Tagged articles

7 articles

Page 1 of 1

May 14, 2026 · Artificial Intelligence

Breaking Homogeneous Reasoning: I²B‑LPO Guides RLVR from Repeated Sampling to Effective Exploration

I²B‑LPO is an exploration‑enhancement framework for RLVR that branches rollouts at high‑entropy nodes, injects latent variables via pseudo self‑attention, and filters paths with an information‑bottleneck self‑reward, achieving up to 5.3% accuracy and 7.4% diversity improvements on multiple math reasoning benchmarks.

RLVRentropyexploration

0 likes · 14 min read

Breaking Homogeneous Reasoning: I²B‑LPO Guides RLVR from Repeated Sampling to Effective Exploration

Machine Heart

Apr 27, 2026 · Artificial Intelligence

What Do Your Logits Know? Surprising Insights from Apple’s New AI Paper

Apple’s recent AI paper probes whether large vision‑language models truly forget user data by examining residual streams and final logits, revealing that hidden image attributes persist in top‑k outputs and exposing significant privacy and security risks.

AI securityVision-Language Modelsinformation bottleneck

0 likes · 11 min read

What Do Your Logits Know? Surprising Insights from Apple’s New AI Paper

Network Intelligence Research Center (NIRC)

Jan 17, 2026 · Artificial Intelligence

DiffNBR: A Spatiotemporal Diffusion and Information‑Bottleneck Approach for Next‑Basket Recommendation

DiffNBR introduces a dual‑path diffusion framework combined with an information‑bottleneck mechanism to jointly model spatial co‑occurrence and temporal evolution in next‑basket recommendation, achieving state‑of‑the‑art performance and effectively disentangling repetitive and exploratory purchase patterns.

DiffNBRdiffusion modelinformation bottleneck

0 likes · 8 min read

DiffNBR: A Spatiotemporal Diffusion and Information‑Bottleneck Approach for Next‑Basket Recommendation

Ele.me Technology

Oct 27, 2025 · Artificial Intelligence

How IAK Transforms Multi‑Domain Recommendation with Pre‑Training and Fine‑Tuning

This paper introduces IAK, a unified multi‑domain recommendation paradigm that treats the system as a large model, leveraging pre‑training and fine‑tuning with an information‑aware adaptive kernel to capture rapid user interest shifts while reducing training costs and improving online performance.

Recommendation Systemsfine‑tuninginformation bottleneck

0 likes · 18 min read

How IAK Transforms Multi‑Domain Recommendation with Pre‑Training and Fine‑Tuning

Alimama Tech

Nov 22, 2023 · Artificial Intelligence

Robust Link Prediction under Bilateral Edge Noise via Robust Graph Information Bottleneck (RGIB)

The paper introduces Robust Graph Information Bottleneck (RGIB), a framework that jointly mitigates bilateral edge noise in link prediction by decoupling topology, label, and representation information, with two variants (RGIB‑SSL and RGIB‑REP) that achieve up to 12.9% AUC gains on benchmarks and have already boosted click‑through‑rate robustness and revenue in Alibaba’s advertising system.

RGIBRobustnessbilateral noise

0 likes · 13 min read

Robust Link Prediction under Bilateral Edge Noise via Robust Graph Information Bottleneck (RGIB)

DataFunSummit

Jan 8, 2022 · Artificial Intelligence

Graph Information Bottleneck and AD‑GCL: Enhancing Graph Representation Learning and Robustness

This article introduces graph representation learning, explains the Graph Information Bottleneck (GIB) framework for obtaining robust graph embeddings, and presents AD‑GCL, a contrastive learning method that leverages GIB principles to improve graph neural network performance without requiring task labels.

Graph RepresentationRobustnessUnsupervised Learning

0 likes · 15 min read

Graph Information Bottleneck and AD‑GCL: Enhancing Graph Representation Learning and Robustness

DataFunTalk

Dec 11, 2021 · Artificial Intelligence

Graph Information Bottleneck (GIB) and AD‑GCL: Enhancing Graph Representation Learning and Robustness

This article introduces graph representation learning, explains the Graph Information Bottleneck (GIB) framework for obtaining robust graph embeddings, and presents AD‑GCL, a contrastive learning method that leverages GIB principles to improve robustness and performance without requiring task labels.

RobustnessUnsupervised Learningcontrastive learning

0 likes · 16 min read

Graph Information Bottleneck (GIB) and AD‑GCL: Enhancing Graph Representation Learning and Robustness