5 citations · 6 across the 8 of their papers we have counts for
10 papers
EnvDreamer: Large-Scale Multimodal-to-Environment Generation for Embodied AI
Kabir Swain, Sijie Han, Antonio Torralba
Large datasets and high capacity models have accelerated progress in vision and language. This work introduces a platform aimed at bringing comparable gains to embodied learning, w…
Tensor Memory: Fixed-Size Recurrent State for Long-Horizon Transformers
Kabir Swain, Sijie Han, Daniel Karl I. Weidele +2
Transformers process images and videos by flattening space and time into long token sequences. While attention and KV caching preserve past features, their memory grows with sequen…
Hurwitz Quaternion Multiplicative Quantization for KV Cache Compression
Kabir Swain, Sijie Han, Daniel Karl I. Weidele +3
We propose \textbf{Hurwitz Quaternion Multiplicative Quantization (HQMQ)}, a \textbf{calibration-free} method for KV cache compression of large language models. HQMQ treats each 4-…
Vision-Language Binding in In-Context Image Generation
Chris Ge, Rohit Gandikota, Antonio Torralba +1
In-context image generation models such as FLUX.2 take a text prompt and an optional reference image as visual conditioning for the output. Internally, all three inputs -- text, re…
VideoSketcher: Sequential Sketch Generation Using Video Model Priors
Hui Ren, Yuval Alaluf, Omer Bar Tal +3
Sketching is inherently sequential: strokes are drawn progressively to explore and refine ideas. Yet most generative approaches treat sketches as static images, ignoring the tempor…
Motion Attribution for Video Generation
Xindi Wu, Despoina Paschalidou, Jun Gao +5
Despite the rapid progress of video generation models, the role of data in influencing motion is poorly understood. We present Motive (MOTIon attribution for Video gEneration), a m…
Feed-Forward Bullet-Time Reconstruction of Dynamic Scenes from Monocular Videos
Hanxue Liang, Jiawei Ren, Ashkan Mirzaei +8
Recent advancements in static feed-forward scene reconstruction have demonstrated significant progress in high-quality novel view synthesis. However, these models often struggle wi…
L4GM: Large 4D Gaussian Reconstruction Model
Jiawei Ren, Kevin Xie, Ashkan Mirzaei +8
We present L4GM, the first 4D Large Reconstruction Model that produces animated objects from a single-view video input -- in a single feed-forward pass that takes only a second. Ke…
LATTE3D: Large-scale Amortized Text-To-Enhanced3D Synthesis
Kevin Xie, Jonathan Lorraine, Tianshi Cao +5
Recent text-to-3D generation approaches produce impressive 3D results but require time-consuming optimization that can take up to an hour per prompt. Amortized methods like ATT3D o…
Align Your Gaussians: Text-to-4D with Dynamic 3D Gaussians and Composed Diffusion Models
Huan Ling, Seung Wook Kim, Antonio Torralba +2
Text-guided diffusion models have revolutionized image and video generation and have also been successfully used for optimization-based 3D object synthesis. Here, we instead focus…