# TriAlignGR: Triangular Multitask Alignment with Multimodal Deep Interest Mining for Generative Recommendation

arXiv: https://arxiv.org/abs/2605.05249 · HTML: https://mlsanity.com/paper/2605.05249/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 5 May 2026.

## Built on by (most cited first, 3 of 3)

- [When Images Look Right and Retrieve Wrong: Coverage-Guided Cross-Scale Re-Indexing for Knowledge-Faithful Generative Perception](https://mlsanity.com/paper/2608.20810/) (2026)
- [Meta-Modal Agent: Sequential Evidence Routing for Missing-Modality Candidate Reranking](https://mlsanity.com/paper/2605.25007/) (2026)
- [HGSQ: Heatmap-Guided Sparse Query Detector for Real-Time Aerial Small Object Detection](https://mlsanity.com/paper/2609.13306/) (2026)

## Abstract (arXiv)

We introduce TriAlignGR, a unified multitask-multimodal framework for generative recommendation that establishes two-stage multimodal semantic propagation: (i) encoding visual semantics directly into SIDs via multimodal embeddings, and (ii) enabling the model to decode these semantics through visual description tasks. Existing Semantic ID (SID) pipelines suffer from two fundamental but underexplored problems: SID Content Degradation (SCD), where cascaded encoding and residual quantization discard critical multimodal and interest-level semantics; and SID Semantic Opacity (SSO), where models autoregressively generate SID sequences without truly comprehending their underlying meaning, leading to hallucination and poor generalization. Prior work addresses at most text-SID alignment, leaving visual semantics and latent user interests entirely unexploited. TriAlignGR resolves both problems through three tightly integrated components: (1)~Cross-Modal Semantic Alignment (CMSA) integrates visual content into SID construction through both VLM-generated textual descriptions and a multimodal embedding model that directly encodes image features alongside text, ensuring that SIDs inherently carry multimodal semantics; (2)~Multimodal Deep Interest Mining (MDIM) leverages LLM Chain-of-Thought reasoning to extract latent user intents (eg ``productivity-focused lifestyle'' from noise-canceling headphones) beyond surface attributes, enriching SID semantics before discretization; and (3)~Triangular Multitask (TMT) jointly trains on eight complementary generation tasks under a single autoregressive loss -- including two novel visual-semantic tasks (VisDesc→SID, VisDesc→Title) that map VLM-generated image descriptions to SIDs and titles, completing the SID-Text-Image triangle -- without requiring task-specific towers or complex loss weighting.