Quantization plays a crucial role in efficiently deploying deep learning models on resource-constrained devices. Post-training quantization does not require access to the original dataset or retraining the full model. Current methods that achieve high performance close to baseline results typically require INT8 fixed-p...
Reem Abdel-Salam, Ahmed H. Abdel-Gawad, Amr G. Wassal· 0 citations
Accurate and efficient analysis of dental radiographs has become increasingly important for disease diagnosis and clinical decision making. In particular, dental radiographs segmentation plays a critical role as it is challenging due to several reasons, such as low contrast, noise in the images, variations in the image...
Reinforcement learning (RL) is promising for spatial text-to-image generation, but existing work largely focuses on policy optimization, assuming accurate rewards and effective online rollouts. We observe in-domain gains with out-of-domain degradation, exposing two limitations: unreliable spatial rewards in open-world...
Xiaofeng Tan, Jia-Xin Lin, Haobo Yuan et al.· 0 citations
End-to-end driving policies can achieve strong task performance while offering limited control over their driving style. Driving style describes how a vehicle accelerates, brakes, and maintains distance. Policies trained without explicit preference conditioning lack a direct mechanism for adjusting these behaviors at i...
Guan-Tian Zheng, Li-Dong Yu, Tian-Yu Gao et al.· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
Autoregressive video generators synthesize long videos through chunk-wise rollouts, yet they are typically trained to predict only the immediate future. This limited prediction horizon makes it challenging to maintain video quality over extended rollouts. To address this problem, we introduce Prospective Forcing, a mul...
Yifan Shen, Yewei Xia, Gongxu Luo et al.· 0 citations
EarthAlign and MeteoLIP provide a foundation for learning and evaluating language-aligned representations of Earth system data and improve upon the corresponding CLIP and SigLIP baselines across three downstream tasks: cross-modal retrieval, weather-condition classification, and physical variable estimation.
F. Maani, N. Saeed, Jia-Qi W. Ma et al.· 0 citations
Diffusion models pose significant risks regarding the generation of illicit content and copyright violations. This has catalyzed the development of machine unlearning to erase harmful concepts or copyrighted styles from a model's generative repertoire without compromising its general performance. However, previous unle...
Yang Xiao, Kaiyuan Deng, Gen Li et al.· 0 citations
Large multimodal models (LMMs) need to understand how entities move and interact as a scene develops. This requires following the same entities over time and relating their observed motion to subsequent changes. We formulate Scene Evolution Understanding (SEU), a task for predicting and interpreting this change. Given...
Chaoyue Li, Shoudong Han, Haoyang Wu et al.· 0 citations
Augmenting worker capabilities in the physical world through guidance has been a decades-long goal for AI agents. One key supporting capability is to understand what the worker is doing, seeing through the human's camera or smart glasses, and assist them in documentation. Despite advances in vision language models, the...
Andrew Perrault, Anmol Takiar, Dominik Wienecki et al.· 0 citations
Accurate sampling from continuous-time generative models can require many model evaluations. Low-step sampling reduces cost, but coarse updates introduce endpoint errors that can accumulate and degrade generation quality. We introduce TraceSampler, a post-training method that corrects these errors without modifying the...
George Matthew (University of Exeter, United Kingdom), Guoqiang Zhang (University of Exeter et al.· 0 citations
Foundation models like V-JEPA are increasingly deployed across a heterogeneous edge-cloud continuum spanning smart glasses, phones, robots, and servers. Yet, they are typically trained as rigid, fixed-capacity networks bound to one device, supporting neither reconfigurable compute budgets nor collaborative execution. E...
Anxhelo Diko, Jieyu Lin, Stefano Ambrogio et al.· 0 citations
Reconstructing accurate camera poses and floor-plan layouts from sparse, unposed, wide-baseline RGB panoramas remains a challenging open problem. Direct multi-room floor-plan prediction is especially difficult in this setting: pose, geometry, semantics, and global layout structure are tightly coupled, yet a complete fl...
Yuguang Li, Yi-Chuan Deng, Zi-Xuan Liu et al.· 0 citations
Exploring how generative AI could make machine vision more accessible to businesses. The post GenEye in a Box: Making Machine Vision Something You Can Just Ask For appeared first on GPT-Lab.
Jennifer Neville did not want to go into computer science—but that’s exactly where she landed. Neville discusses the starts and stops that led to her professional sweet spot and her work identifying “surprising failures” making it hard for AI to handle complexity. The post What AI gets wrong and what failure teaches us appeared first on Microsoft Research.
Computer scientist, entrepreneur, and philanthropist will collaborate with the MIT Schwarzman College of Computing to advance AI and scientific discovery.
