HH
Hossein Hajimirsadeghi
cs.LGcs.AIcs.CVstat.MLcs.CLcs.ROcs.SI
On Valency
published · living versionsW_rpjc2zwf·v1 · currentpublished
Distilling the Shape of Uncertainty: What On-Policy Distillation Learns and How to Predict It
with Shiping Yang, Chuanqi Tang, Layla El Asri, Mohammad Amin Shabani +1
1 version
Preprints & journals
25 papers in the corpus · 2013–2026Can LLMs Access their World Knowledge for Event Prediction?2610.19021v1 · Zijun Wu, Zhitian Zhang, Hossein Hajimirsadeghi et al.2026 · 0 citationsarXiv
Oculi: A Conversational Agentic Platform for Automated Credit Risk Analysis2608.28944v1 · Vennise Ho, Kristian Diana, Sandy Mourad et al.2026 · 0 citationsarXiv
Coverage-Driven KV Cache Eviction for Efficient and Improved Inference of LLM2606.29563v1 · Shuvendu Roy, Mengyao Zhai, Hossein Hajimirsadeghi et al.2026 · 0 citationsarXiv
An Attention-based Model for Robust Forecasting with Missing Modality2606.13970v1 · Zhitian Zhang, Wenjie Zi, Yunduz Rakhmangulova et al.2026 · 0 citationsarXiv
You Need Reasoning to Learn Reasoning: The Limitations of Label-Free RL in Weak Base Models2511.04902v1 · Shuvendu Roy, Hossein Hajimirsadeghi, Mengyao Zhai et al.2025 · 0 citationsarXiv
TabReason: A Reinforcement Learning-Enhanced Reasoning LLM for Explainable Tabular Data Prediction2505.21807v3 · Tommy Xu, Zhitian Zhang, Xiangyu Sun et al.2025 · 0 citationsarXiv
Radar: Fast Long-Context Decoding for Any Transformer2503.10571v1 · Yongchang Hao, Mengyao Zhai, Hossein Hajimirsadeghi et al.2025 · 1 citationarXiv
Were RNNs All We Needed?2410.01201v3 · Leo Feng, Frederick Tung, Mohamed Osama Ahmed et al.2024 · 11 citationsarXiv
Attention as an RNN2405.13956v2 · Leo Feng, Frederick Tung, Hossein Hajimirsadeghi et al.2024 · 3 citationsarXiv
Prompting-based Temporal Domain Generalization2310.02473v2 · Sepidehsadat Hosseini, Mengyao Zhai, Hossein Hajimirsadegh et al.2023 · 0 citationsarXiv
Tree Cross Attention2309.17388v2 · Leo Feng, Frederick Tung, Hossein Hajimirsadeghi et al.2023 · 0 citationsarXiv
Constant Memory Attention Block2306.12599v1 · Leo Feng, Frederick Tung, Hossein Hajimirsadeghi et al.2023 · 0 citationsarXiv
Memory Efficient Neural Processes via Constant Memory Attention Block2305.14567v3 · Leo Feng, Frederick Tung, Hossein Hajimirsadeghi et al.2023 · 1 citationarXiv
Latent Bottlenecked Attentive Neural Processes2211.08458v3 · Leo Feng, Hossein Hajimirsadeghi, Yoshua Bengio et al.2022 · 1 citationarXiv
Training a Vision Transformer from scratch in less than 24 hours with 1 GPU2211.05187v1 · Saghar Irandoust, Thibaut Durand, Yunduz Rakhmangulova et al.2022 · 3 citationsarXiv
Towards Better Selective Classification2206.09034v4 · Leo Feng, Mohamed Osama Ahmed, Hossein Hajimirsadeghi et al.2022 · 5 citationsarXiv
Monotonicity Regularization: Improved Penalties and Novel Applications to Disentangled Representation Learning and Robust Classification2205.08247v1 · Joao Monteiro, Mohamed Osama Ahmed, Hossein Hajimirsadeghi et al.2022 · 1 citationarXiv
TD-GEN: Graph Generation With Tree Decomposition2106.10656v2 · Hamed Shirzad, Hossein Hajimirsadeghi, Amir H. Abdi et al.2021 · 0 citationsarXiv
Variational Selective Autoencoder: Learning from Partially-Observed Heterogeneous Data2102.12679v1 · Yu Gong, Hossein Hajimirsadeghi, Jiawei He et al.2021 · 6 citationsarXiv
Adapting Grad-CAM for Embedding Networks2001.06538v1 · Lei Chen, Jianhui Chen, Hossein Hajimirsadeghi et al.2020 · 86 citationsarXiv
Graph Generation with Variational Recurrent Neural Network1910.01743v1 · Shih-Yang Su, Hossein Hajimirsadeghi, Greg Mori2019 · 14 citationsarXiv
Learning to Detect Blue-White Structures in Dermoscopy Images With Weak Supervision.29993758 · Madooei, Ali, Drew, Mark S, Hajimirsadeghi, Hossein2019 · 23 citationsIEEE journal of biomedical and health informatics. 2019;23(2):779-786
Multi-Instance Classification by Max-Margin Training of Cardinality-Based Markov Networks.28114057 · Hajimirsadeghi, Hossein, Mori, Greg2018 · 11 citationsIEEE transactions on pattern analysis and machine intelligence. 2017;39(9):1839-1852
Discovering Human Interactions in Videos with Limited Data Labeling1502.03851v1 · Mehran Khodabandeh, Arash Vahdat, Guang-Tong Zhou et al.2015 · 17 citationsarXiv
Multiple Instance Learning by Discriminative Training of Markov Networks1309.6833v1 · Hossein Hajimirsadeghi, Jinling Li, Greg Mori et al.2013 · 14 citationsarXiv
Career total: 49 works. 25 are in this corpus.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.