EEG-based visual decoding aims to establish a mapping between neural signals and visual semantics. However, it remains constrained by the dual challenges of severe information granularity mismatch and the low signal-to-noise ratio (SNR) of EEG signals. Existing approaches typically treat visual features as static, igno...
Fan Yin, Chuhang Zheng, Peiliang Gong et al.· 0 citations
Vision-Language-Action Models (VLAs) inherit their visual and linguistic capabilities from Vision-Language Models (VLMs), yet most VLAs are built from off-the-shelf VLMs that are not adapted to the embodied domain, limiting their downstream performance. In this work, we propose EmbodiedMidtrain to bridge the gap betwee...
Yiyang Du, Zhanqiu Guo, Haochen Zhang et al.· 0 citations
Recent diffusion-based models achieve photorealism in image inpainting but require many sampling steps, limiting practical use. Few-step text-to-image models offer faster generation, but naively applying them to inpainting yields poor harmonization and artifacts between the background and inpainted region. We trace thi...
Duc Vu, Kien Nguyen, Ngan Nguyen et al.· 0 citations
Model merging has shown that multitask models can be created by directly combining the parameters of different models that are each specialized on tasks of interest. However, models trained independently on distinct tasks often exhibit interference that degrades the merged model's performance. To solve this problem, we...
Pratik Ramesh, George Stoica, Arun Iyer et al.· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
Generalizable image-based person re-identification (Re-ID) aims to recognize individuals across cameras in unseen domains without retraining. While visual features are sensitive to domain shifts, natural language descriptions remain consistent across domains, regardless of lighting changes and other biases. Since well-...
Timur Mamedov, Karina Kvanchiani, Anton Konushin et al.· 0 citations
Image editing models can modify visual content through natural language, but editing dense documents requires precise local changes amid tightly coupled text, tables, and layout. We introduce VDE Bench, an evaluation resource for studying instruction-guided editing of Chinese and English document images. VDE Bench cont...
Hongzhu Yi, Yujia Yang, Yuanxiang Wang et al.· 0 citations
Large vision-language models (LVLMs) perform well on multimodal tasks, but their ability to reason and precisely align visual and textual information still has room for improvement. In this study, we show that external visual cues, such as symbols or grid lines, help LVLMs form more accurate connections between visual...
Amirmohammad Izadi, Hosein Hasani, Fatemeh Askari et al.· 0 citations
Few-shot fine-grained visual classification (FGVC) aims to discriminate between subtly different categories with very limited data. While Multimodal Large Language Models (MLLM) exhibit strong capabilities in both fine-grained visual understanding and open-world category recognition, directly fine-tuning them on few-sh...
Haiyun Guo, Hongyu Guo, Xiangzhao Hao et al.· 0 citations
Interest in generating realistic synthetic medical images has grown in recent years. Such datasets can mitigate the scarcity of public data for artificial intelligence research and support education. Work on synthesizing dental panoramic radiographs (PRs) has so far relied almost exclusively on generative adversarial n...
Sanyam Jain, Bruna Neves de Freitas, Andreas Basse-OConnor et al.· 0 citations
Digital note-taking is gaining popularity, offering a durable, editable, and easily indexable way of storing notes in a vectorized form, known as digital ink. However, a substantial gap remains between this way of note-taking and traditional pen-and-paper note-taking, a practice that is still favored by a vast majority...
Blagoj Mitrevski, Arina Rak, Julian Schnitzler et al.· 0 citations
T2-Z is introduced for test-time optimization of environment latents, which augments a robotic world model with a learnable environment latent to condition world predictions, and can efficiently infer environment latents from as little as a single test-time interaction trajectory.
Chen-Yuan Zhou, Yi-Ning Hong, Huang Huang et al.· 0 citations
Recent 3D world models increasingly use features from geometry foundation models (GFMs) as predictive world states, benefiting from their rich geometric priors. However, the view dependence of these features entangles scene dynamics with camera-induced variation, making the resulting state evolution harder to predict....
Hongchang Liu, Jian Liu, Yujuan Ding 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.
