DocHop: Benchmarking Out-of-domain Multi-hop Reasoning in Information-Dense Documents
- Zhuoran Yu
- Le Thien Phuc Nguyen
- et al.
- 2026
- ICML 2026
Conference paper
Publications
45 results for Rogerio Feris
Omni-R1: Do You Really Need Audio to Fine-Tune Your Audio LLM?
- Andrew Rouditchenko
- Saurabhchand Bhati
- et al.
- 2025
- ASRU 2025
PosterTeaching VLMs to Localize Specific Objects from In-context Examples
- Sivan Doveh
- Nimrod Shabtay
- et al.
- 2025
- ICCV 2025
Conference paperWorkshop on Memory and Vision
- Zexue He
- Jovana Kondic
- et al.
- 2025
- ICCV 2025
WorkshopM+: Extending MemoryLLM with Scalable Long-Term Memory
- Yu Wang
- Dmitry Krotov
- et al.
- 2025
- ICML 2025
Conference paperCAV-MAE Sync: Improving Contrastive Audio-Visual Mask Autoencoders via Fine-Grained Alignment
- Edson Araujo
- Andrew Rouditchenko
- et al.
- 2025
- CVPR 2025
Conference paperSelf-MoE: Towards Compositional Large Language Models with Self-Specialized Experts
- Junmo Kang
- Leonid Karlinsky
- et al.
- 2025
- ICLR 2025
Conference paperConMe: Rethinking Evaluation of Compositional Reasoning for Modern VLMs
- Irene Huang
- Wei Lin
- et al.
- 2024
- NeurIPS 2024
Conference paperTrans-LoRA: towards data-free Transferable Parameter Efficient Finetuning
- Runqian Wang
- Soumya Ghosh
- et al.
- 2024
- NeurIPS 2024
Conference paperWhisper-Flamingo: Integrating Visual Features into Whisper for Audio-Visual Speech Recognition and Translation
- Andrew Rouditchenko
- Yuan Gong
- et al.
- 2024
- INTERSPEECH 2024
Conference paper