81 citations · 150 across the 48 of their papers we have counts for
54 papers
FOCUS: From Privileged States to RGB-D with Controlled Modality Switching and Representation Alignment
Filip Grigorov, Kourosh Darvish, Nandita Vijaykumar
Vision-based reinforcement learning for robotic manipulation is sample-inefficient because RGB-D observations are high-dimensional and noisy. Privileged state information available…
Activation Sparsity with Weight Approximation for Faster LLM Decoding on Offloaded Weights
JuneHyung Kim, Sankeerth Durvasula, Nandita Vijaykumar
Deploying LLMs on consumer-grade GPUs with insufficient memory to hold their weights can result in prohibitively slow inference, because decoding repeatedly transfers offloaded wei…
KerColle: Unlocking Fine-Grained GPU Concurrency in Vision-Language-Action Models
Anna Li, Christina Giannoula, Nandita Vijaykumar
Vision-Language-Action (VLA) models have emerged as foundational models for next-generation robotics. High VLA inference throughput is critical for meeting the control-rate require…
zkComposer: Decomposing Proof Construction to Scale zkML
Pawan Kumar Sanjaya, Christina Giannoula, Valdy Oktavian +4
Zero-knowledge machine learning (zkML) enables a server to perform verifiable inference while keeping model parameters private from the client. However, existing zkML systems incur…
DataGuard: Guaranteeing Private Training in Systolic-array Based Accelerators
Pawan Kumar Sanjaya, Christina Giannoula, Nikhil Shreekumar +6
Differential privacy (DP) and federated learning (FL) have emerged as important privacy-preserving approaches when using sensitive data to train machine learning (ML) models. FL en…
QPILOTS: Efficient Test-Time Q-Steering for Flow Policies
Yifan Ruan, Chenyang Cao, Andreas Burger +7
Flow-matching and diffusion policies are expressive action generators, but optimizing them with temporal-difference reinforcement learning (RL) remains difficult. Effective policy…
XPR: An Extensible Cross-Platform Point-Based Differentiable Renderer
Steve Rhyner, Sankeerth Durvasula, Aleksandr Kovalev +7
Point-based differentiable rendering underpins modern 3D reconstruction, novel-view synthesis, and learning-based graphics pipelines, but developing new rendering methods often req…
SpecBench: Evaluating Specification-Level Reasoning for Software Engineering LLM Agents
Grant Hamblin, Kevin Song, Zhanda Zhu +4
Software engineering (SWE) agents are transitioning from code generation to full software development lifecycle automation. A critical phase in this lifecycle is specification desi…
Sparse Code Uplifting for Efficient 3D Language Gaussian Splatting
Lovre Antonio Budimir, Yushi Guan, Steve Ryhner +2
3D Language Gaussian Splatting (3DLGS) augments 3D Gaussian Splatting with language-aligned visual features for open-vocabulary 3D scene understanding. A core challenge is efficien…
TuneShift-KD: Knowledge Distillation and Transfer for Fine-tuned Models
Yushi Guan, Jeanine Ohene-Agyei, Daniel Kwan +3
To embed domain-specific or specialized knowledge into pre-trained foundation models, fine-tuning using techniques such as parameter efficient fine-tuning (e.g. LoRA) is a common p…
MERG3R: A Divide-and-Conquer Approach to Large-Scale Neural Visual Geometry
Leo Kaixuan Cheng, Abdus Shaikh, Ruofan Liang +3
Recent advancements in neural visual geometry, including transformer-based models such as VGGT and Pi3, have achieved impressive accuracy on 3D reconstruction tasks. However, their…
CRAFT: Fine-Grained Cost-Aware Expert Replication For Efficient Mixture-of-Experts Serving
Adrian Zhao, Zhenkun Cai, Zhenyu Song +5
Mixture-of-Experts (MoE) has recently emerged as the mainstream architecture for efficiently scaling large language models while maintaining near-constant computational cost. Exper…
LuxRemix: Lighting Decomposition and Remixing for Indoor Scenes
Ruofan Liang, Norman Müller, Ethan Weber +4
We present a novel approach for interactive light editing in indoor scenes from a single multi-view scene capture. Our method leverages a generative image-based light decomposition…
AccelOpt: A Self-Improving LLM Agentic System for AI Accelerator Kernel Optimization
Genghan Zhang, Shaowei Zhu, Anjiang Wei +6
We present AccelOpt, a self-improving large language model (LLM) agentic system that autonomously optimizes kernels for emerging AI acclerators, eliminating the need for expert-pro…
DEQuify your force field: More efficient simulations using deep equilibrium models
Andreas Burger, Luca Thiede, Alán Aspuru-Guzik +1
Machine learning force fields show great promise in enabling more accurate molecular dynamics simulations compared to manually derived ones. Much of the progress in recent years wa…
ContraGS: Codebook-Condensed and Trainable Gaussian Splatting for Fast, Memory-Efficient Reconstruction
Sankeerth Durvasula, Sharanshangar Muhunthan, Zain Moustafa +7
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 ach…
LuxDiT: Lighting Estimation with Video Diffusion Transformer
Ruofan Liang, Kai He, Zan Gojcic +4
Estimating scene lighting from a single image or video remains a longstanding challenge in computer vision and graphics. Learning-based approaches are constrained by the scarcity o…
HIP: Hessian Interatomic Potentials without derivatives
Andreas Burger, Luca Thiede, Nikolaj Rønne +5
Molecular Hessians, the second derivatives of the potential energy, are fundamental to many workflows in computational chemistry. Usually, accurate Hessians are computationally exp…
FG-Attn: Leveraging Fine-Grained Sparse Attention in Video Diffusion Models
Sankeerth Durvasula, Kavya Sreedhar, Zain Moustafa +6
Using diffusion transformers for media generation may require evaluating attention over extremely long sequences, with attention layers accounting for the majority of generation la…
DPQuant: Efficient and Differentially-Private Model Training via Dynamic Quantization Scheduling
Yubo Gao, Renbo Tu, Gennady Pekhimenko +1
Differentially-Private SGD (DP-SGD) and its adaptive variant DP-Adam are powerful techniques to protect user privacy when using sensitive data to train neural networks. During trai…
UniRelight: Learning Joint Decomposition and Synthesis for Video Relighting
Kai He, Ruofan Liang, Jacob Munkberg +7
We address the challenge of relighting a single image or video, a task that demands precise scene intrinsic understanding and high-quality light transport synthesis. Existing end-t…
Squeeze3D: Extreme Neural Compression with Latent Space Bridging
Rishit Dagli, Yushi Guan, Sankeerth Durvasula +2
We propose Squeeze3D, a novel framework that leverages implicit prior knowledge learnt by existing pre-trained encoders and decoders to compress 3D data at extremely high compressi…
INRet: A General Framework for Accurate Retrieval of INRs for Shapes
Yushi Guan, Daniel Kwan, Ruofan Liang +4
Implicit neural representations (INRs) have become an important method for encoding various data types, such as 3D objects or scenes, images, and videos. They have proven to be par…
DiffusionRenderer: Neural Inverse and Forward Rendering with Video Diffusion Models
Ruofan Liang, Zan Gojcic, Huan Ling +8
Understanding and modeling lighting effects are fundamental tasks in computer vision and graphics. Classic physically-based rendering (PBR) accurately simulates the light transport…