6 papers
Latent Personal Memory: Represent personal memory as dynamic soft prompts
Debrup Das, Avinash Amballa, Yashas Malur Saidutta +3
Personalizing large language models (LLMs) requires encoding long-term, user-specific behavioral patterns in a way that is computationally efficient, scalable, and compatible with…
Doc-to-Atom: Learning to Compile and Compose Memory Atoms
Xingjian Diao, Wenbo Li, Yashas Malur Saidutta +3
Long input sequences are central to document understanding and multi-step reasoning in Large Language Models, yet the quadratic cost of attention makes inference both memory-intens…
VOYAGER: A Training Free Approach for Generating Diverse Datasets using LLMs
Avinash Amballa, Yashas Malur Saidutta, Chi-Heng Lin +2
Large language models (LLMs) are increasingly being used to generate synthetic datasets for the evaluation and training of downstream models. However, prior work has noted that suc…
Insertion Language Models: Sequence Generation with Arbitrary-Position Insertions
Dhruvesh Patel, Aishwarya Sahoo, Avinash Amballa +3
Autoregressive models (ARMs), which predict subsequent tokens one-by-one ``from left to right,'' have achieved significant success across a wide range of sequence generation tasks.…
CoPE: A Lightweight Complex Positional Encoding
Avinash Amballa
Recent studies have demonstrated the effectiveness of position encoding in transformer architectures. By incorporating positional information, this approach provides essential guid…
LS-GAN: Human Motion Synthesis with Latent-space GANs
Avinash Amballa, Gayathri Akkinapalli, Vinitra Muralikrishnan
Human motion synthesis conditioned on textual input has gained significant attention in recent years due to its potential applications in various domains such as gaming, film produ…