2026-10-26 ~ 11-01 · Generative
Generative · Personalization · AI Search · Infra · Embodied AI
- 1. PailitaoMMSearch2.0 Technical Report: Scaling Generative Retrieval to Unified End-to-End Multimodal Search · 📖 Deep dive
In Taobao's Pailitao, a user may photograph a shirt and ask for shorts to match it, which calls for a complementary item rather than a duplicate. The usual pipeline classifies intent first and routes to separate…
Appeared in: 10-29
- 2. PinGER: Token-Efficient Generative Retrieval with Semantic IDs · 📖 Deep dive
Generative retrieval encodes each item as a multi-level SID and generates it level by level, but on the input side every history item costs several tokens. During training…
Appeared in: 10-28
- 3. SLIDE: Search-to-List Item Distillation for Single-Rollout Generative Retrieval · 📖 Deep dive
Generative retrieval usually produces candidates online with beam search, and the beams never see each other; writing a whole list in one go by greedy decoding is the most direct alternative but works much worse…
Appeared in: 10-28
- 4. KL-MOPD: Discrepancy-Aware Multi-Objective On-Policy Distillation for Generative Recommendation · 📖 Deep dive
When click and value teachers are distilled together into a generative recommender, equal per-token weights are unfair. On TencentGR the student's KL to the value teacher at the first token is 3.13 times its KL to the…
Appeared in: 10-29
- 5. Latent Residual Reasoning for Ranking in Generative Recommendation · 📖 Deep dive
Generative ranking models usually score every candidate in one forward pass. Refiner, from Meituan and the University of Science and Technology of China, adds a few more steps…
Appeared in: 10-29
- 6. MuSID-KD: Multigranularity Knowledge Distillation for Generative Recommendation with Semantic IDs · 📖 Deep dive
When a SID-based generative recommender is distilled into a small model, the student is usually asked only to match the teacher's distribution over which item to recommend in the end…
Appeared in: 10-28
- 7. From Item Scores to Semantic Tokens: Test-Time Collaborative Adaptation for Generative Recommendation · 📖 Deep dive
In generative recommendation with semantic IDs, the model writes an item's code one token at a time, and beam search keeps only the highest-scoring prefixes at each step. Once a prefix is pruned…
Appeared in: 10-26
- 8. PinRec: Unified Generative Retrieval Model for Pinterest Recommender Systems · 📖 Deep dive
Recommender systems usually run a separate retrieval model for the home feed, search and related items, because each surface wants something different: saves on the home feed, outbound clicks to buy on search…
Appeared in: 10-27
- 9. JevRec: Linguistic Encoding with Jev-like Decision Modeling for LLM-based Generative Recommendation · 📖 Deep dive
Most generative recommenders give every item an SID of the same length, so popular items keep paying for fine-grained codes, while shorter codes squeeze long-tail semantics…
Appeared in: 10-29
- 10. REGER: Modeling inter-item Relations with Semantic IDs for Generative Recommendation · 📖 Deep dive
Cross-entropy tells a generative recommender only which token is correct, with no signal about how other candidates compare. REGER, from the University of Electronic Science and Technology of China…
Appeared in: 10-29