Codebook
No mentions found
This entity hasn't been tracked yet, or Iris is still building its knowledge base.
Related Articles from SNS
Non-Uniform Codebook Design for Optical IRS-Assisted VLC Systems
Announce Type: new Abstract: Optical intelligent reflecting surfaces (OIRS) can improve the coverage of indoor visible light communication (VLC) systems, however, practical deployment requires a finite offline codebook to avoid repeated real-time optimisation of mirror orientations. A uniform codebook with fixed angular steps does not provide uniform coverage on the user plane, because the mapping from steering angles to reflection locations on the user plane is nonlinear. To address this...
HiTokSR: A Coarse-to-Fine Tokenizer with Hierarchical Codebooks for High-Fidelity Real-World Image Super-Resolution
arXiv:2606.01157v1 Announce Type: new Abstract: Vector-quantized (VQ) generative models have shown promising results in real-world image super-resolution (Real-ISR). However, existing methods typically rely on a monolithic latent space that entangles low-frequency structures with high-frequency textures. This entanglement forces a single codebook to capture a combinatorially complex set of structure-texture pairings, which constrains representational capacity and limits codebook utilization.
When Better Codebooks Are Not Enough: Predictive Performance and Behavioral Reliability in LLM Political Event Coding
Announce Type: new Abstract: High accuracy does not necessarily make an LLM a faithful coder. This issue matters because many social-science studies rely on expert-written codebooks to turn text into structured data. We study this problem in political event coding, a challenging source-target relation classification task beyond ordinary sentence-level classification, where models must determine what one actor did to another using detailed coding rules.
AAAC: Activation-Aware Adaptive Codebooks for 4-bit LLM Weight Quantization
arXiv:2605.08692v2 Announce Type: replace Abstract: Post-training weight-only quantization to 4 bits is widely used to reduce the memory and compute costs of large language model inference. Existing PTQ methods, such as AWQ and GPTQ, improve how weights are mapped onto a fixed 4-bit grid through scaling, clipping, or error compensation. To further improve accuracy, methods such as OmniQuant and QuIP\# uses gradient-assisted algorithms at the cost of hours of quantization time.
Semantic Forwarding and Codebook-Enhanced Model Division Multiple Access for Satellite-Terrestrial Networks
arXiv:2603.02536v2 Announce Type: replace Abstract: Satellite-terrestrial communications are severely constrained by high path loss, limited spectrum resources, and time-varying channel conditions, rendering conventional bit-level transmission schemes inefficient and fragile, particularly in low signal-to-noise ratio (SNR) regimes. Semantic communication has emerged as a promising paradigm to address these challenges by prioritizing task-relevant information over exact bit recovery. In this...
CURP: Codebook-based Continuous User Representation for Personalized Generation with LLMs
arXiv:2602.00742v2 Announce Type: replace Abstract: User modeling characterizes individuals through their preferences and behavioral patterns to enable personalized simulation and generation with Large Language Models (LLMs) in contemporary approaches. However, existing methods, whether prompt-based or training-based methods, face challenges in balancing personalization quality against computational and data efficiency.
Distributional Open-Ended Evaluation of LLM Cultural Value Alignment Based on Value Codebook
arXiv:2604.06210v3 Announce Type: replace Abstract: As LLMs are globally deployed, aligning their cultural value orientations is critical for safety and user engagement. However, existing benchmarks face the Construct-Composition-Context ($C^3$) challenge: relying on discriminative, multiple-choice formats that probe value knowledge rather than true orientations, overlook subcultural heterogeneity, and mismatch with real-world open-ended generation. We introduce DOVE, a distributional...
Distributional Open-Ended Evaluation of LLM Cultural Value Alignment Based on Value Codebook
arXiv:2604.06210v4 Announce Type: replace Abstract: As LLMs are globally deployed, aligning their cultural value orientations is critical for safety and user engagement. However, existing benchmarks face the Construct-Composition-Context ($C^3$) challenge: relying on discriminative, multiple-choice formats that probe value knowledge rather than true orientations, overlook subcultural heterogeneity, and mismatch with real-world open-ended generation. We introduce DOVE, a distributional...
Graph is a Natural Regularization: Revisiting Vector Quantization for Graph Representation Learning
arXiv:2508.06588v3 Announce Type: replace Abstract: Vector Quantization (VQ) has recently emerged as a promising approach for learning compressed and discrete representations for graph-structured data. However, a fundamental challenge, i.e., codebook collapse, remains underexplored in the graph domain, significantly limiting the expressiveness and generalization of graph tokens. In this paper, we present an empirical study and observe that codebook collapse consistently occurs when training...
Decoupled Residual Quantization for Robust Semantic IDs in Recommendation
Announce Type: new Abstract: Semantic IDs represent items as shared discrete token sequences and have become a practical tool for recommendation and retrieval. Yet it remains difficult to tell why a tokenizer fails: poor quality may come from codebook underutilization, unstable decision boundaries, or geometric distortion of the embedding space. This paper develops a quantitative framework for diagnosing these failures through expected codeword overlap and effective codebook capacity.