AIConfPaper
← Search

Nilesh Jain

9 accepted papers

2025

ContraGS: Codebook-Condensed and Trainable Gaussian Splatting for Fast, Memory-Efficient Reconstruction

Sankeerth Durvasula, Sharanshangar Muhunthan, Zain Moustafa, Richard Chen, Ruofan Liang, Yushi Guan +4
ICCV 2025accepted

3D Gaussian Splatting (3DGS) is a state-of-art technique to model real-world scenes with high quality and real-time rendering.Typically, a higher quality representation can be achieved by using a large number of 3D Gaussians. However, using large 3D Gaussian counts significantly increases the GPU de…

Cited by 0Source ↗PDF ↗Scholar ↗
2025

Mamba-Shedder: Post-Transformer Compression for Efficient Selective Structured State Space Models

Juan Pablo Munoz, Jinjie Yuan, Nilesh Jain
NAACL 2025long

Large pre-trained models have achieved outstanding results in sequence modeling. The Transformer block and its attention mechanism have been the main drivers of the success of these models. Recently, alternative architectures, such as Selective Structured State Space Models (SSMs), have been propose…

Cited by 2Source ↗PDF ↗code ↗Scholar ↗
2025

Retri3D: 3D Neural Graphics Representation Retrieval

Yushi Guan, Daniel Kwan, Jean Sebastien Dandurand, Xi Yan, Ruofan Liang, Yuxuan Zhang +4
ICLR 2025spotlight

Learnable 3D Neural Graphics Representations (3DNGR) have emerged as promising 3D representations for reconstructing 3D scenes from 2D images. Numerous works, including Neural Radiance Fields (NeRF), 3D Gaussian Splatting (3DGS), and their variants, have significantly enhanced the quality of these r…

Cited by 0Source ↗PDF ↗Scholar ↗
2024

EFTNAS: Searching for Efficient Language Models in First-Order Weight-Reordered Super-Networks

Juan Pablo Munoz, Yi Zheng, Nilesh Jain
COLING 2024main

Transformer-based models have demonstrated outstanding performance in natural language processing (NLP) tasks and many other domains, e.g., computer vision. Depending on the size of these models, which have grown exponentially in the past few years, machine learning practitioners might be restricted…

Cited by 3Source ↗PDF ↗code ↗Scholar ↗
2024

LoNAS: Elastic Low-Rank Adapters for Efficient Large Language Models

Juan Pablo Munoz, Jinjie Yuan, Yi Zheng, Nilesh Jain
COLING 2024main

Large Language Models (LLMs) continue to grow, reaching hundreds of billions of parameters and making it challenging for Deep Learning practitioners with resource-constrained systems to use them, e.g., fine-tuning these models for a downstream task of their interest. Adapters, such as low-rank adapt…

Cited by 13Source ↗PDF ↗code ↗Scholar ↗
2024

SQFT: Low-cost Model Adaptation in Low-precision Sparse Foundation Models

Juan Pablo Munoz, Jinjie Yuan, Nilesh Jain
EMNLP 2024finding

Large pre-trained models (LPMs), such as large language models, have become ubiquitous and are employed in many applications. These models are often adapted to a desired domain or downstream task through a fine-tuning stage. This paper proposes SQFT, an end-to-end solution for low-precision sparse p…

Cited by 3Source ↗PDF ↗code ↗Scholar ↗
2024

Shears: Unstructured Sparsity with Neural Low-rank Adapter Search

J. Pablo Muñoz, Jinjie Yuan, Nilesh Jain
NAACL 2024industry

Recently, several approaches successfully demonstrated that weight-sharing Neural Architecture Search (NAS) can effectively explore a search space of elastic low-rank adapters (LoRA), allowing the parameter-efficient fine-tuning (PEFT) and compression of large language models. In this paper, we intr…

Cited by 11Source ↗PDF ↗code ↗Scholar ↗
2024

Textual-Visual Logic Challenge: Understanding and Reasoning in Text-to-Image Generation

Peixi Xiong*, Michael A Kozuch, Nilesh Jain
ECCV 2024poster

"Text-to-image generation plays a pivotal role in computer vision and natural language processing by translating textual descriptions into visual representations. However, understanding complex relations in detailed text prompts filled with rich relational content remains a significant challenge. To…

Cited by 0Source ↗PDF ↗code ↗Scholar ↗
2022

EZNAS: Evolving Zero-Cost Proxies For Neural Architecture Scoring

Yash Akhauri, Juan Pablo Munoz, Nilesh Jain, Ravishankar Iyer
NeurIPS 2022accept

Neural Architecture Search (NAS) has significantly improved productivity in the design and deployment of neural networks (NN). As NAS typically evaluates multiple models by training them partially or completely, the improved productivity comes at the cost of significant carbon footprint. To alleviat…

Cited by 14Source ↗PDF ↗Scholar ↗