6 papers
Structuring The Future: Diffusion LLM Speculative Decoding via Calibrated Draft Graphs
Sudhanshu Agrawal, Risheek Garrepalli, Raghavv Goel +3
Diffusion LLMs (dLLMs) have recently emerged as a powerful alternative to autoregressive LLMs (AR-LLMs) with the potential to operate at significantly higher token-generation rates…
A Comparative analysis of Layer-wise Representational Capacity in AR and Diffusion LLMs
Raghavv Goel, Risheek Garrepalli, Sudhanshu Agrawal +3
Autoregressive (AR) language models build representations incrementally via left-to-right prediction, while diffusion language models (dLLMs) are trained through full-sequence deno…
ConFu: Contemplate the Future for Better Speculative Sampling
Zongyue Qin, Raghavv Goel, Mukul Gagrani +3
Speculative decoding has emerged as a powerful approach to accelerate large language model (LLM) inference by employing lightweight draft models to propose candidate tokens that ar…
MADI: Masking-Augmented Diffusion with Inference-Time Scaling for Visual Editing
Shreya Kadambi, Risheek Garrepalli, Shubhankar Borse +2
Despite the remarkable success of diffusion models in text-to-image generation, their effectiveness in grounded visual editing and compositional control remains challenging. Motiva…
DuoLoRA : Cycle-consistent and Rank-disentangled Content-Style Personalization
Aniket Roy, Shubhankar Borse, Shreya Kadambi +8
We tackle the challenge of jointly personalizing content and style from a few examples. A promising approach is to train separate Low-Rank Adapters (LoRA) and merge them effectivel…
Sparse High Rank Adapters
Kartikeya Bhardwaj, Nilesh Prasad Pandey, Sweta Priyadarshi +9
Low Rank Adaptation (LoRA) has gained massive attention in the recent generative AI research. One of the main advantages of LoRA is its ability to be fused with pretrained models,…