ICER is a black-box framework that addresses the gap in text-to-image models in harmful content generation through two components: an LLM-based rewriter that produces fluent, natural-language adversarial prompts, and in-context experience replay that accumulates successful jailbreaking patterns into a reusable prior.
Zhi-Yi Chin, Pin-Yu Chen, Wei-Chen Chiu et al.· 2 citations
This work introduces Projected Distribution Matching Distillation (PDMD) to filter critic errors, and shows how this projection stabilizes training and improves sample quality where DMD degrades and develops unnatural textures.
Zi-Mo Wang, Junkun Yuan, Ang-Tian Wang et al.· 0 citations
MT-OPSD is proposed, an on-policy self-distillation framework that trains the model on self-generated conditioning states with editing supervision from a clean-conditioned teacher, without requiring multi-turn annotations, and substantially improves long-horizon editing success and reduces multi-turn collapse.
Liang-Bing Zhao, Le Zhuo, Mohamed Elhoseiny· 0 citations
The results show that the value of pixel reconstruction depends on where discriminative signal lies in the input, which predicts that objectives preserving high-variance pixel content will transfer best.
Carlos Garrido-Munoz, Jorge Calvo-Zaragoza· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
It is suggested that linking a model's internal features to its errors and their effects on performance may help select training images that improve performance, thereby allowing the model's current state to guide which images are labeled next.
Yushi Nakaya, K. Higuchi, Shuichi Ishida· 0 citations
This work introduces REPI, a training framework based on a scaffold-to-internalization strategy, in which projected encoder representations initially serve as a temporary scaffold and are then progressively internalized by the diffusion transformer.
Han-Si Fu, Jia-Cheng Chen, Bao-Quan Zhao et al.· 0 citations
AnswerMap is introduced, a training-free, task-agnostic, black-box visual rationale constructed from the output head that offers a new lens on VLM interpretability and, through its read-outs, a new output interface for visual tasks beyond text tokens.
Mohamed Eltahir, Fardows Adam, Duaa M. Tahir et al.· 0 citations
Braco is a lightweight four-step coder that combines transform-basis truncation, input-independent basis-coordinate embeddings, budget-dependent orthogonal re-parameterization, and learned spatial residual tokens from lightweight pooling that forms the favorable empirical accuracy-efficiency frontier under compression.
Rui-Lian Zhong, Yu Li, Zhe-Yu Yan et al.· 0 citations
Post-training foundation video models on heterogeneous reward-weighted data usually assume that all data categories induce compatible updates. This assumption is fragile when categories correspond to different skills, domains, or evaluation dimensions. We study this problem in text-to-video post-training, where VBench2...
Jia Song (The Hong Kong University of Science and Technology), Wenhow Li (The Hong Kong University of Science and Technology), Lichen Bai (The Hong Kong University of Science and Technology) et al.· 0 citations
Deepfake detection methods have become increasingly effective yet most provide limited insight into the evidence behind their predictions. However, in forensic settings users also need to know which manipulation cues support the decision and where they appear. Existing explainability methods only partially address this...
Georgios Tsoumplekas, Vazgken Vanian, Alexandros Doumanoglou et al.· 0 citations
It is found that applying textual guidance too early can limit its ability to identify answer-relevant visual regions, whereas text-to-visual attention becomes more informative at intermediate decoder depths.
Min-Chan Kang, Kyeonghye Park, Seoyoung Cho et al.· 0 citations
A small detector is trained to predict the internal development of answer readiness and stop reasoning at that point, connecting the internal development of answer readiness to a practical rule for allocating reasoning computation.
Professor Paris Smaragdis develops computers with superhuman hearing for applications like speech recognition, music understanding, and environmental monitoring.
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.
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
