Tagged articles

9 articles

Page 1 of 1

Apr 20, 2026 · Artificial Intelligence

How VA‑π Bridges Tokenizers and Autoregressive Generators for Pixel‑Perfect Images

VA‑π introduces a lightweight post‑training framework that uses variational inference and reinforcement learning to align tokenizers with visual autoregressive generators, achieving dramatic quality gains, extreme training efficiency, and robust pixel‑level reconstruction across diverse image generation tasks.

Autoregressive ModelsPixel AlignmentReinforcement Learning

0 likes · 14 min read

How VA‑π Bridges Tokenizers and Autoregressive Generators for Pixel‑Perfect Images

AIWalker

Mar 6, 2026 · Artificial Intelligence

VA‑π: Pixel‑Level Alignment Achieves 50% FID Reduction with 25‑Minute Fine‑Tuning

The paper introduces VA‑π, a lightweight post‑training framework that aligns pixel‑level reconstruction with autoregressive generation using variational inference and reinforcement learning, achieving up to 50% FID reduction after just 25 minutes of fine‑tuning on LlamaGen‑XXL.

AR ModelsPixel AlignmentVariational Inference

0 likes · 14 min read

VA‑π: Pixel‑Level Alignment Achieves 50% FID Reduction with 25‑Minute Fine‑Tuning

DataFunTalk

Aug 31, 2024 · Artificial Intelligence

Preference‑Oriented Diversity Model Based on Mutual Information for E‑commerce Search Re‑ranking (SIGIR 2024)

This paper, accepted at SIGIR 2024, introduces PODM‑MI, a preference‑oriented diversity re‑ranking model for e‑commerce search that jointly optimizes accuracy and diversity by modeling user intent with multivariate Gaussian distributions and maximizing mutual information between user preferences and candidate items.

E-commerce SearchUser Preference ModelingVariational Inference

0 likes · 11 min read

Preference‑Oriented Diversity Model Based on Mutual Information for E‑commerce Search Re‑ranking (SIGIR 2024)

JD Tech

Aug 26, 2024 · Artificial Intelligence

Preference-oriented Diversity Model Based on Mutual Information for E-commerce Search Re-ranking (SIGIR 2024)

This article presents the SIGIR 2024 accepted PODM‑MI model, which uses variational inference and mutual‑information maximization to jointly optimize relevance and diversity in JD e‑commerce search re‑ranking, demonstrating significant gains in both user conversion and result diversity through extensive online experiments.

DiversityE-commerce SearchPreference Modeling

0 likes · 11 min read

JD Cloud Developers

Aug 26, 2024 · Artificial Intelligence

Boosting E‑Commerce Re‑ranking Diversity and Accuracy with Mutual‑Information

This paper introduces PODM‑MI, a preference‑oriented diversity model that jointly optimizes relevance and diversity in e‑commerce search re‑ranking by leveraging variational inference and mutual‑information, demonstrating significant gains in both user conversion and result variety on JD.com.

DiversityE-commerce SearchPreference Modeling

0 likes · 10 min read

Boosting E‑Commerce Re‑ranking Diversity and Accuracy with Mutual‑Information

DataFunTalk

Jun 24, 2024 · Artificial Intelligence

CausalMMM: Learning Causal Structure for Marketing Mix Modeling

The paper introduces CausalMMM, a variational inference framework that integrates Granger causality and graph neural networks to automatically discover heterogeneous causal structures in marketing mix modeling, enabling more accurate GMV prediction and actionable insights for diverse advertisers.

AdvertisingGMV predictionGraph Neural Network

0 likes · 15 min read

CausalMMM: Learning Causal Structure for Marketing Mix Modeling

Alimama Tech

Jun 21, 2024 · Artificial Intelligence

CausalMMM: Learning Causal Structure for Marketing Mix Modeling

CausalMMM introduces an encoder‑decoder framework that automatically discovers heterogeneous, interpretable causal graphs among advertising channels while modeling temporal decay and saturation, using Granger‑based variational inference, and achieves over 5.7% improvement in causal structure learning and significant GMV prediction gains on Alibaba’s data.

Variational Inferencemarketing mix modelingtime series forecasting

0 likes · 16 min read

Model Perspective

Oct 20, 2022 · Artificial Intelligence

Unlocking Bayesian Inference: How Probabilistic Programming Simplifies Complex Models

This article explains Bayesian statistics as a probabilistic framework, describes how modern numerical methods and probabilistic programming languages automate inference, and reviews both Markov and non‑Markov techniques such as MCMC, grid computation, Laplace approximation, and variational inference for building complex models.

Bayesian inferenceMCMCVariational Inference

0 likes · 7 min read

Unlocking Bayesian Inference: How Probabilistic Programming Simplifies Complex Models

Architecture Digest

Feb 11, 2018 · Artificial Intelligence

Recent Advances in Bayesian Machine Learning: Foundations, Non‑Parametric Methods, and Large‑Scale Applications

This article reviews recent progress in Bayesian machine learning, covering foundational theory, non‑parametric approaches such as Dirichlet and Indian buffet processes, regularized Bayesian inference, and scalable techniques for big‑data environments including stochastic variational methods, distributed algorithms, and hardware acceleration.

Big DataMonte CarloVariational Inference

0 likes · 23 min read

Recent Advances in Bayesian Machine Learning: Foundations, Non‑Parametric Methods, and Large‑Scale Applications