Publications (6)
SVFT: Parameter-Efficient Fine-Tuning with Singular Vectors
Vijay Lingam, Atula Tejaswi, Aditya Vavre +7
Popular parameter-efficient fine-tuning (PEFT) methods, such as LoRA and its variants, freeze pre-trained model weights \(W\) and inject learnable matrices \(ÎW\). These \(ÎW\) m…
RARe: Retrieval Augmented Retrieval with In-Context Examples
Atula Tejaswi, Yoonsang Lee, Sujay Sanghavi +1
While in-context learning is well-studied with decoder-only language models (LLMs), its utility for encoder-only models remains underexplored. We study in-context learning for enco…
Reward-Gated On-Policy Distillation
Mohammad Sadegh Akhondzadeh, Vijay Lingam, Atula Tejaswi +3
On-policy distillation is a powerful way to transfer reasoning ability from a strong teacher to a smaller student: the student samples trajectories from its own policy, and the tea…
Exploring Design Choices for Building Language-Specific LLMs
Atula Tejaswi, Nilesh Gupta, Eunsol Choi
Despite rapid progress in large language models (LLMs), their performance on a vast majority of languages remains unsatisfactory. In this paper, we study building language-specific…
Entropy Aware Reward Guidance for Diffusion Language Model Alignment
Atula Tejaswi, Litu Rout, Constantine Caramanis +2
Reward guidance, also known as posterior sampling, is a popular method for test-time adaptation and post-training in continuous diffusion models. In this paper, we study reward gui…
OpenThoughts-Agent: Data Recipes for Agentic Models
Negin Raoof, Richard Zhuang, Marianna Nezhurina +47
Agentic language models dramatically expand the applications of AI yet little is publicly known about how to curate training data for broadly capable agents. Existing open efforts…