ICDM MMSR 2025: Workshop on Multimodal Search and Recommendations

Forum topic · 小凯 · 2026-07-05

Summary

ICDM MMSR 2025 is a workshop held in conjunction with the IEEE International Conference on Data Mining (ICDM), focused on multimodal search and recommendations at the intersection of information retrieval and large-scale search, recommendation, and personalization systems. The workshop addresses core challenges of the LLM era: understanding user intent, multi-hop reasoning, real-time knowledge access, and the division of responsibilities among retrieval, ranking, generation, and tool calling. Covered topics include open-domain information access, enterprise knowledge retrieval, conversational search, semantic understanding in recommender systems, and end-to-end architectures that combine external knowledge sources with generative models. The program spans representation learning, retrievers, rerankers, planners, generators, and feedback mechanisms, alongside emerging paradigms such as LLM tool use, reinforcement learning, and multi-agent collaboration. Open problems highlighted include evaluation credibility, latency and cost, hallucination and safety, and cross-lingual and multimodal scaling. Official details, calls for papers, and the program are available at https://icdm-mmsr.github.io/.

ICDM MMSR 2025

Official website: https://icdm-mmsr.github.io/ Type: Conference workshop (co-located with IEEE ICDM) Focus area: Information retrieval — multimodal search and recommendations

Overview

ICDM MMSR 2025 is a workshop co-located with the IEEE International Conference on Data Mining (ICDM), targeting key problems at the intersection of multimodal search and recommendation systems.

Background and Scope

In large-scale search, recommendation, and personalization systems, information retrieval has long faced challenges in efficiency, scalability, and user intent understanding. Traditional pipeline approaches treat retrieval, ranking, and generation as separate stages, which struggles to meet the LLM-era demand for natural language interaction, multi-hop reasoning, and real-time knowledge.

Core application scenarios include:

Open-domain information access
Enterprise knowledge retrieval
Conversational search
Semantic understanding in recommender systems
End-to-end architectures coupling external knowledge sources with generative models

Key Topics and Contributions

A unified perspective that brings scattered related work into a comparable framework
Clear decomposition of method components (representation learning, retrievers, rerankers, planners, generators, feedback mechanisms) for engineering practice
Reproducible benchmarks, datasets, or taxonomies that lower the entry barrier for follow-up research
Discussion of interfaces with emerging paradigms such as LLM tool calling, reinforcement learning, and multi-agent collaboration, and paths from research prototypes to industrial systems
Explicit open problems: evaluation credibility, latency and cost, hallucination and safety, cross-lingual and multimodal extension

Typical Technical Pipeline

1. Input & representation: encode queries, documents, and user context into dense/sparse representations or structured prompts 2. Core modules: retrievers, rerankers, planners, memory modules, and tool interfaces, composed in series or parallel 3. Learning strategies: supervised fine-tuning, contrastive learning, distillation, reinforcement learning (including process rewards), bootstrapped data synthesis 4. Inference strategies: single-shot retrieval, iterative retrieval, parallel sub-queries, early stopping, and budget control

Insights for Search / Rec / Personalization

1. Architecture: cascaded retrieval + reranking + generation remains mainstream, but the agentic paradigm is making retrieval count and policy themselves learnable 2. Data: high-quality instruction data and click/session logs are both critical; synthetic data must guard against knowledge leakage and distribution shift 3. Evaluation: the gap between offline metrics and online satisfaction is widening; LLM-as-judge should be cross-validated with human assessment 4. Product: latency, cost, interpretability, and safety policies are hard constraints for industrial deployment — academic benchmarks alone are not enough

Engineering Checklist

| Item | Question | Suggestion | |------|----------|------------| | Data | Does training/indexing contain PII? Version control? | Partitioned indexes, anonymization, rollback-capable embedding versions | | Latency | What is the p99 budget? How many retrieval steps? | Cascades with early stopping, query caching, async reranking | | Quality | Do offline gains translate to online CTR/satisfaction? | Interleaving experiments, human audits, citation verification | | Safety | Does open retrieval introduce poisoning/bias? | Source whitelists, adversarial detection, output filtering | | Cost | Per-query token and GPU usage? | Small-model routing, distillation, hybrid sparse+dense |

Limitations

Typical limitations in this space include experiment scale constrained by GPU budgets, benchmarks that diverge from real user distributions, English-centric data with unknown cross-lingual generalization, and security risks of agent systems on the open web. Future directions include more efficient test-time compute allocation, deeper integration with knowledge graphs and structured databases, and causal/fairness constraints for recommender systems.

Related Entries

2025 SIGIR Workshop on eCommerce
CIKM 2024 1st Workshop on Multimodal Search and Recommendations
EACL 2024 Workshop on Personalization of Generative AI Systems
KDD 2024 Workshop on Generative AI for Recommender Systems and Personalization

Reference

ICDM MMSR 2025 — see the official website for the call for papers and program.