Computer Vision and Pattern Recognition Workshops, 2015

2014

Radar target classification by micro-Doppler contributions.

[BibT_eX]

[DOI]

Pavlo O. Molchanov

PhD thesis, 2014

Classification of aircraft using micro-Doppler bicoherence-based features.

[BibT_eX]

[DOI]

María-Pilar Jarabo-Amores

IEEE Trans. Aerosp. Electron. Syst., 2014

2013

The Use of Automotive Radars in Video-Based Overtaking Assistance Applications.

[BibT_eX]

[DOI]

IEEE Trans. Intell. Transp. Syst., 2013

Classification of ground moving targets using bicepstrum-based features extracted from Micro-Doppler radar signatures.

[BibT_eX]

[DOI]

EURASIP J. Adv. Signal Process., 2013

On Micro-Doppler Period Estimation.

[BibT_eX]

[DOI]

Proceedings of the 19th International Conference on Control Systems and Computer Science, 2013

Pavlo Molchanov

Timeline

Legend:

Links

Online presence:

On csauthors.net:

Bibliography

Loading...