DIGER makes semantic IDs in generative recommendation differentiable via Gumbel noise and decay schedules, yielding consistent gains on public datasets by aligning indexing and recommendation losses.
Sq-vae: Variational bayes on discrete representation with self-annealed stochastic quantization
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
roles
background 1polarities
background 1representative citing papers
Finite scalar quantization simplifies VQ-VAE latents by independently rounding a few dimensions to fixed levels, producing an equivalent-sized implicit codebook with competitive performance and no collapse.
Cola DLM proposes a hierarchical latent diffusion model that learns a text-to-latent mapping, fits a global semantic prior in continuous space with a block-causal DiT, and performs conditional decoding, establishing latent prior modeling as an alternative to token-level autoregressive language model
Q2D2 uses 2D geometric grid projections to quantize feature pairs in neural audio codecs, yielding implicit codebooks that improve efficiency and utilization over RVQ, VQ, and FSQ while maintaining reconstruction quality.
ArcVQ-VAE adds spherical angular-margin regularization consisting of ball-bounded norms and arc-cosine margin loss to improve codebook utilization in VQ-VAE for image tasks.
Scene-adaptive lattice vector quantization improves rate-distortion performance of 3DGS compression over uniform scalar quantization while adding little overhead and supporting multiple bit rates from one trained model.
citing papers explorer
-
Differentiable Semantic ID for Generative Recommendation
DIGER makes semantic IDs in generative recommendation differentiable via Gumbel noise and decay schedules, yielding consistent gains on public datasets by aligning indexing and recommendation losses.
-
Finite Scalar Quantization: VQ-VAE Made Simple
Finite scalar quantization simplifies VQ-VAE latents by independently rounding a few dimensions to fixed levels, producing an equivalent-sized implicit codebook with competitive performance and no collapse.
-
Continuous Latent Diffusion Language Model
Cola DLM proposes a hierarchical latent diffusion model that learns a text-to-latent mapping, fits a global semantic prior in continuous space with a block-causal DiT, and performs conditional decoding, establishing latent prior modeling as an alternative to token-level autoregressive language model
-
Two-Dimensional Quantization for Geometry-Aware Audio Coding
Q2D2 uses 2D geometric grid projections to quantize feature pairs in neural audio codecs, yielding implicit codebooks that improve efficiency and utilization over RVQ, VQ, and FSQ while maintaining reconstruction quality.
-
ArcVQ-VAE: A Spherical Vector Quantization Framework with ArcCosine Additive Margin
ArcVQ-VAE adds spherical angular-margin regularization consisting of ball-bounded norms and arc-cosine margin loss to improve codebook utilization in VQ-VAE for image tasks.
-
Improving 3D Gaussian Splatting Compression by Scene-Adaptive Lattice Vector Quantization
Scene-adaptive lattice vector quantization improves rate-distortion performance of 3DGS compression over uniform scalar quantization while adding little overhead and supporting multiple bit rates from one trained model.