Get started
Author

Soumye Singhal

Multi-label Iterated Learning for Image Classification with Label Ambiguity
2022 · Sai Rajeswar, Pau Rodriguez, et al. · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · 38
PDF
Countering Language Drift with Seeded Iterated Learning
2020 · Lu, Yuchen, Singhal, Soumye, et al. · arXiv (Cornell University) · 38
PDF
Recall Traces: Backtracking Models for Efficient Reinforcement Learning
2018 · Goyal, Anirudh, Brakel, Philemon, et al. · arXiv (Cornell University) · 37
PDF
Supervised Seeded Iterated Learning for Interactive Language Learning
2020 · Yuchen Lu, Soumye Singhal, et al. · Conference on Empirical Methods in Natural Language Processing (EMNLP) · 5
PDF
Nemotron 3 Nano Omni: Efficient and Open Multimodal Intelligence
2026 · NVIDIA, :, et al. · arXiv (Cornell University) · 1
PDF
NVIDIA Nemotron 3: Efficient and Open Intelligence
2025 · NVIDIA, :, et al. · arXiv (Cornell University) · 1
PDF
Llama-Nemotron: Efficient Reasoning Models
2025 · Bercovich, Akhiad, Levy, Itay, et al. · arXiv (Cornell University) · 1
PDF
Effective Backdoor Mitigation in Vision-Language Models Depends on the Pre-training Objective
2023 · Verma, Sahil, Bhatt, Gantavya, et al. · arXiv (Cornell University) · 1
PDF
Jointly Trained Image and Video Generation using Residual Vectors
2020 · Yatin Dandi, Aniket Das, et al. · IEEE Winter Conference on Applications of Computer Vision · 1
PDF
Priming Base Models for Agentic Post-Training: An Open Midtraining Recipe
2026 · Singhal, Soumye, Jennings, Joseph, et al. · arXiv (Cornell University)
PDF
Before They Can Solve: Predicting Post-Training Coding-Agent Performance from Base Models
2026 · Yu, Tan, Bukharin, Alexander, et al. · arXiv (Cornell University)
PDF
Nemotron-Labs-3-Puzzle-75B-A9B: Compressing Hybrid MoE LLMs
2026 · Bercovich, Akhiad, Abramovich, Talor, et al. · arXiv (Cornell University)
PDF
Nemotron 3 Ultra: Open, Efficient Mixture-of-Experts Hybrid Mamba-Transformer Model for Agentic Reasoning
2026 · NVIDIA, :, et al. · arXiv (Cornell University)
PDF
Nemotron 3 Super: Open, Efficient Mixture-of-Experts Hybrid Mamba-Transformer Model for Agentic Reasoning
2026 · NVIDIA, :, et al. · arXiv (Cornell University)
PDF
Nemotron 3 Nano: Open, Efficient Mixture-of-Experts Hybrid Mamba-Transformer Model for Agentic Reasoning
2025 · NVIDIA, :, et al. · arXiv (Cornell University)
PDF
NVIDIA Nemotron Nano V2 VL
2025 · NVIDIA, :, et al. · arXiv (Cornell University)
PDF
NVIDIA Nemotron Nano 2: An Accurate and Efficient Hybrid Mamba-Transformer Reasoning Model
2025 · NVIDIA, :, et al. · arXiv (Cornell University)
PDF
Adversarial Training of Reward Models
2025 · Bukharin, Alexander, Qian, Haifeng, et al. · arXiv (Cornell University)
PDF
Nemotron-H: A Family of Accurate and Efficient Hybrid Mamba-Transformer Models
2025 · NVIDIA, :, et al. · arXiv (Cornell University)
PDF
Reward-aware Preference Optimization: A Unified Mathematical Framework for Model Alignment
2025 · Sun, Shengyang, Zhang, Yian, et al. · arXiv (Cornell University)
PDF
Overcoming Label Ambiguity with Multi-label Iterated Learning
2021 · Sai Rajeswar Mudumba, Pau Rodríguez, et al.
Works count: 22
Citation count: 123
H-index: 4
I10-index: 3
Year
Topic
Type