---
markdown_generated_at: "2026-10-14"
title: "AI Research Papers"
url: "https://www.qualcomm.com/research/artificial-intelligence/papers"
---

# AI Research Papers

Novel papers are one of the ways Qualcomm Technologies contributes impactful research to the larger community of AI research. Below are papers that Qualcomm AI Research has written or co-authored.

229 Papers

- **Generative AI** — [PyramidalWan: On Making Pretrained Video Model Pyramidal for Efficient Inference](https://arxiv.org/abs/2601.04792) — Denis Korzhenkov, Adil Karjauv, et al. | CVPR, 2026 — [https://qualcomm-ai-research.github.io/PyramidalWan/](https://qualcomm-ai-research.github.io/PyramidalWan/)
- **Speech, Audio, and Language Processing** — [FC-TTS: Style and Timbre Control in Zero-Shot Text-to-Speech with Disentangled Speech Representations](https://arxiv.org/abs/2605.24618) — Yoonhyung Lee, Hyunsin Park, et al. | ACL, 2026
- **Generative AI** — [MoAlign: Motion-Centric Representation Alignment for Video Diffusion Models](https://arxiv.org/abs/2510.19022) — Aritra Bhowmik, Denis Korzhenkov, et al. | ICLR, 2026
- **Generative AI** — [Multi-Scale Local Speculative Decoding for Image Generation](https://arxiv.org/abs/2601.05149) — Elia Peruzzo, Guillaume Sautière, et al. | CVPR, 2026 — [https://qualcomm-ai-research.github.io/mulo-sd-webpage/](https://qualcomm-ai-research.github.io/mulo-sd-webpage/)
- **Generative AI** — [ReHyAt: Recurrent Hybrid Attention for Video Diffusion Transformers](https://arxiv.org/abs/2601.04342) — Mohsen Ghafoorian, Amirhossein Habibian | CVPR, 2026 — [https://qualcomm-ai-research.github.io/rehyat/](https://qualcomm-ai-research.github.io/rehyat/)
- **Computer Vision** — [DEVA: Fine-tuning Multimodal Large Language Models for Visual Perception Tasks](https://openaccess.thecvf.com/content/CVPR2026/html/Das_DEVA_Fine-tuning_Multimodal_Large_Language_Models_for_Visual_Perception_Tasks_CVPR_2026_paper.html) — Debasmit Das, Munawar Hayat, et al. | CVPR, 2026
- **Computer Vision** — [BluRef: Unsupervised Image Deblurring with Dense-Matching References](https://arxiv.org/abs/2603.14176) — Bang-Dang Pham, Anh Tran, et al. | CVPR, 2026 — [https://qualcomm-ai-research.github.io/BluRef/](https://qualcomm-ai-research.github.io/BluRef/)
- **Generative AI** — [Feedback Adaptation for Retrieval-Augmented Generation](https://arxiv.org/abs/2604.06647) — Jihwan Bang, Seunghan Yang, et al. | ACL, 2026
- **Model and Power Efficiency** — [STaMP: Sequence Transformation and Mixed Precision for Low-Precision Activation Quantization](https://arxiv.org/abs/2510.26771) — Marco Federici, Riccardo Del Chiaro, et al. | ICLR, 2026
- **Personalization and On-Device Learning** — [Memory-Efficient Fine-Tuning Diffusion Transformer via Dynamic Patch Sampling and Block Skipping](https://arxiv.org/abs/2603.20755) — Sunghyun Park, Jeongho Kim, et al. | CVPR, 2026
- **Computer Vision** — [SwiftTailor: Efficient 3D Garment Generation with Geometry Image Representation](https://arxiv.org/abs/2603.19053) — Phuc Pham, Uy Dieu Tran, et al. | CVPR, 2026
- **Generative AI** — [PixelRush: Ultra-Fast, Training-Free High-Resolution Image Generation via One-step Diffusion](https://arxiv.org/html/2602.12769) — Phuc Lai, Phong Nguyen, et al. | CVPR, 2026
- **Generative AI** — [Attention Surgery: An Efficient Recipe to Linearize Your Video Diffusion Transformer](https://arxiv.org/abs/2509.24899) — Mohsen Ghafoorian, Denis Korzhenkov, et al. | CVPR, 2026 — [https://qualcomm-ai-research.github.io/attention-surgery/](https://qualcomm-ai-research.github.io/attention-surgery/)
- **Generative AI** — [Fast SceneScript: Fast and Accurate Language-Based 3D Scene Understanding via Multi-Token Prediction](https://arxiv.org/abs/2512.05597) — Ruihong Yin, Xuepeng Shi, et al. | CVPR, 2026
- **Personalization and On-Device Learning** — [Resolving the Identity Crisis in Text-to-Image Generation](https://arxiv.org/pdf/2510.01399) — Shubhankar Borse, Farzad Farhadzadeh, et al. | CVPR, 2026
- **Optimization and Reinforcement Learning** — [Android Coach: Improve Online Agentic Training Efficiency with Single State Multiple Actions](https://arxiv.org/abs/2604.07277) — Guo Gan, Yuxuan Ding, et al. | ACL, 2026
- **Generative AI** — [Revisit Visual Prompt Tuning: The Expressiveness of Prompt Experts](https://arxiv.org/abs/2501.18936) — Minh Le, Anh Nguyen, et al. | ICLR, 2026
- **Generative AI** — [InverFill: One-Step Inversion for Enhanced Few-Step Diffusion Inpainting](https://arxiv.org/abs/2603.23463) — Duc Vu, Kien Nguyen, et al. | CVPR, 2026
- **Generative AI** — [Concept-Aware LoRA for Domain-Aligned Segmentation Dataset Generation](https://arxiv.org/abs/2503.22172) — Minho Park, Sunghyun Park, et al. | CVPR, 2026
- **Generative AI** — [Ar2Can: An Architect and an Artist Leveraging a Canvas for Multi-Human Generation](https://arxiv.org/pdf/2511.22690) — Shubhankar Borse, Phuc Pham, et al. | CVPR, 2026
- **Generative AI** — [Neodragon Neodragon Badge: Mobile Video Generation using Diffusion Transformer](https://arxiv.org/abs/2511.06055) — Animesh Karnewar, Denis Korzhenkov, et al. | ICLR, 2026 — [https://qualcomm-ai-research.github.io/neodragon/](https://qualcomm-ai-research.github.io/neodragon/)
- **Generative AI** — [Anti-I2V: Safeguarding your photos from malicious image-to-video generation](https://arxiv.org/abs/2603.24570) — Duc Vu, Anh Nguyen, et al. | CVPR, 2026
- **Generative AI** — [Dynamic Tool Dependency Retrieval for Efficient Function Calling](https://arxiv.org/pdf/2512.17052) — Bhrij Patel, Davide Belli, et al. | ACL, 2026
- **Generative AI** — [QuoKA: Query-Oriented KV Selection for Efficient LLM Prefill](https://arxiv.org/abs/2602.08722v1) — Junyoung Park, Mingu Lee, et al. | ICLR, 2026
- **Neural Reasoning and Embodied AI** — [Hybrid Training for Vision-Language-Action Models](https://arxiv.org/abs/2510.00600) — Pietro Mazzaglia, Cansu Sancaktar, et al. | ICLR, 2026
- **Generative AI** — [Can Vision-Language Models Answer Face to Face Questions in the Real-World?](https://arxiv.org/abs/2503.19356) — Reza Pourreza, Rishit Dagli, et al. | ICLR, 2026
- **Generative AI** — [Enhancing Hallucination Detection through Noise Injection](https://arxiv.org/pdf/2502.03799) — Litian Liu, Reza Pourreza, et al. | ICLR, 2026
- **Neural Reasoning and Embodied AI** — [KaVa: Latent Reasoning via Compressed KV-Cache Distillation](https://arxiv.org/abs/2510.02312) — Anna Kuzina, Maciej Pioro, et al. | ICLR, 2026
- **Generative AI** — [FLoC: Facility Location-Based Efficient Visual Token Compression for Long Video Understanding](https://arxiv.org/abs/2511.00141) — Janghoon Cho, Jungsoo Lee, et al. | ICLR, 2026
- **Machine Learning Fundamentals** — [Non-exchangeable Conformal Prediction with Optimal Transport: Tackling Distribution Shifts with Unlabeled Data](https://arxiv.org/abs/2507.10425) — Alvaro H.C. Correia, Christos Louizos | NeurIPS, 2025
- **Generative AI** — [Masks Can Be Distracting: On Context Comprehension in Diffusion Language Models](https://arxiv.org/abs/2511.21338) — Julianna Piskorz, Cristina Pinneri, et al. | Workshop at NeurIPS, 2025
- **Generative AI** — [Can Multi-Modal LLMs Provide Live Step-by-Step Task Guidance?](https://arxiv.org/abs/2511.21998) — Apratim Bhattacharyya, Bicheng Xu, et al. | NeurIPS, 2025
- **Neural Reasoning and Embodied AI** — [Analyzing and Improving Chain-of-Thought Monitorability Through Information Theory](https://openreview.net/pdf?id=3YJ3JAI8Sz) — Usman Anwar, Tim Bakker, et al. | NeurIPS Workshop, 2025
- **Model and Power Efficiency** — [KeyDiff: Key Similarity-Based KV Cache Eviction for Long-Context LLM Inference in Resource-Constrained Environments](https://arxiv.org/abs/2504.15364) — Junyoung Park, Dalton Jones, et al. | NeurIPS, 2025
- **Generative AI** — [CIFLEX: Contextual Instruction Flow for Sub-task Execution in Multi-Turn Interactions with a Single On-Device LLM](https://arxiv.org/abs/2510.01239) — Juntae Lee, Jihwan Bang, et al. | EMNLP, 2025
- **Generative AI** — [Attention Guided Alignment in Efficient Vision-Language Models](https://www.arxiv.org/abs/2511.17793) — Shweta Mahajan, Hoang Le, et al. | NeurIPS Workshop, 2025
- **Wireless and RF** — [ReQuestNet: A Foundational Learning model for Channel Estimation](https://arxiv.org/abs/2508.08790) — Kumar Pratik, Pouriya Sadeghi, et al. | IEEE Globecom, 2025
- **Neural Reasoning and Embodied AI** — [Think Straight, Stop Smart: Structured Reasoning for Efficient Multi-Hop RAG](https://arxiv.org/abs/2510.19171) — Jihwan Bang, Juntae Lee, et al. | NeurIPS Workshop, 2025
- **Generative AI** — [Learning Contextual Retrieval for Robust Conversational Search](https://arxiv.org/abs/2509.19700) — Seunghan Yang, Juntae Lee, et al. | EMNLP, 2025
- **Machine Learning Fundamentals** — [Generalized Contrastive Learning for Universal Multimodal Retrieval](https://arxiv.org/abs/2509.25638) — Jungsoo Lee, Janghoon Cho, et al. | NeurIPS, 2025
- **Neural Reasoning and Embodied AI** — [Embodied Representation Alignment with Mirror Neurons](https://arxiv.org/abs/2509.21136) — Wentao Zhu, Zhining Zhang, et al. | ICCV, 2025
- **Generative AI** — [Supercharged One-step Text-to-Image Diffusion Models with Negative Prompts](https://arxiv.org/abs/2412.02687) — Viet Nguyen, Anh Nguyen, et al. | ICCV, 2025
- **Computer Vision** — [ODG: Occupancy Prediction Using Dual Gaussians](https://www.arxiv.org/abs/2506.09417) — Yunxiao Shi, Yinhao Zhu, et al. | NeurIPS, 2025
- **Generative AI** — [Improved Training Technique for Shortcut Models](https://arxiv.org/abs/2510.21250) — Anh Nguyen, Viet Nguyen, et al. | NeurIPS, 2025
- **Machine Learning Fundamentals** — [Revisiting Bi-Linear State Transitions in Recurrent Neural Networks](https://arxiv.org/abs/2505.21749) — M.Reza Ebrahimi, Roland Memisevic | NeurIPS, 2025
- **Generative AI** — [MultiHuman-Testbench: Benchmarking Image Generation for Multiple Humans](https://arxiv.org/abs/2506.20879) — Shubhankar Borse, Seokeon Choi, et al. | NeurIPS, 2025 — [https://github.com/Qualcomm-AI-research/MultiHuman-Testbench](https://github.com/Qualcomm-AI-research/MultiHuman-Testbench)
- [OmniDraft: A Cross-vocabulary, Online Adaptive Drafter for On-device Speculative Decoding](https://arxiv.org/abs/2507.02659) — Ramchalam Kinattinkara Ramakrishnan, Zhaocong Yuan, et al. | NeurIPS, 2025
- **Computer Vision** — [VaLID: Variable-Length Input Diffusion for Novel View Synthesis](https://arxiv.org/abs/2312.08892) — Shijie Li, Farhad G. Zanjani, et al. | WACV, 2025
- **Machine Learning Fundamentals** — [Approximating Full Conformal Prediction for Neural Network Regression with Gauss-Newton Influence](https://openreview.net/forum?id=vcX0k4rGTt) — Dharmesh Tailor, Alvaro Correia, et al. | ICLR, 2025 — [https://github.com/Qualcomm-AI-research/newton-influence-conformal](https://github.com/Qualcomm-AI-research/newton-influence-conformal)
- **Personalization and On-Device Learning** — [Zero-Shot Adaptation of Parameter-Efficient Fine-Tuning in Diffusion Models](https://arxiv.org/abs/2506.04244) — Farzad Farhadzadeh, Debasmit Das, et al. | ICML, 2025
- **Wireless and RF** — [Differentiable and Learnable Wireless Simulation with Geometric Transformers](https://arxiv.org/abs/2406.14995) — Thomas Hehn, Markus Peschl, et al. | ICLR, 2025 — [https://github.com/Qualcomm-AI-research/Wi-GATr](https://github.com/Qualcomm-AI-research/Wi-GATr)
- **Generative AI** — [Multi-Draft Speculative Sampling: Canonical Decomposition and Theoretical Limits](https://arxiv.org/abs/2410.18234) — Ashish Khisti, Reza Ebrahimi, et al. | ICLR, 2025
- **Machine Learning Fundamentals** — [PADRe: A Unifying Polynomial Attention Drop-in Replacement for Efficient Vision Transformer](https://arxiv.org/abs/2407.11306) — Pierre-David Letourneau, Manish Kumar Singh, et al. | ICLR, 2025
- **Personalization and On-Device Learning** — [LoRA-X: Bridging Foundation Models with Training-Free Cross-Model Adaptation](https://arxiv.org/abs/2501.16559) — Farzad Farhadzadeh, Debasmit Das, et al. | ICLR, 2025
- **Generative AI** — [How Efficient is LLM-Generated Code? A Rigorous & High-Standard Benchmark](https://arxiv.org/abs/2406.06647) — Ruizhong Qiu, Weiliang Will Zeng, et al. | ICLR, 2025
- **Computer Vision** — [Any3DIS: Class-Agnostic 3D Instance Segmentation by 2D Mask Tracking](https://arxiv.org/abs/2411.16183) — Phuc Nguyen, Minh Luu, et al. | CVPR, 2025
- **Machine Learning Fundamentals** — [Tri-WE: Tripartite Weight-Space Ensemble for Few-Shot Class-Incremental Learning](https://openaccess.thecvf.com/content/CVPR2025/papers/Lee_Tripartite_Weight-Space_Ensemble_for_Few-Shot_Class-Incremental_Learning_CVPR_2025_paper.pdf) — Juntae Lee, Munawar Hayat, et al. | CVPR, 2025
- **Generative AI** — [SwiftEdit: Lightning Fast Text-Guided Image Editing via One-Step Diffusion](https://arxiv.org/abs/2412.04301) — Trong-Tung Nguyen, Quang Nguyen, et al. | CVPR, 2025
- **Computer Vision** — [SharpDepth: Sharpening Metric Depth Predictions Using Diffusion Distillation](https://arxiv.org/abs/2411.18229) — Duc-Hai Pham, Tung Do, et al. | CVPR, 2025
- **Computer Vision** — [Sort-free Gaussian Splatting via Weighted Sum Rendering](https://arxiv.org/abs/2410.18931) — Qiqi Hou, Randall Rauwendaal, et al. | ICLR, 2025
- **Machine Learning Fundamentals** — [Low-Rank Adaptation in Multilinear Operator Networks for Security-Preserving Incremental Learning](https://openaccess.thecvf.com/content/CVPR2025/papers/Ta_Low-Rank_Adaptation_in_Multilinear_Operator_Networks_for_Security-Preserving_Incremental_Learning_CVPR_2025_paper.pdf) — Huu Binh Ta, Duc Nguyen, et al. | CVPR, 2025
- **Personalization and On-Device Learning** — [CustomKD: Customizing Large Vision Foundation for Edge Model Improvement via Knowledge Distillation](https://arxiv.org/abs/2503.18244) — Jungsoo Lee, Debasmit Das, et al. | CVPR, 2025
- **Computer Vision** — [Distilling Multi-modal Large Language Models for Autonomous Driving](https://arxiv.org/abs/2501.09757) — Deepti Hegde, Rajeev Yasarla, et al. | CVPR, 2025
- **Personalization and On-Device Learning** — [HyperNet Fields: Efficiently Training Hypernetworks without Ground Truth by Learning Weight Trajectories](https://arxiv.org/abs/2412.17040) — Eric Hedlin, Munawar Hayat, et al. | CVPR, 2025
- **Generative AI** — [Planar Gaussian Splatting](https://arxiv.org/abs/2412.01931) — Farhad G. Zanjani, Hong Cai, et al. | WACV, 2025
- **Generative AI** — [HexaGen3D: Stable Diffusion is One Step Away from Fast and Diverse Text-to-3D Generation](https://arxiv.org/abs/2401.07727) — Antoine Mercier, Ramin Nakhli, et al. | WACV, 2025
- **Power and Model Efficiency** — [Efficient LLM Inference using Dynamic Input Pruning and Cache-Aware Masking](https://arxiv.org/abs/2412.01380) — Davide Belli, Marco Federici Mart van Baalen, et al. | MLSys, 2025 — [https://github.com/Qualcomm-AI-research/dynamic-sparsity](https://github.com/Qualcomm-AI-research/dynamic-sparsity)
- **Neural Reasoning and Embodied AI** — [Local Look-Ahead Guidance via Verifier-in-the-Loop for Automated Theorem Proving](https://arxiv.org/abs/2503.09730) — Arash Behboodi, GabrieleCesa, et al. | ACL, 2025
- **Generative AI** — [Look, Remember and Reason: Grounded Reasoning in Videos with Language Models](https://openreview.net/forum?id=jhPvuc7kxB) — Apratim Bhattacharyya, Roland Memisevic, et al. | ICLR, 2024
- **Neural Reasoning and Embodied AI** — [Live Fitness Coaching as a Testbed for Situated Interaction](https://arxiv.org/abs/2407.08101) — Sunny Panchal, Apratim Bhattacharyya, et al. | NeurIPS, 2024 — [https://github.com/Qualcomm-AI-research/FitCoach](https://github.com/Qualcomm-AI-research/FitCoach)
- **Generative AI** — [Hollowed Net for On-Device Personalization of Text-to-Image Diffusion Models](https://arxiv.org/abs/2411.01179) — NeurIPS, 2024
- **Neural Reasoning and Embodied AI** — [ClevrSkills: Compositional Language And Visual Understanding in Robotics](https://arxiv.org/abs/2411.09052v1) — Sanjay Haresh · Daniel Dijkman · Apratim Bhattacharyya · Roland Memisevic | NeurIPS, 2024
- **Data Compression** — [Low-Latency Neural Stereo Streaming](https://arxiv.org/abs/2403.17879) — Qiqi Hou, Hoang Le, et al. | CVPR, 2024
- **Computer Vision** — [Neural graphics texture compression supporting random access](https://arxiv.org/abs/2407.00021) — Farzad Farhadzadeh, Qiqi Hou, et al. | ECCV, 2024
- **Computer Vision** — [DeCoTR: Enhancing Depth Completion with 2D and 3D Attentions](https://arxiv.org/abs/2403.12202v1) — Yunxiao Shi, Manish Kumar Singh, et al. | CVPR, 2024
- **Neural Reasoning and Embodied AI** — [Live Fitness Coaching as a Testbed for Situated Interaction](https://arxiv.org/abs/2407.08101) — Sunny Panchal, Apratim Bhattacharyya, et al. | NeurIPS, 2024
- **Generative AI** — [Sparse High Rank Adapters](https://arxiv.org/abs/2406.13175) — Kartikeya Bhardwaj, Nilesh Prasad Pandey, et al. | NeurIPS, 2024
- **Machine Learning Fundamentals** — [An Information Theoretic Perspective on Conformal Prediction](https://arxiv.org/abs/2405.02140) — Alvaro H.C. Correia, Fabio Valerio Massoli, et al. | NeurIPS, 2024
- **Computer Vision** — [Skip-Attention: Improving Vision Transformers by Paying Less Attention](https://openreview.net/pdf?id=vI95kcLAoU) — Shashanka Venkataramanan, Amir Ghodrati, et al. | ICLR, 2024
- **Machine Learning Fundamentals** — [CodeIt: Self-Improving Language Models with Prioritized Hindsight Replay](https://arxiv.org/abs/2402.04858) — Natasha Eve Butt, Auke Wiggers, et al. | ICML, 2024
- **Machine Learning Fundamentals** — [Probabilistic Approach to Learning the Degree of Equivariance in Steerable CNNs](https://arxiv.org/abs/2406.03946) — Lars Veefkind, Gabriele Cesa | ICML, 2024
- **Machine Learning Fundamentals** — [Textual Training for the Hassle-Free Removal of Unwanted Visual Data: Case Studies on OOD and Hateful Image Detection](https://arxiv.org/abs/2409.19840) — Saehyung Lee, Jisoo Mok, et al. | NeurIPS, 2024
- **Personalization and On-Device Learning** — [Stepping Forward on the Last Mile](https://arxiv.org/abs/2411.04036v1) — Chen Feng, Shaojie Zhuo, et al. | NeurIPS, 2024
- **Machine Learning Fundamentals** — [Mutual Information Perspective on Federated Contrastive Learning](https://arxiv.org/abs/2405.02081) — Christos Louizos, Matthias Reisser, et al. | ICLR, 2024
- **Generative AI** — [Read-ME: Refactorizing LLMs as Router-Decoupled Mixture of Experts with System Co-Design](https://arxiv.org/abs/2410.19123) — Ruisi Cai, Yeonju Ro, et al. | NeurIPS, 2024
- **Computer Vision** — [OCAI: Improving Optical Flow Estimation by Occlusion and Consistency Aware Interpolation](https://arxiv.org/abs/2403.18092) — Jisoo Jeong, Hong(Herbert) Cai, et al. | CVPR, 2024
- **Machine Learning Fundamentals** — [On Sampling Strategies for Spectral Model Sharding](https://arxiv.org/abs/2410.24106v1) — Denis Korzhenkov, Christos Louizos | NeurIPS, 2024
- **Computer Vision** — [Clockwork Diffusion: Efficient Generation With Model-Step Distillation](https://arxiv.org/abs/2312.08128v2) — Amirhossein Habibian, Amir Ghodrati, et al. | CVPR, 2024
- **Personalization and On-Device Learning** — [FouRA: Fourier Low Rank Adaptation](https://arxiv.org/abs/2406.08798) — Shubhankar Borse, Shreya Kadambi, et al. | NeurIPS, 2024
- **Machine Learning Fundamentals** — [Robust Scheduling with GFlowNets](https://arxiv.org/abs/2302.05446) — David W. Zhang, Corrado Rainone, et al. | ICLR, 2023
- **Wireless and RF** — [Neural 5G Indoor Localization with IMU Supervision](https://arxiv.org/abs/2402.09948) — Aleksandr Ermolov, Shreya Kadambi, et al. | Globecom, 2023
- **Personalization and On-Device Learning** — [EcoTTA: Memory-Efficient Continual Test-time Adaptation via Self-distilled Regularization](https://arxiv.org/abs/2303.01904) — Junha Song, Jungsoo Lee, et al. | CVPR, 2023
- **Computer Vision** — [4D Panoptic Segmentation as Invariant and Equivariant Field Prediction](https://arxiv.org/abs/2303.15651) — Minghan Zhu, Shizhong Han, et al. | ICCV, 2023
- **Speech, Audio, and Language Processing** — [Federated Learning Toolkit with Voice-based User Verification Demo](https://www.isca-archive.org/interspeech_2023/mandke23_interspeech.html) — Prathamesh Mandke1, Rachel Oberst1, et al. | Interspeech, 2023
- **Computer Vision** — [DG-Recon: Depth-Guided Neural 3D Scene Reconstruction](https://openaccess.thecvf.com/content/ICCV2023/papers/Ju_DG-Recon_Depth-Guided_Neural_3D_Scene_Reconstruction_ICCV_2023_paper.pdf) — Jihong Ju, Ching Wei Tseng, et al. | ICCV, 2023
- **Computer Vision** — [X-Align: Cross-Modal Cross-View Alignment for Bird’s-Eye-View Segmentation](https://arxiv.org/abs/2210.06778) — Shubhankar Borse, Marvin Klingner, et al. | WACV, 2023
- **Computer Vision** — [X3KD: Knowledge Distillation Across Modalities, Tasks and Stages for Multi-Camera 3D Object Detection](https://arxiv.org/abs/2303.02203) — Marvin Klingner, Shubhankar Borse, et al. | CVPR, 2023
- **Computer Vision** — [DejaVu: Conditional Regenerative Learning to Enhance Dense Prediction](https://arxiv.org/abs/2303.01573) — Shubhankar Borse, Debasmit Das, et al. | CVPR, 2023
- **Speech, Audio, and Language Processing** — [Knowledge Distillation from Non-streaming to Streaming ASR Encoder using Auxiliary Non-streaming Layer](https://www.isca-speech.org/archive/interspeech_2023/shim23_interspeech.html) — Kyuhong Shim, Jinkyu Lee, et al. | Interspeech, 2023
- **Computer Vision** — [PartSLIP: Low-Shot Part Segmentation for 3D Point Clouds via Pretrained Image-Language Models](https://arxiv.org/abs/2212.01558) — Minghua Liu, Yinhao Zhu, et al. | CVPR, 2023
- **Speech, Audio, and Language Processing** — [Improving Small Footprint Few-shot Keyword Spotting with Supervision on Auxiliary Data](https://arxiv.org/abs/2309.00647) — Seunghan Yang, Byeonggeun Kim, et al. | Interspeech, 2023
- **Machine Learning Fundamentals** — [Progressive Random Convolutions for Single Domain Generalization](https://arxiv.org/abs/2304.00424) — Seokeon Choi, Debasmit Das, et al. | CVPR, 2023
- **Computer Vision** — [3D Distillation: Improving Self-Supervised Monocular Depth Estimation on Reflective Surfaces](https://openaccess.thecvf.com/content/ICCV2023/papers/Shi_3D_Distillation_Improving_Self-Supervised_Monocular_Depth_Estimation_on_Reflective_Surfaces_ICCV_2023_paper.pdf) — Xuepeng Shi, Georgi Dikov, et al. | ICCV, 2023
- **Generative AI** — [Deductive Verification of Chain-of-Thought Reasoning](https://arxiv.org/abs/2306.03872) — Zhan Ling, Yunhao Fang, et al. | NeurIPS, 2023
- **Personalization and On-Device Learning** — [Hyperparameter Optimization through Neural Network Partitioning](https://arxiv.org/abs/2304.14766) — Christos Louizos, Matthias Reisser, et al. | ICLR, 2023
- **Machine Learning Fundamentals** — [Composite Slice Transformer: An Efficient Transformer with Composition of Multi-Scale Multi-Range Attentions](https://openreview.net/forum?id=nWTzIsgrYNN) — Mingu Lee, Saurabh Pitre, et al. | ICLR, 2023
- **Machine Learning Fundamentals** — [EDGI: Equivariant Diffusion for Planning with Embodied Agents](https://arxiv.org/abs/2303.12410) — Johann Brehmer, Joey Bose (former QC intern), et al. | NeurIPS, 2023
- **Computer Vision** — [GlueStick: Robust Image Matching by Sticking Points and Lines Together](https://arxiv.org/abs/2304.02008) — Rémi Pautrat, Iago Suárez, et al. | ICCV, 2023
- **Computer Vision** — [MAMo: Leveraging Memory and Attention for Monocular Video Depth Estimation](https://arxiv.org/abs/2307.14336) — Rajeev Yasarla, Hong Cai, et al. | ICCV, 2023
- **Wireless and RF** — [WiNeRT: Towards Neural Ray Tracing for Wireless Channel Modelling and Differentiable Simulations](https://openreview.net/forum?id=tPKKXeW33YU) — Tribhuvanesh Orekondy, Pratik Kumar, et al. | ICLR, 2023
- **Personalization and On-Device Learning** — [TTN: A Domain-Shift Aware Batch Normalization in Test-Time Adaptation](https://arxiv.org/abs/2302.05155) — Hyesu Lim, Byeonggeun Kim, et al. | ICLR, 2023
- **Computer Vision** — [Label Shift Adapter for Test-Time Adaptation under Covariate and Label Shifts](https://arxiv.org/abs/2308.08810) — Sunghyun Park, Seunghan Yang, et al. | ICCV, 2023
- **Machine Learning Fundamentals** — [Neural DAG Scheduling Via One-Shot Priority Sampling](https://openreview.net/forum?id=WL8FlAugqQ) — Wonseok Jeon, Mukul Gagrani, et al. | ICLR, 2023
- **Computer Vision** — [Task-Agnostic Open-Set Prototype for Few-Shot Open-Set Recognition](https://ieeexplore.ieee.org/abstract/document/10222412) — Byeonggeun Kim, Juntae Lee, et al. | ICIP, 2023
- **Wireless and RF** — [GNSS Positioning using Cost Function Regulated Multilateration and Graph Neural Networks](https://arxiv.org/abs/2402.18630) — Amir Jalalirad, Davide Belli, et al. | IONGNSS, 2023
- **Data Compression** — [Boosting neural video codecs by exploiting hierarchical redundancy](https://arxiv.org/abs/2208.04303) — Reza Pourreza, Hoang Le, et al. | WACV, 2023
- **Data Compression** — [A neural video codec with spatial rate-distortion control](https://openaccess.thecvf.com/content/WACV2023/papers/Fathima_A_Neural_Video_Codec_With_Spatial_Rate-Distortion_Control_WACV_2023_paper.pdf) — Noor Fathima; Jens Petersen; Guillaume Sautière; Auke Wiggers; Reza Pourreza | WACV, 2023
- **Computer Vision** — [ResQ: Residual Quantization for Video Perception](https://arxiv.org/abs/2308.09511) — Davide Abati, Haitam Ben Yahia, et al. | ICCV, 2023
- **Power and Model Efficiency** — [Pruning vs Quantization: Which is Better?](https://arxiv.org/abs/2307.02973) — Andrey Kuzmin, Markus Nagel, et al. | NeurIPS, 2023
- **Personalization and On-Device Learning** — [Towards Open-Set Test-Time Adaptation Utilizing the Wisdom of Crowds in Entropy Minimization](https://arxiv.org/abs/2308.06879) — Jungsoo Lee, Debasmit Das, et al. | ICCV, 2023
- **Power and Model Efficiency** — [Quantizable Transformers: Removing Outliers by Helping Attention Heads Do Nothing](https://arxiv.org/abs/2306.12929) — Yelysei Bondarenko, Markus Nagel, et al. | NeurIPS, 2023
- **Computer Vision** — [Efficient Neural Supersampling on a Novel Gaming Dataset](https://arxiv.org/abs/2308.01483#:~:text=Real%2Dtime%20rendering%20for%20video,solution%20to%20address%20this%20challenge.) — Antoine Mercier, Ruan Erasmus, et al. | ICCV, 2023
- **Computer Vision** — [Factorized Inverse Path Tracing for Efficient and Accurate Material-Lighting Estimation](https://arxiv.org/abs/2304.05669) — Liwen Wu, Rui Zhu, et al. | ICCV, 2023 — [https://github.com/lwwu2/fipt](https://github.com/lwwu2/fipt)
- **Wireless and RF** — [Predicting large-scale channel parameters from adaptively sized map data](https://arxiv.org/abs/2310.04570) — Thomas Hehn, Tribhuvanesh Orekondy, et al. | Globecom, 2023
- **Computer Vision** — [Few-Shot Common Action Localization via Cross-Attentional Fusion of Context and Temporal Dynamics](https://openaccess.thecvf.com/content/ICCV2023/papers/Lee_Few-Shot_Common_Action_Localization_via_Cross-Attentional_Fusion_of_Context_and_ICCV_2023_paper.pdf) — Juntae Lee, Mihir Jain, et al. | ICCV, 2023
- **Computer Vision** — [Multi-scale temporal feature fusion for few-shot action recognition](https://ieeexplore.ieee.org/document/10223132) — Jun-Tae Lee, Sungrack Yun | ICIP, 2023
- **Machine Learning Fundamentals** — [Geometric Algebra Transformers](https://arxiv.org/abs/2305.18415) — Johann Brehmer, Sönke Behrends, et al. | NeurIPS, 2023 — [https://www.qualcomm.com/research/artificial-intelligence/ai-research/papers-with-code/paper-13](https://www.qualcomm.com/research/artificial-intelligence/ai-research/papers-with-code/paper-13)
- **Machine Learning Fundamentals** — [Scalarization for Multi-Task and Multi-Domain Learning at Scale](https://arxiv.org/abs/2310.08910) — Amelie Royer, Tijmen Blankevoort, et al. | NeurIPS, 2023
- **Computer Vision** — [DistractFlow: Improving Optical Flow Estimation via Realistic Distractions and Pseudo-Labeling](https://arxiv.org/abs/2303.14078) — Jisoo Jeong, Hong Cai, et al. | CVPR, 2023
- **Machine Learning Fundamentals** — [Batch Bayesian Optimization on Permutations using the Acquisition Weighted Kernel](https://arxiv.org/abs/2102.13382) — Changyong Oh, Roberto Bondesan, et al. | NeurIPS, 2022
- **Computer Vision** — [Perceptual Consistency in Video Segmentation](https://openaccess.thecvf.com/content/WACV2022/papers/Zhang_Perceptual_Consistency_in_Video_Segmentation_WACV_2022_paper.pdf) — Shubhankar Borse, Hong Cai, et al. | WACV, 2022
- **Personalization and On-Device Learning** — [Multi-Head Modularization to Leverage Generalization Capability in Multi-Modal Networks](https://aaai-2022.virtualchair.net/poster_aaai7586) — Jun-Tae Lee, Hyunsin Park, et al. | AAAI, 2022
- **Data Compression** — [GameCodec: Neural Cloud Gaming Video Codec](https://bmvc2022.mpi-inf.mpg.de/0204.pdf) — Hoang Le, Reza Pourreza, et al. | BMVC, 2022
- **Computer Vision** — [Leaky Gated Cross-Attention for Weakly Supervised Multi-Modal Temporal Action Localization](https://openaccess.thecvf.com/content/WACV2022/papers/Lee_Leaky_Gated_Cross-Attention_for_Weakly_Supervised_Multi-Modal_Temporal_Action_Localization_WACV_2022_paper.pdf) — Jun-Tae Lee, Sungrack Yun, et al. | WACV, 2022
- **Machine Learning Fundamentals** — [A PAC-Bayesian Generalization Bound for Equivariant Networks](https://arxiv.org/abs/2210.13150) — Arash Behboodi, Gabriele Cesa, et al. | NeurIPS, 2022
- **Wireless and RF** — [MIMO-GAN: Generative MIMO Channel Modeling](https://arxiv.org/abs/2203.08588) — Tribhuvanesh Orekondy, Arash Behboodi, et al. | ICC, 2022
- **Data Compression** — [Region of interest based neural video compression](https://arxiv.org/abs/2203.01978) — Yura Perugachi-Diaz, Guillaume Sautière, et al. | BMVC, 2022
- **Computer Vision** — [Dynamic Iterative Refinement for Efficient 3D Hand Pose Estimation](https://openaccess.thecvf.com/content/WACV2022/papers/Yang_Dynamic_Iterative_Refinement_for_Efficient_3D_Hand_Pose_Estimation_WACV_2022_paper.pdf) — John Yang, Yash Bhalgat, et al. | WACV, 2022
- **Computer Vision** — [SALISA: Saliency-Based Input Sampling for Efficient Video Object Detection](https://link.springer.com/chapter/10.1007/978-3-031-20080-9_18) — Babak Ehteshami Bejnordi, Amirhossein Habibian, et al. | ECCV, 2022
- **Machine Learning Fundamentals** — [On the symmetries of the synchronization problem in Cryo-EM: Multi-Frequency Vector Diffusion Maps on the Projective Plane](https://openreview.net/forum?id=owDcdLGgEm) — Gabriele Cesa, Arash Behboodi, et al. | NeurIPS, 2022
- **Wireless and RF** — [Neural RF SLAM for unsupervised positioning and mapping with channel state information](https://arxiv.org/abs/2203.08264) — Shreya Kadambi, Arash Behboodi, et al. | ICC, 2022
- **Machine Learning Fundamentals** — [CITRIS: Causal Identifiability from Temporal Intervened Sequences](https://arxiv.org/abs/2202.03169) — Taco Cohen | ICML, 2022
- **Computer Vision** — [Panoptic, Instance and Semantic Relations: A Relational Context Encoder to Enhance Panoptic Segmentation](https://arxiv.org/abs/2204.05370) — Shubhankar Borse, Hyojin Park, et al. | CVPR, 2022
- **Machine Learning Fundamentals** — [Weakly supervised causal representation learning](https://arxiv.org/abs/2203.16437) — Johann Brehmer, Pim de Haan, et al. | NeurIPS, 2022 — [https://www.qualcomm.com/research/artificial-intelligence/ai-research/papers-with-code/paper-13](https://www.qualcomm.com/research/artificial-intelligence/ai-research/papers-with-code/paper-13)
- **Personalization and On-Device Learning** — [ConFeSS: A Framework for Single Source Cross-Domain Few-Shot Learning](https://openreview.net/forum?id=zRJu6mU2BaE) — Debasmit Das, Sungrack Yun, et al. | ICLR, 2022
- **Machine Learning Fundamentals** — [Message Passing Neural PDE Solvers](https://openreview.net/forum?id=vSix3HPYKSU) — Johannes Brandstetter, Daniel E. Worrall, et al. | ICLR, 2022
- **Computer Vision** — [Imposing Consistency for Optical Flow Estimation](https://arxiv.org/abs/2204.07262) — Jisoo Jeong, Jamie Menjay Lin, et al. | CVPR, 2022
- **Power and Model Efficiency** — [Overcoming Oscillations in Quantization-Aware Training](https://arxiv.org/abs/2203.11086) — Markus Nagel, Marios Fournarakis, et al. | ICML, 2022
- **Machine Learning Fundamentals** — [A Program to Build E(N)-Equivariant Steerable CNNs](https://openreview.net/forum?id=WE4qe9xlnQw) — Gabriele Cesa, Leon Lang, et al. | ICLR, 2022
- **Wireless and RF** — [Learning Perturbations for Soft-Output Linear MIMO Demappers](https://arxiv.org/abs/2209.00529) — Daniel E. Worrall, Markus Peschl, et al. | Globecom, 2022
- **Data Compression** — [Optimized learned entropy coding parameters for practical neural-based image and video compression](http://arxiv.org/abs/2301.08752) — Amir Said, Reza Pourreza, et al. | PCS, 2022
- **Computer Vision** — [IRISformer: Dense Vision Transformers for Single-Image Inverse Rendering in Indoor Scenes](https://openreview.net/pdf?id=UQEgwWpAlFY) — Janarbek Matai, Fatih Porikli | CVPR, 2022
- **Power and Model Efficiency** — [FP8 Quantization: The Power of the Exponent](https://arxiv.org/abs/2208.09225) — Andrey Kuzmin, Mart Van Baalen, et al. | NeurIPS, 2022 — [https://www.qualcomm.com/research/artificial-intelligence/ai-research/papers-with-code/paper-11](https://www.qualcomm.com/research/artificial-intelligence/ai-research/papers-with-code/paper-11)
- **Computer Vision** — [Delta Distillation for Efficient Video Processing](https://link.springer.com/chapter/10.1007/978-3-031-19833-5_13) — Amirhossein Habibian, Haitam Ben Yahia, et al. | ECCV, 2022 — [https://github.com/Qualcomm-AI-research/delta-distillation](https://github.com/Qualcomm-AI-research/delta-distillation)
- **Wireless and RF** — [Beyond Codebook-Based Analog Beamforming at mmWave: Compressed Sensing and Machine Learning Methods](https://arxiv.org/abs/2211.02102) — Hamed Pezeshki, Fabio Valerio Massoli, et al. | Globecom, 2022
- **Data Compression** — [Transformer-based Transform Coding](https://openreview.net/forum?id=IDwN6xjHnK8) — Yinhao Zhu, Yang Yang, et al. | ICLR, 2022
- **Computer Vision** — [AuxAdapt: Stable and Efficient Test-Time Adaptation for Temporally Consistent Video Semantic Segmentation](https://openaccess.thecvf.com/content/WACV2022/papers/Zhang_AuxAdapt_Stable_and_Efficient_Test-Time_Adaptation_for_Temporally_Consistent_Video_WACV_2022_paper.pdf) — Shubhankar Borse, Hong Cai, et al. | WACV, 2022
- **Machine Learning Fundamentals** — [Revisiting single-gated Mixtures of Experts](https://arxiv.org/abs/2304.05497) — Amelie Royer, Ilia Karmanov, et al. | BMVC, 2022
- **Data Compression** — [Differentiable bit-rate estimation for neural-based video codec enhancement](http://arxiv.org/abs/2301.09776) — Amir Said, Manish Kumar Singh, et al. | PCS, 2022
- **Personalization and On-Device Learning** — [Variational On-the-Fly Personalization](https://proceedings.mlr.press/v162/kim22e.html) — Jun-Tae Lee, Simyung Chang | ICML, 2022
- **Machine Learning Fundamentals** — [Equivariant Priors for compressed sensing with unknown orientation](https://arxiv.org/abs/2206.14069) — Fabio Valerio Massoli, Arash Behboodi | ICML, 2022
- **Optimization and Reinforcement Learning** — [Neural topological ordering for computation graphs](https://arxiv.org/abs/2207.05899) — Mukul Gagrani, Corrado Rainone, et al. | NeurIPS, 2022
- **Computer Vision** — [InverseForm: A Loss Function for Structured Boundary-Aware Segmentation](https://arxiv.org/abs/2104.02745) — Shubhankar Borse, Ying Wang, et al. | CVPR, 2021 — [https://www.qualcomm.com/research/artificial-intelligence/ai-research/papers-with-code/paper-2](https://www.qualcomm.com/research/artificial-intelligence/ai-research/papers-with-code/paper-2)
- **Machine Learning Fundamentals** — [Gauge Equivariant Mesh CNNs: Anisotropic convolutions on geometric graphs](https://arxiv.org/abs/2003.05425) — Pim de Haan, Maurice Weiler, et al. | ICLR, 2021 — [https://www.qualcomm.com/research/artificial-intelligence/ai-research/papers-with-code/paper-6](https://www.qualcomm.com/research/artificial-intelligence/ai-research/papers-with-code/paper-6)
- **Power and Model Efficiency** — [Distilling Optimal Neural Networks: Rapid Search in Diverse Spaces](https://arxiv.org/abs/2012.08859v1) — Bert Moons, Parham Noorzad, et al. | ICCV, 2021
- **Personalization and On-Device Learning** — [Prototype-based Personalized Pruning](https://arxiv.org/abs/2103.15564) — Jangho Kim, Simyung Chang, et al. | ICASSP, 2021
- **AI Compilers, Algorithms, and System Architecture** — [A Quantitative Theory of Bottleneck Structures for Data Networks](https://arxiv.org/abs/2210.03534) — Jordi Ros-Giralt, Noah Amsel, et al. | 2021
- **Machine Learning Fundamentals** — [Efficient Action Recognition via Dynamic Knowledge Propagation](https://openaccess.thecvf.com/content/ICCV2021/papers/Kim_Efficient_Action_Recognition_via_Dynamic_Knowledge_Propagation_ICCV_2021_paper.pdf) — Hanul Kim, Mihir Jain, et al. | ICCV, 2021
- **Machine Learning Fundamentals** — [Motion-Augmented Self-Training for Video Recognition at Smaller Scale](https://openaccess.thecvf.com/content/ICCV2021/papers/Gavrilyuk_Motion-Augmented_Self-Training_for_Video_Recognition_at_Smaller_Scale_ICCV_2021_paper.pdf) — Kirill Gavrilyuk, Mihir Jain, et al. | ICCV, 2021
- **Computer Vision** — [Skip-Convolutions for Efficient Video Processing](https://arxiv.org/abs/2104.11487) — Amirhossein Habibian, Davide Abati, et al. | CVPR, 2021 — [https://www.qualcomm.com/research/artificial-intelligence/ai-research/papers-with-code/paper-3](https://www.qualcomm.com/research/artificial-intelligence/ai-research/papers-with-code/paper-3)
- **Machine Learning Fundamentals** — [Probabilistic Numeric Convolutional Neural Networks](https://arxiv.org/abs/2010.10876) — Marc Finzi, Roberto Bondesan, et al. | ICLR, 2021 — [https://www.qualcomm.com/research/artificial-intelligence/ai-research/papers-with-code/paper-4](https://www.qualcomm.com/research/artificial-intelligence/ai-research/papers-with-code/paper-4)
- **Data Compression** — [Progressive Neural Image Compression with Nested Quantization and Latent Ordering](https://arxiv.org/abs/2102.02913) — Yadong Lu, Yinhao Zhu, et al. | ICIP, 2021
- **Power and Model Efficiency** — [Understanding and Overcoming the Challenges of Efficient Transformer Quantization](https://aclanthology.org/2021.emnlp-main.627.pdf) — Yelysei Bondarenko, Markus Nagel, et al. | EMNLP, 2021 — [https://www.qualcomm.com/research/artificial-intelligence/ai-research/papers-with-code/paper-5](https://www.qualcomm.com/research/artificial-intelligence/ai-research/papers-with-code/paper-5)
- **Personalization and On-Device Learning** — [Federated Learning of User Verification Models Without Sharing Embeddings](https://icml.cc/virtual/2021/spotlight/8754) — Hossein Hosseini, Hyunsin Park, et al. | ICML, 2021
- **Wireless and RF** — [Neural Augmentation of Kalman Filter with Hypernetwork for Channel Tracking](https://arxiv.org/abs/2109.12561) — Kumar Pratik, Rana Ali Amjad, et al. | Globecom, 2021
- **Data Compression** — [Extending Neural P-frame Codecs for B-frame Coding](https://openaccess.thecvf.com/content/ICCV2021/papers/Pourreza_Extending_Neural_P-Frame_Codecs_for_B-Frame_Coding_ICCV_2021_paper.pdf) — Reza Pourreza and Taco Cohen | ICCV, 2021
- **Data Compression** — [Overfitting for Fun and Profit: Instance-Adaptive Data Compression](https://arxiv.org/abs/2101.08687) — Ties van Rozendaal, Iris A.M. Huijben, et al. | ICLR, 2021
- **Computer Vision** — [FrameExit: Conditional Early Exiting for Efficient Video Recognition](https://arxiv.org/abs/2104.13400) — Amir Ghodrati, Babak Ehteshami Bejnordi, et al. | CVPR, 2021 — [https://www.qualcomm.com/research/artificial-intelligence/ai-research/papers-with-code/paper-1](https://www.qualcomm.com/research/artificial-intelligence/ai-research/papers-with-code/paper-1)
- **Computer Vision** — [Conditional Model Selection for Efficient Video Understanding](https://www.bmvc2021-virtualconference.com/conference/papers/paper_1376.html) — Mihir Jain, Haitam Ben Yahia, et al. | BMVC, 2021
- **Computer Vision** — [HS3: Learning with Proper Task Complexity in Hierarchically Supervised Semantic Segmentation](https://www.bmvc2021-virtualconference.com/conference/papers/paper_0749.html) — Shubhankar Borse, Hong Cai, et al. | BMVC, 2021
- **Personalization and On-Device Learning** — [Federated Learning of User Verification Models Without Sharing Embeddings](https://arxiv.org/abs/2104.08776) — Hossein Hosseini, Hyunsin Park, et al. | ICML, 2021
- **Machine Learning Fundamentals** — [The Hintons in your Neural Network: a Quantum Field Theory View of Deep Learning](https://arxiv.org/abs/2103.04913) — Roberto Bondesan, Max Welling | ICML, 2021
- **Speech, Audio, and Language Processing** — [Broadcasted Residual Learning for Efficient Keyword Spotting](https://arxiv.org/abs/2106.04140) — Byeonggeun Kim, Simyung Chang, et al. | Interspeech, 2021 — [https://www.qualcomm.com/research/artificial-intelligence/ai-research/papers-with-code/paper-10](https://www.qualcomm.com/research/artificial-intelligence/ai-research/papers-with-code/paper-10)
- **Speech, Audio, and Language Processing** — [PQK: Model Compression for Computational Resource Constraint via Pruning, Quantization and Knowledge Distillation](https://arxiv.org/abs/2106.14681) — Jangho Kim, Simyung Chang, et al. | Interspeech, 2021
- **Wireless and RF** — [Modality-Agnostic Topology Aware Localization](https://papers.nips.cc/paper/2021/hash/569ff987c643b4bedf504efda8f786c2-Abstract.html) — Farhad Ghazvinian Zanjani, Ilia Karmanov, et al. | NeurIPS, 2021
- **Machine Learning Fundamentals** — [Cross-Attentional Audio-Visual Fusion for Weakly-Supervised Action Localization](https://openreview.net/forum?id=hWr3e3r-oH5) — Jun-Tae Lee, Mihir Jain, et al. | ICLR, 2021
- **Wireless and RF** — [Hand gesture recognition using 802.11ad mmWave sensor in the mobile device](https://ieeexplore.ieee.org/document/9419978) — Yuwei Ren, Jiuyuan Lu, et al. | WCNC, 2021
- **Speech, Audio, and Language Processing** — [SubSpectral Normalization for Neural Audio Data Processing](https://arxiv.org/abs/2103.13620) — Simyung Chang, Hyoungwoo Park, et al. | ICASSP, 2021
- **Wireless and RF** — [WiCluster: Passive Indoor 2D/3D Positioning using WiFi without Precise Labels](https://arxiv.org/abs/2107.01002) — Ilia Karmanov, Farhad G. Zanjani, et al. | Globecom, 2021
- **Personalization and On-Device Learning** — [A Graphical Model Perspective On Federated Learning](https://dp-ml.github.io/2021-workshop-ICLR/files/34.pdf) — Christos Louizos, Matthias Reisser, et al. | ICLR, 2021
- **Computer Vision** — [X-Distill: Improving Self-Supervised Monocular Depth via Cross-Task Distillation](https://www.bmvc2021-virtualconference.com/conference/papers/paper_0510.html) — Hong Cai, Janarbek Matai, et al. | BMVC, 2021
- **Power and Model Efficiency** — [A Data and Compute Efficient Design for Limited-Resources Deep Learning](https://arxiv.org/abs/2004.09691) — Mirgahney Mohamed, Gabriele Cesa, et al. | ICLR, 2020
- **Data Compression** — [Adversarial Distortion for Learned Video Compression](https://arxiv.org/abs/2004.09508) — Vijay Veerabadran, Reza Pourreza, et al. | CVPR, 2020
- **Data Compression** — [Lossy Compression with Distortion Constrained Optimization](https://arxiv.org/abs/2005.04064) — Ties van Rozendaal, Guillaume Sautière, et al. | CVPR, 2020
- **Computer Vision** — [ActionBytes: Learning from Trimmed Videos to Localize Actions](https://openaccess.thecvf.com/content_CVPR_2020/html/Jain_ActionBytes_Learning_From_Trimmed_Videos_to_Localize_Actions_CVPR_2020_paper.html) — Mihir Jain, Amir Ghodrati1, et al. | CVPR, 2020
- **Power and Model Efficiency** — [Bayesian Bits: Unifying Quantization and Pruning](https://arxiv.org/abs/2005.07093) — Mart van Baalen, Christos Louizos, et al. | NeurIPS, 2020 — [https://www.qualcomm.com/research/artificial-intelligence/ai-research/papers-with-code/paper-7](https://www.qualcomm.com/research/artificial-intelligence/ai-research/papers-with-code/paper-7)
- **Power and Model Efficiency** — [Batch-Shaping for Learning Conditional Channel Gated Networks](https://arxiv.org/abs/1907.06627) — Babak Ehteshami Bejnordi, Tijmen Blankevoort, et al. | ICLR, 2020
- **Computer Vision** — [End-to-End Lane Marker Detection via Row-wise Classification](https://arxiv.org/abs/2005.08630) — Seungwoo Yoo, Heeseok Lee, et al. | CVPR, 2020
- **Power and Model Efficiency** — [Up or Down? Adaptive Rounding for Post-Training Quantization](https://arxiv.org/abs/2004.10568) — ICML, 2020
- **AI Compilers, Algorithms, and System Architecture** — [Ordering Chaos: Memory-Aware Scheduling of Irregularly Wired Neural Networks for Edge Devices](https://arxiv.org/abs/2003.02369) — Byung Hoon Ahn, Jinwon Lee, et al. | MLSys, 2020
- **Power and Model Efficiency** — [Gradient l1 Regularization for Quantization Robustness](https://arxiv.org/abs/2002.07520) — Milad Alizadeh, Arash Behboodi, et al. | ICLR, 2020
- **Power and Model Efficiency** — [Structured Convolutions for Efficient Neural Network Design](https://arxiv.org/abs/2008.02454) — Yash Bhalgat, Yizhe Zhang, et al. | NeurIPS, 2020
- **Data Compression** — [Feedback Recurrent Autoencoder](https://arxiv.org/abs/1911.04018) — Yang Yang, Guillaume Sautière, et al. | ICASSP, 2020
- **Power and Model Efficiency** — [Conditional Channel Gated Networks for Task-Aware Continual Learning](https://arxiv.org/abs/2004.00070) — Davide Abati, Jakub Tomczak, et al. | CVPR, 2020
- **Machine Learning Fundamentals** — [Natural Graph Networks](https://arxiv.org/abs/2007.08349) — Pim de Haan, Taco Cohen, et al. | NeurIPS, 2020
- **Power and Model Efficiency** — [LSQ+: Improving low-bit quantization through learnable offsets and better initialization](https://arxiv.org/abs/2004.09576) — Yash Bhalgat, Jinwon Lee, et al. | CVPR, 2020
- **Power and Model Efficiency** — [Differentiable Joint Pruning and Quantization for Hardware Efficiency](https://arxiv.org/abs/2007.10463) — Ying Wang, Yadong Lu, et al. | ECCV, 2020
- **Power and Model Efficiency** — [Blended Coarse Gradient Descent for Full Quantization of Deep Neural Networks](https://arxiv.org/abs/1808.05240) — Penghang Yin, Shuai Zhang, et al. | RMS, 2019
- **Machine Learning Fundamentals** — [A General Theory of Equivariant CNNs on Homogeneous Spaces](https://arxiv.org/abs/1811.02017) — Taco Cohen, Mario Geiger, et al. | NeurIPS, 2019
- **Power and Model Efficiency** — [DAC: Data-free Automatic Acceleration of Convolutional Networks](https://arxiv.org/abs/1812.08374) — Xin Li, Shuai Zhang, et al. | WACV, 2019
- **Computer Vision** — [Weakly-supervised Degree of Eye-Closeness Estimation](https://arxiv.org/abs/1910.10845) — Eyasu Mequanint, Shuai Zhang, et al. | ICCV, 2019
- **Computer Vision** — [Recognizing Compressed Videos: Challenges and Promises](http://openaccess.thecvf.com/content_ICCVW_2019/papers/RLQ/Pourreza_Recognizing_Compressed_Videos_Challenges_and_Promises_ICCVW_2019_paper.pdf) — Reza Pourreza, Amir Ghodrati, et al. | ICCV, 2019
- **Machine Learning Fundamentals** — [Gauge Equivariant Convolutional Networks and the Icosahedral CNN](https://arxiv.org/abs/1902.04615) — Taco S. Cohen, Maurice Weiler, et al. | ICML, 2019
- **Speech, Audio, and Language Processing** — [An End-to-End Text-independent Speaker Verification Framework with a Keyword Adversarial Network](https://arxiv.org/abs/1908.02612) — Sungrack Yun, Janghoon Cho, et al. | Interspeech, 2019
- **Power and Model Efficiency** — [Understanding Straight-Through Estimator in Training Activation Quantized Neural Nets](https://arxiv.org/abs/1903.05662) — Penghang Yin, Jiancheng Lyu, et al. | ICLR, 2019
- **Power and Model Efficiency** — [Data-Free Quantization through Weight Equalization and Bias Correction](https://arxiv.org/abs/1906.04721) — Markus Nagel, Mart van Baalen, et al. | ICCV, 2019
- **Optimization and Reinforcement Learning** — [Combinatorial Bayesian Optimization using Graph Cartesian Product](https://arxiv.org/abs/1902.00448) — Jakub Tomczak, Max Welling, et al. | NeurIPS, 2019
- **Data Compression** — [Video Compression With Rate-Distortion Autoencoders](https://arxiv.org/abs/1908.05717) — Amirhossein Habibian, Ties van Rozendaal, et al. | ICCV, 2019
- **Wireless and RF** — [Vehicle Detection with Automotive Radar using Deep Learning on Range-Azimuth-Doppler Tensors](http://openaccess.thecvf.com/content_ICCVW_2019/papers/CVRSUAD/Major_Vehicle_Detection_With_Automotive_Radar_Using_Deep_Learning_on_Range-Azimuth-Doppler_ICCVW_2019_paper.pdf) — Bence Major, Daniel Fontijne, et al. | ICCV, 2019
- **Power and Model Efficiency** — [Relaxed Quantization for Discretized Neural Networks](https://arxiv.org/abs/1810.01875) — Christos Louizos, Matthias Reisser, et al. | NeurIPS, 2018
- **Optimization and Reinforcement Learning** — [Risk-averse Behavior Planning for Autonomous Driving under Uncertainty](https://arxiv.org/abs/1812.01254) — Mohammad Naghshvar, Ahmed K. Sadek, et al. | NeurIPS, 2018
- **Personalization and On-Device Learning** — [Multi-Fidelity Recursive Behavior Prediction](https://arxiv.org/abs/1901.01831) — Mihir Jain, Ahmed Sadek, et al. | NeurIPS, 2018
- **Power and Model Efficiency** — [A Quantization-Friendly Separable Convolution for MobileNets](https://arxiv.org/abs/1803.08607) — Tao Sheng, Chen Feng, et al. | EMC^, 2018
- **Computer Vision** — [A Compact Deep Learning Model for Robust Facial Expression Recognition](http://openaccess.thecvf.com/content_cvpr_2018_workshops/papers/w41/Kuo_A_Compact_Deep_CVPR_2018_paper.pdf) — Chieh-Ming Kuo, Shang-Hong Lai, et al. | CVPR, 2018
- **Machine Learning Fundamentals** — [Spherical CNNs](https://arxiv.org/abs/1801.10130) — T.S. Cohen, M. Geiger, et al. | ICLR, 2018
- **Machine Learning Fundamentals** — [HexaConv](https://arxiv.org/abs/1803.02108) — E. Hoogeboom, J.W.T. Peters, et al. | ICLR, 2018
- **Machine Learning Fundamentals** — [3D Steerable CNNs: Learning Rotationally Equivariant Features in Volumetric Data](https://arxiv.org/abs/1807.02547) — Maurice Weiler, Mario Geiger, et al. | NeurIPS, 2018
- **Speech, Audio, and Language Processing** — [Speaker Clustering by Iteratively Finding Discriminative Feature Space and Cluster Labels](https://www.isca-archive.org/interspeech_2017/yun17_interspeech.pdf) — Sungrack Yun, Hye Jin Jang, et al. | Interspeech, 2017
- **Computer Vision** — [Video2vec Embeddings Recognize Events when Examples are Scarce](https://ieeexplore.ieee.org/document/7740886/) — Amirhossein Habibian; Thomas Mensink; Cees G. M. Snoek | IEEE, 2017