5 citations · 7 across the 8 of their papers we have counts for
10 papers
ReaDiT Guidance: Control for Image and Video Generation using Diffusion Transformer Features
Jay Mahajan, Chang Liu, Rauf Makharov +3
We present DiT Readout (ReaDiT) Guidance, a lightweight framework for controlling generation with Diffusion Transformer (DiT) models via their internal feature representations. Rea…
Learning Physics-Guided Residual Dynamics for Deformable Object Simulation
Shivansh Patel, Kaifeng Zhang, Sanjay Pokkali +2
Simulating deformable objects is essential for a wide range of robotic manipulation applications, yet accurately predicting their dynamics remains challenging. We propose Physics-G…
Generalizable VLA Finetuning via Representation Anchoring and Language-Action Alignment
Dwip Dalal, Shivansh Patel, Chahit Jain +8
Finetuning a pretrained vision-language model (VLM) on robot demonstrations via behavior cloning (BC) has become the standard recipe for vision-language-action (VLA) policies. Howe…
CRAFT: A Tendon-Driven Hand with Hybrid Hard-Soft Compliance
Leo Lin, Shivansh Patel, Jay Moon +2
We introduce CRAFT hand, a tendon-driven anthropomorphic hand with hybrid hard-soft compliance for contact-rich manipulation. The design is based on a simple idea: contact is not u…
Constructive Distortion: Improving MLLMs with Attention-Guided Image Warping
Dwip Dalal, Gautam Vashishtha, Utkarsh Mishra +6
Multimodal large language models (MLLMs) often miss small details and spatial relations in cluttered scenes, leading to errors in fine-grained perceptual grounding. We introduce At…
Robotic Manipulation by Imitating Generated Videos Without Physical Demonstrations
Shivansh Patel, Shraddhaa Mohan, Hanlin Mai +3
This work introduces Robots Imitating Generated Videos (RIGVid), a system that enables robots to perform complex manipulation tasks--such as pouring, wiping, and mixing--purely by…
A Real-to-Sim-to-Real Approach to Robotic Manipulation with VLM-Generated Iterative Keypoint Rewards
Shivansh Patel, Xinchen Yin, Wenlong Huang +5
Task specification for robotic manipulation in open-world environments is challenging, requiring flexible and adaptive objectives that align with human intentions and can evolve th…
UnZipLoRA: Separating Content and Style from a Single Image
Chang Liu, Viraj Shah, Aiyu Cui +1
This paper introduces UnZipLoRA, a method for decomposing an image into its constituent subject and style, represented as two distinct LoRAs (Low-Rank Adaptations). Unlike existing…
Street TryOn: Learning In-the-Wild Virtual Try-On from Unpaired Person Images
Aiyu Cui, Jay Mahajan, Viraj Shah +3
Most virtual try-on research is motivated to serve the fashion business by generating images to demonstrate garments on studio models at a lower cost. However, virtual try-on shoul…
ZipLoRA: Any Subject in Any Style by Effectively Merging LoRAs
Viraj Shah, Nataniel Ruiz, Forrester Cole +4
Methods for finetuning generative models for concept-driven personalization generally achieve strong results for subject-driven or style-driven generation. Recently, low-rank adapt…