Near-infrared (NIR) imaging does not consistently outperform standard color cameras for daytime agricultural traversability once spatial data leakage is eliminated. Prior benchmarks suggesting an NIR advantage used sequence-level splits that permitted spatially autocorrelated imagery into test sets, artificially inflat...
Generating human-centric videos that preserve both visual identity and person-specific expressive behavior remains a fundamental challenge. In addition to reproducing appearance, a model must replicate the facial behaviors that characterize how a subject expresses emotion over time. However, most state-of-the-art metho...
Pokrzywa Baptiste, Nabyl Quignon, Yara Bahram et al.· 0 citations
This work presents TryOnReward, a fine-grained reward model tailored for VTON that significantly outperforms generic judges in human preference alignment, and when serving as the RFT reward function, it consistently yields human-preferred try-on results across multiple baselines.
Xue-Heng Li, Yong Liu, Xiao-Long Fu et al.· 0 citations
The Compute-Value Audit (CVA) is introduced, a sequential framework that asks whether extra sampling creates opportunity, observable signals provide a reliable state, that state supports a beneficial action, and the resulting gain exceeds the full entry fee of generation and verification.
Bistable images such as the duck-rabbit are classic stimuli in which one image supports multiple mutually incompatible interpretations, typically reported one at a time in humans. We ask whether multimodal large language models (MLLMs) show similar report behavior and what internal computations support it. Using the LL...
Ryota Takatsuki, Tomoki Doi, Amane Watahiki et al.· 0 citations
Multimodal large language models (MLLMs) cannot process every frame of a long video because of limitations in visual-token and computational budgets. Three primary approaches have been proposed to enhance their long-video understanding capabilities: (i) Retraining an MLLM on a large video corpus and/or extending its in...
This survey traces the evolution from LM-driven SemCom to TokenCom, and examines the token abstraction, the transmission techniques it requires, and two emerging paradigms, namely TokenCom for LM services and for embodied and agentic intelligence.
Voxel-spacing-aware extraction separates geometric modeling from interpolation-induced signal modification while preserving the native image signal, offering a coherent alternative to isotropic resampling for radiomic analysis of anisotropic CT and MRI.
David Corral Fontecha, J. M. Bautista, P. Fernández-Miranda et al.· arXiv.org· 0 citations
Overall, test-time augmentation over a small set of known rotations is the most consistent driver of accuracy, whereas the best-performing representation is strongly backbone-dependent, whereas the best-performing representation is strongly backbone-dependent.
Felix Schmalzel, Reimar Waitz, Moritz Kronberger et al.· 0 citations
This submission to the MedReason 2026 challenge is described, covering multiple-choice (MCQ) and open-ended (OE) medical visual question answering (VQA) under fully offline, containerized inference, and it is found that MCQ retrieval must compare answer \emph{semantics} rather than answer labels.
RSIAgent is introduced, a training-free multi-agent framework for recursive self-improvement through autonomous memory construction that substantially improves strong open-source models, enabling Kimi-K3 and GLM-5.3 to outperform frontier closed-source models including GPT-6.3.
Sibo Zhu, Shi-Cheng Fan, Xin-Yue Wang et al.· 5 citations
A Kinematics-Aware Decoupled Learning Network for robust 3D hand pose estimation and a task-decoupled hierarchical multitask framework, which separates 2D joint localization from depth estimation and incorporates a dedicated multitask learning strategy for depth regression.
Jun Lu, Zhen-Ming Chen, Lin Chen 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.
