-
[Paper Review] Goldfish: Monolingual Language Models for 350 Languages
1,154 small monolingual GPT-2 models covering 350 low-resource languages. With 5MB-1GB of byte-premium-scaled text and 39M-125M parameters, they consistently beat XGLM 4.5B, BLOOM 7.1B, and MaLA-500 10B on FLORES perplexity.
-
[Paper Review] Algorithmically Establishing Trust in Evaluators
A zero-knowledge-style challenge–response protocol that certifies the trustworthiness of an evaluator (e.g. LLM-as-a-judge) without any labelled data, bounded by (1/4)^r.
-
[Paper Review] RTP-LX: Can LLMs Evaluate Toxicity in Multilingual Scenarios?
AAAI-25 paper introducing RTP-LX: a human-transcreated, human-annotated corpus of 1,100 toxic prompts across 28 languages, used to stress-test 10 S/LLMs as multilingual safety evaluators.
-
[Paper Review] Improving Large-Scale Recommender Systems with Auxiliary Learning
Analysis of C2AL, Meta's framework that combats majority-cohort bias in large-scale ads recommendation models via cohort-contrastive auxiliary learning.
-
[Paper Review] AgenticRecTune: Multi-Agent with Self-Evolving Skillhub for Recommendation System Optimization
An LLM multi-agent framework that automates the tuning of system-level configuration (fusion weights, demotion weights, diversity thresholds) across all three stages — pre-ranking, ranking, re-ranking — of Google Discover. Five specialized agents (Actor, Critic, Insight, Skill, Online) form a closed loop that feeds live A/B results back into memory and a self-evolving skillhub, simultaneously lifting engagement and diversity in production.
-
[Paper Review] Graph-Based Audience Expansion Model for Marketing Campaigns
A two-stage lookalike model from Rakuten — TransE-style pretraining on a 70+ service cross-service knowledge graph, then a GCN that aggregates 'knowledge queries' (head + relation embeddings) rather than neighbor entities. SIGIR 2024 short paper.
-
[Paper Review] Personalized marketing: Leveraging AI for culturally aware segmentation and targeting
A short application paper that bolts LIME onto K-means over Kaggle's 200-row Mall Customer dataset. The biggest discussion point is the gap between the 'culturally aware' framing in the title and what the experiment actually does.
-
[Paper Review] Persistent Visual Memory: Sustaining Perception for Deep Generation in LVLMs
An autoregressive LVLM's visual attention collapses as O(t⁻¹) under growing textual history. PVM adds a parallel retrieval branch alongside each FFN to restore visual perception during deep generation.
-
[Paper Review] Unlocking the power of AI in CRM: A comprehensive multidimensional exploration
A qualitative study that distills 1,055 papers down to 64, plus 24 in-depth interviews with CRM practitioners, to organize AI-powered CRM capabilities into three dimensions and eight sub-dimensions through a microfoundations-of-dynamic-capabilities lens.
-
[Paper Review] The relevance of lead prioritization: a B2B lead scoring model based on machine learning
A B2B software SME's four-year CRM dataset benchmarked across 15 classifiers via PyCaret — Gradient Boosting wins (98.39% accuracy, AUC 0.9891). Lead Source / Reason for State / Lead Classification dominate feature importance.
