Alessandro Sordoni

Computer Science · Physical Sciences

30h-index5.3kcitations126works0.62yr avg
OpenAlex↗Google Scholar↗

Accepting Students?

No reports yet. Know if this professor is taking students?

Research Topics

Topic Modeling(76), Natural Language Processing Techniques(56), Multimodal Machine Learning Applications(27), Domain Adaptation and Few-Shot Learning(16), Speech Recognition and Synthesis(14)

Publications126 total

Effect of Document Packing on the Latent Multi-Hop Reasoning Capabilities of Large Language Models
arXiv (Cornell University)·2025Open Access
Learning to Extract Context for Context-Aware LLM Inference
arXiv (Cornell University)·2025Open Access
BugPilot: Complex Bug Generation for Efficient Learning of SWE Skills
arXiv (Cornell University)·2025Open Access
The Markovian Thinker: Architecture-Agnostic Linear Scaling of Reasoning
ArXiv.org·2025Open Access
Exploring Sparse Adapters for Scalable Merging of Parameter Efficient Experts
arXiv (Cornell University)·2025Open Access
Putting the Value Back in RL: Better Test-Time Scaling by Unifying LLM Reasoners With Verifiers
arXiv (Cornell University)·2025Open Access
debug-gym: A Text-Based Environment for Interactive Debugging
arXiv (Cornell University)·2025· 1 citedOpen Access
Training Plug-n-Play Knowledge Modules with Deep Context Distillation
arXiv (Cornell University)·2025Open Access
A Modular Approach for Clinical SLMs Driven by Synthetic Data with Pre-Instruction Tuning, Model Merging, and Clinical-Tasks Alignment
2025· 1 citedOpen Access
Not All LLM Reasoners Are Created Equal
arXiv (Cornell University)·2024· 2 citedOpen Access
VinePPO: Refining Credit Assignment in RL Training of LLMs
arXiv (Cornell University)·2024· 1 citedOpen Access
A Survey on Model MoErging: Recycling and Routing Among Specialized Experts for Collaborative Learning
arXiv (Cornell University)·2024Open Access
Improving Context-Aware Preference Modeling for Language Models
arXiv (Cornell University)·2024· 1 citedOpen Access
Efficient Adversarial Training in LLMs with Continuous Attacks
arXiv (Cornell University)·2024· 3 citedOpen Access
Towards Modular LLMs by Building and Reusing a Library of LoRAs
arXiv (Cornell University)·2024Open Access
V-STaR: Training Verifiers for Self-Taught Reasoners
arXiv (Cornell University)·2024· 3 citedOpen Access
Efficient Adversarial Training in LLMs with Continuous Attacks
2024
Efficient Reinforcement Learning by Discovering Neural Pathways
2024
Improving Context-Aware Preference Modeling for Language Models
2024
Guiding Language Model Reasoning with Planning Tokens
arXiv (Cornell University)·2023· 2 citedOpen Access
page 1 of 7Next →

Frequent Co-authors

Adam Trischler(18), Yoshua Bengio(17), Jian‐Yun Nie(11), Aaron Courville(11), Philip Bachman(10), Joëlle Pineau(5), Rémi Tachet des Combes(5), Zhouhan Lin(5), Nan Rosemary Ke(5), Michel Galley(4), Michael Auli(4), Chris Brockett(4), Yangfeng Ji(4), Margaret Mitchell(4), Jianfeng Gao(4), Bill Dolan(4), Xingdi Yuan(4), Yikang Shen(4), Chris Pal(4), Tong Wang(3)