Mostafa Dehghani

Identifiers

• name variant Mostafa Dehghani 0.60 · backfill

Papers (58)

1. Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities cs.CL · 2025 · author #1873
2. Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context cs.CL · 2024 · author #557
3. Gemini: A Family of Highly Capable Multimodal Models cs.CL · 2023 · author #483
4. Patch n' Pack: NaViT, a Vision Transformer for any Aspect Ratio and Resolution cs.CV · 2023 · author #1
5. PaLI-X: On Scaling up a Multilingual Vision and Language Model cs.CV · 2023 · author #12
6. PaLM 2 Technical Report cs.CL · 2023 · author #40
7. End-to-End Spatio-Temporal Action Localisation with Video Transformers cs.CV · 2023 · author #4
8. Scaling Vision Transformers to 22 Billion Parameters cs.CV · 2023 · author #1
9. Dual PatchNorm cs.CV · 2023 · author #2
10. Adaptive Computation with Elastic Input Sequence cs.LG · 2023 · author #5
11. Sparse Upcycling: Training Mixture-of-Experts from Dense Checkpoints cs.LG · 2022 · author #8
12. Scaling Instruction-Finetuned Language Models cs.LG · 2022 · author #9
13. Transcending Scaling Laws with 0.1% Extra Compute cs.CL · 2022 · author #16
14. $\Lambda$-DARTS: Mitigating Performance Collapse by Harmonizing Operation Selection among Cells cs.LG · 2022 · author #5
15. Intersection of Parallels as an Early Stopping Criterion cs.LG · 2022 · author #3
16. Scaling Laws vs Model Architectures: How does Inductive Bias Influence Scaling? cs.LG · 2022 · author #2
17. Confident Adaptive Language Modeling cs.CL · 2022 · author #4
18. Beyond Transfer Learning: Co-finetuning for Action Localisation cs.CV · 2022 · author #6
19. Simple Open-Vocabulary Object Detection with Vision Transformers cs.CV · 2022 · author #9
20. UL2: Unifying Language Learning Paradigms cs.CL · 2022 · author #2
21. Retrieval-Enhanced Machine Learning cs.LG · 2022 · author #3
22. Transformer Memory as a Differentiable Search Index cs.CL · 2022 · author #3
23. VUT: Versatile UI Transformer for Multi-Modal Multi-Task User Interface Modeling cs.CV · 2021 · author #4
24. PolyViT: Co-training Vision Transformers on Images, Videos and Audio cs.CV · 2021 · author #7
25. Discrete Representations Strengthen Vision Transformer Robustness cs.CV · 2021 · author #3
26. The Efficiency Misnomer cs.LG · 2021 · author #1
27. SCENIC: A JAX Library for Computer Vision Research and Beyond cs.CV · 2021 · author #1
28. Exploring the Limits of Large Scale Pre-training cs.LG · 2021 · author #2
29. Scale Efficiently: Insights from Pre-training and Fine-tuning Transformers cs.CL · 2021 · author #2
30. The Benchmark Lottery cs.LG · 2021 · author #1
31. TokenLearner: What Can 8 Learned Tokens Do for Images and Videos? cs.CV · 2021 · author #4
32. Gradual Domain Adaptation in the Wild:When Intermediate Distributions are Absent cs.LG · 2021 · author #4
33. Parameter-efficient Multi-task Fine-tuning for Transformers via Shared Hypernetworks cs.CL · 2021 · author #3
34. Are Pre-trained Convolutions Better than Pre-trained Transformers? cs.CL · 2021 · author #2
35. ViViT: A Video Vision Transformer cs.CV · 2021 · author #2
36. OmniNet: Omnidirectional Representations from Transformers cs.CV · 2021 · author #2
37. Long Range Arena: A Benchmark for Efficient Transformers cs.LG · 2020 · author #2
38. An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale cs.CV · 2020 · author #7
39. Efficient Transformers: A Survey cs.LG · 2020 · author #2
40. IDF++: Analyzing and Improving Integer Discrete Flows for Lossless Compression cs.LG · 2020 · author #3
41. Transferring Inductive Biases through Knowledge Distillation cs.LG · 2020 · author #2
42. MetNet: A Neural Weather Model for Precipitation Forecasting cs.LG · 2020 · author #4
43. HiTR: Hierarchical Topic Model Re-estimation for Measuring Topical Diversity of Documents cs.CL · 2018 · author #2
44. Universal Transformers cs.CL · 2018 · author #1
45. Learning to Rank from Samples of Variable Quality cs.IR · 2018 · author #1
46. Neural Networks for Information Retrieval cs.IR · 2018 · author #4
47. Learning to Learn from Weak Supervision by Full Supervision stat.ML · 2017 · author #1
48. Words are Malleable: Computing Semantic Shifts in Political and Media Discourse cs.CL · 2017 · author #2
49. Fidelity-Weighted Learning cs.LG · 2017 · author #1
50. Avoiding Your Teacher's Mistakes: Training Neural Networks with Controlled Weak Supervision cs.LG · 2017 · author #1
51. On Search Powered Navigation cs.IR · 2017 · author #1
52. Learning to Attend, Copy, and Generate for Session-Based Query Suggestion cs.IR · 2017 · author #1
53. Share your Model instead of your Data: Privacy Preserving Mimic Learning for Ranking cs.IR · 2017 · author #1
54. Neural Networks for Information Retrieval cs.IR · 2017 · author #4
55. Neural Ranking Models with Weak Supervision cs.IR · 2017 · author #1
56. Hierarchical Re-estimation of Topic Models for Measuring Topical Diversity cs.IR · 2017 · author #2
57. On Horizontal and Vertical Separation in Hierarchical Text Classification cs.IR · 2016 · author #1
58. Generalized Group Profiling for Content Customization cs.IR · 2016 · author #1

Mentions

• 2305.10403 #40 · arxiv_oai · confidence 0.70 Mostafa Dehghani
• 2307.06304 #1 · arxiv_oai · confidence 0.70 Mostafa Dehghani
• 2301.13195 #5 · arxiv_oai · confidence 0.70 Mostafa Dehghani
• 2302.01327 #2 · arxiv_oai · confidence 0.70 Mostafa Dehghani
• 2304.12160 #4 · arxiv_oai · confidence 0.70 Mostafa Dehghani
• 2210.07998 #5 · arxiv_oai · confidence 0.70 Mostafa Dehghani
• 2205.05131 #2 · arxiv_oai · confidence 0.70 Mostafa Dehghani
• 2212.05055 #8 · arxiv_oai · confidence 0.70 Mostafa Dehghani
• 2302.05442 #1 · arxiv_oai · confidence 0.70 Mostafa Dehghani
• 2210.11416 #9 · arxiv_oai · confidence 0.70 Mostafa Dehghani
• 2210.11399 #16 · arxiv_oai · confidence 0.70 Mostafa Dehghani
• 2207.07061 #4 · arxiv_oai · confidence 0.70 Mostafa Dehghani
• 2202.06991 #3 · arxiv_oai · confidence 0.70 Mostafa Dehghani
• 2208.09529 #3 · arxiv_oai · confidence 0.70 Mostafa Dehghani
• 2207.10551 #2 · arxiv_oai · confidence 0.70 Mostafa Dehghani
• 2205.06230 #9 · arxiv_oai · confidence 0.70 Mostafa Dehghani
• 2207.03807 #6 · arxiv_oai · confidence 0.70 Mostafa Dehghani
• 2205.01230 #3 · arxiv_oai · confidence 0.70 Mostafa Dehghani
• 2106.11297 #4 · arxiv_oai · confidence 0.70 Mostafa Dehghani
• 2111.10493 #3 · arxiv_oai · confidence 0.70 Mostafa Dehghani
• 2110.12894 #1 · arxiv_oai · confidence 0.70 Mostafa Dehghani
• 2009.06732 #2 · arxiv_oai · confidence 0.70 Mostafa Dehghani
• 2109.10686 #2 · arxiv_oai · confidence 0.70 Mostafa Dehghani
• 2105.03322 #2 · arxiv_oai · confidence 0.70 Mostafa Dehghani
• 2112.05692 #4 · arxiv_oai · confidence 0.70 Mostafa Dehghani
• 2111.12993 #7 · arxiv_oai · confidence 0.70 Mostafa Dehghani
• 2103.15691 #2 · arxiv_oai · confidence 0.70 Mostafa Dehghani
• 2110.11403 #1 · arxiv_oai · confidence 0.70 Mostafa Dehghani
• 2110.02095 #2 · arxiv_oai · confidence 0.70 Mostafa Dehghani
• 2107.07002 #1 · arxiv_oai · confidence 0.70 Mostafa Dehghani
• 2106.06080 #4 · arxiv_oai · confidence 0.70 Mostafa Dehghani
• 2106.04489 #3 · arxiv_oai · confidence 0.70 Mostafa Dehghani
• 2010.11929 #7 · arxiv_oai · confidence 0.70 Mostafa Dehghani
• 2006.12459 #3 · arxiv_oai · confidence 0.70 Mostafa Dehghani
• 2103.01075 #2 · arxiv_oai · confidence 0.70 Mostafa Dehghani
• 2011.04006 #2 · arxiv_oai · confidence 0.70 Mostafa Dehghani
• 2006.00555 #2 · arxiv_oai · confidence 0.70 Mostafa Dehghani
• 2003.12140 #4 · arxiv_oai · confidence 0.70 Mostafa Dehghani
• 1807.03819 #1 · arxiv_oai · confidence 0.70 Mostafa Dehghani
• 1810.05436 #2 · arxiv_oai · confidence 0.70 Mostafa Dehghani
• 1806.08694 #1 · arxiv_oai · confidence 0.70 Mostafa Dehghani
• 1711.02799 #1 · arxiv_oai · confidence 0.70 Mostafa Dehghani
• 1801.02178 #4 · arxiv_oai · confidence 0.70 Mostafa Dehghani
• 1711.00313 #1 · arxiv_oai · confidence 0.70 Mostafa Dehghani
• 1711.11383 #1 · arxiv_oai · confidence 0.70 Mostafa Dehghani
• 1711.05603 #2 · arxiv_oai · confidence 0.70 Mostafa Dehghani
• 1708.03418 #1 · arxiv_oai · confidence 0.70 Mostafa Dehghani
• 1711.00310 #1 · arxiv_oai · confidence 0.70 Mostafa Dehghani
• 1707.07605 #1 · arxiv_oai · confidence 0.70 Mostafa Dehghani
• 1707.04242 #4 · arxiv_oai · confidence 0.70 Mostafa Dehghani
• 1704.08803 #1 · arxiv_oai · confidence 0.70 Mostafa Dehghani
• 1701.04273 #2 · arxiv_oai · confidence 0.70 Mostafa Dehghani
• 1609.00514 #1 · arxiv_oai · confidence 0.70 Mostafa Dehghani
• 1609.00511 #1 · arxiv_oai · confidence 0.70 Mostafa Dehghani
• 2305.18565 #12 · arxiv_oai · confidence 0.70 Mostafa Dehghani

Frequent Coauthors

• Yi Tay 20 shared papers
• Neil Houlsby 13 shared papers
• Anurag Arnab 12 shared papers
• Donald Metzler 12 shared papers
• Jaap Kamps 12 shared papers
• Dara Bahri 8 shared papers
• Josip Djolonga 8 shared papers
• Alexey Gritsenko 7 shared papers
• Basil Mustafa 7 shared papers
• Denny Zhou 7 shared papers
• Hosein Azarbonyad 7 shared papers
• Mario Lu\v{c}i\'c 7 shared papers
• Siamak Shakeri 7 shared papers
• Aliaksei Severyn 6 shared papers
• Maarten de Rijke 6 shared papers
• Maarten Marx 6 shared papers
• Matthias Minderer 6 shared papers
• Samira Abnar 6 shared papers
• Slav Petrov 6 shared papers
• Xavier Garcia 6 shared papers