This work proposes HiLo-Token, an input-adaptive token compression framework that allocates more token budget to high-frequency, rich-context regions while assigning fewer tokens to low-frequency areas, and introduces a simple yet effective high-frequency token selection strategy based on spatial frequency.
This work introduces SUPREME, an open-source framework that distributes these stages across multiple GPUs and makes three contributions: a registry-based design for adding new methods, metrics, models, and scenarios; a multi-GPU architecture supporting multiple accelerators and precision modes.
P. Andreou, J. Lanyon, Axel Finke et al.· arXiv.org· 0 citations
A criterion-agnostic signal-validation framework based on Kendall's $\tau$, majority-vote probability, and Condorcet cycles against exact iid-uniform nulls; the analysis reveals significant but moderate designer agreement, with every TASTE criterion rejecting the random-rater null.
Hao-Nan Zhu, Elad Hirsch, A. Minetti et al.· arXiv.org· 0 citations
This study tackles Generalized Category Discovery via a Relational Retrieval perspective, explicitly coupling labeled and unlabeled data through bidirectional knowledge transfer, and proposes Relational Pattern Consistency (RPC) that enables mutual enhancement.
Yulin Xu, Chunqi Guo, Yuanzhen Shuai et al.· International Conference on...· 3 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
Semi-DPO is proposed, a semi-supervised approach that treats consistent pairs as clean labeled data and conflicting ones as noisy unlabeled data and significantly improves alignment with complex human preferences, without requiring additional human annotation or explicit reward models during training.
Xinxing Liu, Ming Li, Zonglin Lyu et al.· arXiv.org· 5 citations
This paper introduces an Neighborhood-Aware Anchor Pruning (NAAP) strategy, which evaluates anchor importance via weighted neighborhood feature aggregation and then merges low-contribution anchors into salient neighbors, yielding a compact yet geometry-consistent anchor set.
X. Deng, Xian-Dong Meng, Hengyu Man et al.· arXiv.org· 0 citations
Human identity-preserving text-to-video generation remains challenging under large changes in viewpoint, facial expression, illumination, and motion. Existing methods condition the generator on a single reference portrait, but a static image cannot capture how identity-bearing cues evolve across views and expressions,...
The GameHorizon Suite, a unified data and evaluation suite that measures gameplay capabilities at different horizons for diverse model families, can provide a standardized yardstick for evaluating gameplay capabilities across horizons and model families.
Yi-Ran Wang, Xingyilang Yin, Junfu Pu et al.· 0 citations
WorldCrafter is a video world model that learns a camera-queryable implicit 3D-aware memory that enables streaming scene exploration from a single input image or text prompt and shows substantial gains in long-horizon consistency and camera-control accuracy while preserving visual quality during minute-scale exploratio...
Wang-Bo Yu, Kun-Hao Liu, Wen-Bo Hu et al.· 3 citations
A visuo-tactile WAM that encodes each fingertip independently, aggregates the resulting features through a finger- and pose-aware tactile compressor, and injects the tactile latent into a video diffusion world model for joint visuo-tactile world modeling is presented.
Hao-Ran Yuan, Ze-Kai Wang, Bo-Ning Shao et al.· 1 citation
Pr PrismGPT, a Vision-Language Model (VLM) framework that produces structured, region-aware editing plans from a single input image without relying on commercial black-box tools is presented.
Ke Zhao, Hue Nguyen, Abhijith Punnappurath et al.· 0 citations
Latent diffusion models now dominate medical image generation, and every such pipeline rests on a \emph{tokenizer} that compresses images into the latent codes for image generation to operate on. Thereby, the tokenizer choice bounds every downstream task from reconstruction fidelity and generation quality to the repres...
Niklas Bubeck, Yundi Zhang, Vasiliki Sideri-Lampretsa et al.· 0 citations
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.
