Semantic
No mentions found
This entity hasn't been tracked yet, or Iris is still building its knowledge base.
Related Articles from SNS
Improving Semantic Uncertainty Quantification in LVLMs with Semantic Gaussian Processes
arXiv:2512.14177v3 Announce Type: replace Abstract: Large Vision-Language Models (LVLMs) often produce plausible but unreliable outputs, making robust uncertainty estimation essential. Recent work on semantic uncertainty estimates relies on external models to cluster multiple sampled responses and measure their semantic consistency. However, these clustering methods are often fragile, highly sensitive to minor phrasing variations, and can incorrectly group or separate semantically similar...
Learning a Semantic Calibration Network for Open-Vocabulary Semantic Segmentation
Announce Type: new Abstract: Semantic image segmentation assigns a predefined category label to each pixel, has achieved significant progress lately. Open-Vocabulary Segmentation (OVS) extends the segmentation task from a fixed set to an open set, enabling the identification and segmentation of novel concepts based on arbitrary text inputs, such as category names or descriptions. In this paper, we propose a novel Semantic Calibration Network (SCN) for open-vocabulary semantic segmentation.
DySem: Uncovering Dynamic Semantic Components of Large Language Models for Calculating Semantic Textual Similarity
Announce Type: replace Abstract: Calculating semantic textual similarity is a foundational task in natural language processing. Current large language models (LLMs) based methods typically rely on extracting last-layer hidden states with fixed dimensions to compute similarity for every text pairs. We argue that this paradigm is suffer from two limitations: (i) The last hidden layer encodes more general knowledge rather than just semantic knowledge, making it suboptimal for semantic...
Bridge the Last-Mile Gap to Semantic Analytics: Compiling Natural-Language Queries into Semantic Operator Pipelines
arXiv:2606.04641v1 Announce Type: new Abstract: Automated AI workflows increasingly rely on natural-language reasoning over heterogeneous data, but lack a practical way to execute it through optimized semantic data systems. Recent semantic operator systems, such as Palimpzest and LOTUS, expose declarative operators for filtering, joining, mapping, and aggregating over tables, text, and images using natural-language predicates. However, these systems require users to manually choose...
Cohort-based Semantic Labeling: AI-Enabled Recovery of Visualization Semantics from Deployed SVGs
arXiv:2606.09782v1 Announce Type: new Abstract: Many web-based visualizations are deployed as Scalable Vector Graphics (SVG), a format that faithfully preserves visual appearance but typically omits the higher-level semantic structure needed for machine interpretation. Once rendered and published, information about a visualization's components, roles, and encodings is no longer explicitly available, limiting downstream operations such as querying, accessibility augmentation, explanation,...
Semantic Foam: Unifying Spatial and Semantic Scene Decomposition
Announce Type: replace Abstract: Modern scene reconstruction methods, such as 3D Gaussian Splatting, deliver photo-realistic novel view synthesis at real-time speeds, yet their adoption in interactive graphics applications has been limited. A major bottleneck is the difficulty of interacting with these representations compared to traditional, human-authored 3D assets. While previous research has attempted to impose semantic decomposition on these models, significant challenges remain...
Shared Semantics, Divergent Mechanisms: Unsupervised Feature Discovery by Aligning Semantics and Mechanisms
Announce Type: new Abstract: As large language models are increasingly deployed in high-stakes settings, there is a growing need for tools that audit not only model outputs but also the internal computations that produce them. Circuit analysis is a central approach in mechanistic interpretability, but it is typically target-conditioned, explaining a single prompt paired with a chosen completion. This target-conditioned setup can obscure heterogeneity across a model's continuation distribution.
Larch: Learned Query Optimization for Semantic Predicates
Announce Type: new Abstract: With the advent of Large Language Models (LLMs), many database systems introduced semantic operators that enabled analytical queries over unstructured data (e.g. text, images, videos). Semantic operators typically incur high inference costs and latencies making semantic (AI) SQL queries challenging to apply on large scale datasets. At the same time, their semantic nature leads database engines to treat them as black boxes, making AISQL queries difficult to optimize.
Disambiguation of two-tone images reveals semantic contributions to object recognition in the EEG
Electrophysiological responses to visual objects carry information about stimulus identity and semantic category, but it remains difficult to know whether such information represents semantic knowledge or merely regularities in physical image features. Here, we presented two-tone images while recording EEG to dissociate the learned semantic concept from physical stimulus properties in the electrophysiological signal. Seventeen healthy participants completed a semantic disambiguation...
HybridCodec: Fast Dual-Stream, Semantically Enhanced Neural Audio Codec
arXiv:2606.06743v1 Announce Type: new Abstract: The popularity of neural audio codecs as speech tokenizers has surged with the advent of Multimodal Large Language Models. New codec architectures with semantic and acoustic disentanglement have emerged. There are two main approaches to introduce semantic information into codec models: one distills semantic information from SSL representations into the first RVQ layer, while the other maintains separate streams for semantic and acoustic features.