Publications | Research

2025

Efficient Molecular Conformer Generation with SO(3)-Averaged Flow Matching and Reflow

Zhonglin Cao, Mario Geiger, Allan Dos Santos Costa, Danny Reidenbach, Karsten Kreis, Tomas Geffner, Franco Pellegrini, Guoqing Zhou, Emine Kucukbenli

ICML

Helix Parallelism: Rethinking Sharding Strategies for Interactive Multi-Million-Token LLM Decoding

Nidhi Bhatia, Ankit More, Ritika Borkar, Tiyasa Mitra, Ramon Matas, Ritchie Zhao, Maximilian Golub, Dheevatsa Mudigere, Brian Pharris, Bita Darvish Rouhani

Score-based Diffusion Models in Function Space

Jae Hyun Lim, Nikola Kovachki, Ricardo Baptista, Christopher Beckham, Kamyar Azizzadenesheli, Jean Kossaifi, Vikram Voleti, Jiaming Song, Karsten Kreis, Jan Kautz, Christopher Pal, Arash Vahdat, Anima Anandkumar

Spec2RTL-Agent: Automated Hardware Code Generation from Complex Specifications Using LLM Agent Systems

Zhongzhi Yu, Mingjie Liu, Michael Zimmer, Yingyan (Celine) Lin, Yong Liu, Mark Haoxing Ren

AssertionForge: Enhancing Formal Verification Assertion Generation with Structured Representation of Specifications and RTL

Yunsheng Bai, Ghaith Bany Hamad, Syed Suhaib, Mark Haoxing Ren

GauRast: Enhancing GPU Triangle Rasterizers to Accelerate 3D Gaussian Splatting

Sixu Li, Ben Keller, Yingyan Celine Lin, Brucek Khailany

GEM: GPU-Accelerated Emulator-Inspired RTL Simulation

Zizheng Guo, Yanqing Zhang, Mark Haoxing Ren

Best Paper Award Nomination at DAC, 2025

Towards a VLM Benchmark for Simulated Robotics

Xuning Yang, Clemens Eppner, Valts Blukis, Peter Belcak, Stephen Tyree, Stan Birchfield, Fabio Ramos, Jonathan Tremblay

Robot policy evaluation for sim-to-real transfer: A benchmarking perspective

Xuning Yang, Clemens Eppner, Jonathan Tremblay, Dieter Fox, Stan Birchfield, Fabio Ramos

Task-Based Tensor Computations on Modern GPUs

Rohan Yadav, Michael Garland, Alex Aiken, Michael Bauer

PLDI

FoundationStereo: Zero-Shot Stereo Matching

Bowen Wen, Matthew Trepte, Joseph Aribido, Jan Kautz, Orazio Gallo, Stan Birchfield

CVPR

Best Paper Nomination

Adapting to the Unknown: Training-Free Audio-Visual Event Perception with Dynamic Thresholds

Eitan Shaar, Ariel Shaulov, Gal Chechik, Lior Wolf

CVPR

RL-RC-DoT: A Block-level RL agent for Task-Aware Video Compression

Uri Gadot, Assaf Shocher, Shie Mannor, Gal Chechik, Assaf Hallak

CVPR

Make It Count: Text-to-Image Generation with an Accurate Number of Objects

Lital Binyamin, Yoad Tewel, Eran Hirsch, Royi Rassin, Gal Chechik

CVPR

TriTex: Learning Texture from a Single Mesh via Triplane Semantic Features

Dana Cohen-Bar, Daniel Cohen-Or, Gal Chechik, Yoni Kasten

CVPR

BLADE: Single-view Body Mesh Estimation through Accurate Depth Estimation

Shengze Wang, Jiefeng Li, Tianye Li, Ye Yuan, Henry Fuchs, Koki Nagano, Shalini De Mello, Michael Stengel

CVPR

Coherent 3D Portrait Video Reconstruction via Triplane Fusion

Shengze Wang, Xueting Li, Chao Liu, Matthew Chan, Michael Stengel, Henry Fuchs, Shalini De Mello, Koki Nagano

CVPR

SimAvatar: Simulation-Ready Clothed Gaussian Avatars from Text

Xueting Li, Ye Yuan, Shalini De Mello, Gilles Daviet, Jonathan Leaf, Miles Macklin, Jan Kautz, Umar Iqbal

CVPR

GRS: Generating robotic simulation tasks from real-world images

Alex Zook, Josef Spjut, Jonathan Tremblay

CVPR

A Generative AI Game Jam Case Study from October 2024

Josef Spjut

CVPR

MambaVision: A Hybrid Mamba-Transformer Vision Backbone

Ali Hatamizadeh, Jan Kautz

CVPR

Marco: Configurable Graph-Based Task Solving and Multi-AI Agents Framework for Hardware Design

Chia-Tung (Mark) Ho, Jing Gong, Yunsheng Bai, Chenhui Deng, Mark Haoxing Ren, Brucek Khailany

Beyond the Buzz: A Pragmatic Take on Inference Disaggregation

Tiyasa Mitra, Ritika Borkar, Nidhi Bhatia, Ramon Matas, Shivam Raj, Dheevatsa Mudigere, Ritchie Zhao, Maximilian Golub, Arpan Dutta, Sailaja Madduri, Dharmesh Jani, Brian Pharris, Bita Darvish Rouhani

SLIM: One-shot Quantization and Sparsity with Low-rank Approximation for LLM Weight Compression

Mohammad Mozaffari , Amir Yazdanbakhsh, Maryam Mehri Dehnavi