papers

Publications (6)

cs.LG2024

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 \(ΔW\). These \(ΔW\) m…

cs.CL2026

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…

cs.LG2026

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…

cs.CL2024

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…

cs.LG2026

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…

cs.AI2026

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…