Category: News

NVIDIA AI releases C-RADIOv4 vision backbone unifying SigLIP2, DINOv3, SAM3 for classification, dense prediction, segmentation workloads at scaleMarkTechPost How do you combine SigLIP2, DINOv3, and SAM3 into a single vision backbone without sacrificing dense or segmentation performance? NVIDIA’s C-RADIOv4 is a new agglomerative vision backbone that distills three strong teacher models, SigLIP2-g-384, DINOv3-7B, and SAM3, into a single student encoder. It extends the AM-RADIO and RADIOv2.5 line, keeping similar computational cost while improving
The post NVIDIA AI releases C-RADIOv4 vision backbone unifying SigLIP2, DINOv3, SAM3 for classification, dense prediction, segmentation workloads at scale appeared first on MarkTechPost.

 How do you combine SigLIP2, DINOv3, and SAM3 into a single vision backbone without sacrificing dense or segmentation performance? NVIDIA’s C-RADIOv4 is a new agglomerative vision backbone that distills three strong teacher models, SigLIP2-g-384, DINOv3-7B, and SAM3, into a single student encoder. It extends the AM-RADIO and RADIOv2.5 line, keeping similar computational cost while improving
The post NVIDIA AI releases C-RADIOv4 vision backbone unifying SigLIP2, DINOv3, SAM3 for classification, dense prediction, segmentation workloads at scale appeared first on MarkTechPost. Read More  

SkeletonGaussian: Editable 4D Generation through Gaussian Skeletonizationcs.AI updates on arXiv.org arXiv:2602.04271v1 Announce Type: cross
Abstract: 4D generation has made remarkable progress in synthesizing dynamic 3D objects from input text, images, or videos. However, existing methods often represent motion as an implicit deformation field, which limits direct control and editability. To address this issue, we propose SkeletonGaussian, a novel framework for generating editable dynamic 3D Gaussians from monocular video input. Our approach introduces a hierarchical articulated representation that decomposes motion into sparse rigid motion explicitly driven by a skeleton and fine-grained non-rigid motion. Concretely, we extract a robust skeleton and drive rigid motion via linear blend skinning, followed by a hexplane-based refinement for non-rigid deformations, enhancing interpretability and editability. Experimental results demonstrate that SkeletonGaussian surpasses existing methods in generation quality while enabling intuitive motion editing, establishing a new paradigm for editable 4D generation. Project page: https://wusar.github.io/projects/skeletongaussian/

 arXiv:2602.04271v1 Announce Type: cross
Abstract: 4D generation has made remarkable progress in synthesizing dynamic 3D objects from input text, images, or videos. However, existing methods often represent motion as an implicit deformation field, which limits direct control and editability. To address this issue, we propose SkeletonGaussian, a novel framework for generating editable dynamic 3D Gaussians from monocular video input. Our approach introduces a hierarchical articulated representation that decomposes motion into sparse rigid motion explicitly driven by a skeleton and fine-grained non-rigid motion. Concretely, we extract a robust skeleton and drive rigid motion via linear blend skinning, followed by a hexplane-based refinement for non-rigid deformations, enhancing interpretability and editability. Experimental results demonstrate that SkeletonGaussian surpasses existing methods in generation quality while enabling intuitive motion editing, establishing a new paradigm for editable 4D generation. Project page: https://wusar.github.io/projects/skeletongaussian/ Read More  

SCALE: Self-uncertainty Conditioned Adaptive Looking and Execution for Vision-Language-Action Modelscs.AI updates on arXiv.org arXiv:2602.04208v1 Announce Type: cross
Abstract: Vision-Language-Action (VLA) models have emerged as a promising paradigm for general-purpose robotic control, with test-time scaling (TTS) gaining attention to enhance robustness beyond training. However, existing TTS methods for VLAs require additional training, verifiers, and multiple forward passes, making them impractical for deployment. Moreover, they intervene only at action decoding while keeping visual representations fixed-insufficient under perceptual ambiguity, where reconsidering how to perceive is as important as deciding what to do. To address these limitations, we propose SCALE, a simple inference strategy that jointly modulates visual perception and action based on ‘self-uncertainty’, inspired by uncertainty-driven exploration in Active Inference theory-requiring no additional training, no verifier, and only a single forward pass. SCALE broadens exploration in both perception and action under high uncertainty, while focusing on exploitation when confident-enabling adaptive execution across varying conditions. Experiments on simulated and real-world benchmarks demonstrate that SCALE improves state-of-the-art VLAs and outperforms existing TTS methods while maintaining single-pass efficiency.

 arXiv:2602.04208v1 Announce Type: cross
Abstract: Vision-Language-Action (VLA) models have emerged as a promising paradigm for general-purpose robotic control, with test-time scaling (TTS) gaining attention to enhance robustness beyond training. However, existing TTS methods for VLAs require additional training, verifiers, and multiple forward passes, making them impractical for deployment. Moreover, they intervene only at action decoding while keeping visual representations fixed-insufficient under perceptual ambiguity, where reconsidering how to perceive is as important as deciding what to do. To address these limitations, we propose SCALE, a simple inference strategy that jointly modulates visual perception and action based on ‘self-uncertainty’, inspired by uncertainty-driven exploration in Active Inference theory-requiring no additional training, no verifier, and only a single forward pass. SCALE broadens exploration in both perception and action under high uncertainty, while focusing on exploitation when confident-enabling adaptive execution across varying conditions. Experiments on simulated and real-world benchmarks demonstrate that SCALE improves state-of-the-art VLAs and outperforms existing TTS methods while maintaining single-pass efficiency. Read More  

DeFrame: Debiasing Large Language Models Against Framing Effectscs.AI updates on arXiv.org arXiv:2602.04306v1 Announce Type: cross
Abstract: As large language models (LLMs) are increasingly deployed in real-world applications, ensuring their fair responses across demographics has become crucial. Despite many efforts, an ongoing challenge is hidden bias: LLMs appear fair under standard evaluations, but can produce biased responses outside those evaluation settings. In this paper, we identify framing — differences in how semantically equivalent prompts are expressed (e.g., “A is better than B” vs. “B is worse than A”) — as an underexplored contributor to this gap. We first introduce the concept of “framing disparity” to quantify the impact of framing on fairness evaluation. By augmenting fairness evaluation benchmarks with alternative framings, we find that (1) fairness scores vary significantly with framing and (2) existing debiasing methods improve overall (i.e., frame-averaged) fairness, but often fail to reduce framing-induced disparities. To address this, we propose a framing-aware debiasing method that encourages LLMs to be more consistent across framings. Experiments demonstrate that our approach reduces overall bias and improves robustness against framing disparities, enabling LLMs to produce fairer and more consistent responses.

 arXiv:2602.04306v1 Announce Type: cross
Abstract: As large language models (LLMs) are increasingly deployed in real-world applications, ensuring their fair responses across demographics has become crucial. Despite many efforts, an ongoing challenge is hidden bias: LLMs appear fair under standard evaluations, but can produce biased responses outside those evaluation settings. In this paper, we identify framing — differences in how semantically equivalent prompts are expressed (e.g., “A is better than B” vs. “B is worse than A”) — as an underexplored contributor to this gap. We first introduce the concept of “framing disparity” to quantify the impact of framing on fairness evaluation. By augmenting fairness evaluation benchmarks with alternative framings, we find that (1) fairness scores vary significantly with framing and (2) existing debiasing methods improve overall (i.e., frame-averaged) fairness, but often fail to reduce framing-induced disparities. To address this, we propose a framing-aware debiasing method that encourages LLMs to be more consistent across framings. Experiments demonstrate that our approach reduces overall bias and improves robustness against framing disparities, enabling LLMs to produce fairer and more consistent responses. Read More