Semantic Mutual Information
No mentions found
This entity hasn't been tracked yet, or Iris is still building its knowledge base.
Related Articles from SNS
SMI: Efficient Self-Supervised Learning via Mutual-Information-Inspired Dependency Optimization
Announce Type: new Abstract: Self-supervised learning (SSL) has achieved remarkable representation learning performance, but many existing methods rely on large batch sizes, memory banks, momentum encoders, or global synchronization mechanisms that substantially increase computational cost and training complexity. In this work, we propose Semantic Mutual Information (SMI), a lightweight self-supervised objective derived from a mutual-information-inspired dependency formulation under Gaussian...
Operationalizing Linguistic Methods through Prompt-Engineering Skills: An Automatic Chinese Web Neologism Detection Pipeline
Announce Type: new Abstract: We present a method for automatic Chinese web neologism detection that operationalizes traditional linguistic identification principles as prompt-engineering skills. The method has four stages: tokenizer-independent character n-gram candidate generation; dictionary anchoring with a Pointwise Mutual Information pre-filter; a well-formedness skill based on Chinese word-formation principles; and a combined rule and three-way classification skill that distinguishes...
Rethinking Multimodal Few-Shot 3D Point Cloud Segmentation: From Fused Refinement to Decoupled Arbitration
Announce Type: replace Abstract: In this paper, we revisit multimodal few-shot 3D point cloud semantic segmentation (FS-PCS), identifying a conflict in "Fuse-then-Refine" paradigms: the "Plasticity-Stability Dilemma." In addition, CLIP's inter-class confusion can result in semantic blindness. To address these issues, we present the Decoupled-experts Arbitration Few-Shot SegNet (DA-FSS), a model that effectively distinguishes between semantic and geometric paths and mutually regularizes their...
Fully Spiking Neural Networks with Target Awareness for Energy-Efficient UAV Tracking
Announce Type: replace Abstract: Spiking Neural Networks (SNNs), characterized by their event-driven computation and low power consumption, have shown great potential for energy-efficient visual tracking on unmanned aerial vehicles (UAVs). However, existing SNN-based trackers often rely on costly event cameras, which limits their deployment on standard RGB-camera UAV platforms.
Selective Coupling of Decoupled Informative Regions: Masked Attention Alignment for Data-Free Quantization of Vision Transformers
arXiv:2606.04373v1 Announce Type: new Abstract: Data-Free Quantization (DFQ) addresses data security concerns by synthesizing samples, without accessing real data. It has garnered increasing attention in the context of Vision Transformers (ViTs), owing to the superiority of the self-attention mechanism compared to classical convolutional operation. However, previous DFQ arts for ViTs often suffer from a distribution mismatch between synthetic samples and input distribution expected by...
Selective Coupling of Decoupled Informative Regions: Masked Attention Alignment for Data-Free Quantization of Vision Transformers
arXiv:2606.04373v2 Announce Type: replace Abstract: Data-Free Quantization (DFQ) addresses data security concerns by synthesizing samples, without accessing real data. It has garnered increasing attention in the context of Vision Transformers (ViTs), owing to the superiority of the self-attention mechanism compared to classical convolutional operation. However, previous DFQ arts for ViTs often suffer from a distribution mismatch between synthetic samples and input distribution expected by...
Enhancing Video Representations with Spatiotemporal-Semantic Residual to Mitigate Hallucinations in Video Large Multimodal Models
arXiv:2601.22574v2 Announce Type: replace Abstract: Although Video Large Multimodal Models have achieved strong performance in video understanding, they still suffer from hallucination. Existing inference-time intervention methods usually modify videos under the contrastive decoding framework, but their heuristic designs bring limited improvements and increase inference latency. To address these issues, we propose ViSSRes, an inference-time intervention method that enhances video...
UniRTL: Unifying Code and Graph for Robust RTL Representation Learning
arXiv:2605.31040v1 Announce Type: new Abstract: Developing effective representations for register transfer level (RTL) designs is crucial for accelerating the hardware design workflow. Existing approaches, however, typically rely on a single data modality, either the RTL code or its associated graph-based representation, limiting the expressiveness and generalization ability of the learned representations. For RTL, the control data flow graph (CDFG) offers a comprehensive structural...
NILC: Discovering New Intents with LLM-assisted Clustering
Announce Type: replace Abstract: New intent discovery (NID) seeks to recognize both new and known intents from unlabeled user utterances, which finds prevalent use in practical dialogue systems. Existing works towards NID mainly adopt a cascaded architecture, wherein the first stage focuses on encoding the utterances into informative text embeddings beforehand, while the latter is to group similar embeddings into clusters (i.e., intents), typically by K-Means. However, such a cascaded...
You Don't Love Systemd Timers Enough
Figure 1: Plato's Cave by Jan Pietersz Saenredam; 24 hour clock licensed under CC3 from Wikimedia; systemd logo by the systemd project licensed under CC-BY-SA 4.0 My favorite metonymic technology term is "cron job": even though cron may not literally be the daemon that executes actions on a schedule, we apply the term to anything that walks like a cron and quacks like a cron . As Patrick McKenzie likes to point out, cron jobs are one of the most eminently useful computing primitives. They...