Position-Aware Drafting for Inference Acceleration in LLM-Based Generative List-Wise Recommendation | Paper Citation Record

Observation ecd621d7-e368-4333-8ae5-93293caad541 · outbound

This paper cites arXiv preprint arXiv:2509.03236 , year=.

Position-Aware Drafting for Inference Acceleration in LLM-Based Generative List-Wise Recommendation arXiv preprint arXiv:2509.03236 , year=

Reference 1

Resolution: metadata mismatch; arxiv_id, observed 2026-05-12T10:06:29.872890Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation fe900949-ae80-4c7b-95c3-6a140dfc5d45 · outbound

This paper cites OneRec: Unifying Retrieve and Rank with Generative Recommender and Iterative Preference Alignment.

Position-Aware Drafting for Inference Acceleration in LLM-Based Generative List-Wise Recommendation OneRec: Unifying Retrieve and Rank with Generative Recommender and Iterative Preference Alignment

Reference 2

Resolution: verified exact; arxiv_id, observed 2026-05-12T18:30:36.120082Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 34d86ddc-4448-4692-8736-ebda98ad9261 · outbound

This paper cites Dlcrec: A novel approach for managing diversity in llm-based recommender systems.

Position-Aware Drafting for Inference Acceleration in LLM-Based Generative List-Wise Recommendation Dlcrec: A novel approach for managing diversity in llm-based recommender systems

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-05-27T09:28:54.153021Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 05c500de-309d-4449-9a99-1ecb9532bbdf · outbound

This paper cites Knowledge-enhanced con- versational recommendation via transformer-based sequential modeling.

Position-Aware Drafting for Inference Acceleration in LLM-Based Generative List-Wise Recommendation Knowledge-enhanced con- versational recommendation via transformer-based sequential modeling

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-05-27T09:28:54.146740Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 81f784fe-558c-4c0d-be42-b7ccf3609845 · outbound

This paper cites Decoding in latent spaces for efficient inference in llm-based recommendation.

Position-Aware Drafting for Inference Acceleration in LLM-Based Generative List-Wise Recommendation Decoding in latent spaces for efficient inference in llm-based recommendation

Reference 5

Resolution: verified exact; arxiv_id, observed 2026-05-12T10:06:29.855506Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 4ed9aa09-4465-4552-b0a7-7a6a6e9858b4 · outbound

This paper cites Efficient inference for large language model-based generative recommendation.

Position-Aware Drafting for Inference Acceleration in LLM-Based Generative List-Wise Recommendation Efficient inference for large language model-based generative recommendation

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-05-27T09:28:54.269224Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 66a6b10b-2912-40d9-98bd-1fb57cd933ed · outbound

This paper cites Efficiency unleashed: Inference acceleration for llm-based recommender systems with speculative decoding.

Position-Aware Drafting for Inference Acceleration in LLM-Based Generative List-Wise Recommendation Efficiency unleashed: Inference acceleration for llm-based recommender systems with speculative decoding

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-05-27T09:28:54.137408Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 78111f0a-7d0a-47d0-b84e-cc83e83f5b69 · outbound

This paper cites Fast inference from transform- ers via speculative decoding.

Position-Aware Drafting for Inference Acceleration in LLM-Based Generative List-Wise Recommendation Fast inference from transform- ers via speculative decoding

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-05-27T09:28:54.255101Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 52d294ab-ba12-4e7c-9c26-463ec80f03b4 · outbound

This paper cites Speculative Decoding: Exploiting Speculative Execution for Accelerating Seq2seq Generation.

Position-Aware Drafting for Inference Acceleration in LLM-Based Generative List-Wise Recommendation Speculative Decoding: Exploiting Speculative Execution for Accelerating Seq2seq Generation

Reference 9

Resolution: metadata mismatch; arxiv_id, observed 2026-05-12T10:06:29.908758Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 0023b997-b4a0-478d-99b5-92a106d8ed04 · outbound

This paper cites Unlocking efficiency in large language model inference: A comprehensive survey of speculative decoding.

Position-Aware Drafting for Inference Acceleration in LLM-Based Generative List-Wise Recommendation Unlocking efficiency in large language model inference: A comprehensive survey of speculative decoding

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-05-27T09:28:54.286173Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation d04f00d6-ec81-44b4-9f0a-3f9a4c10f530 · outbound

This paper cites Accelerating Large Language Model Decoding with Speculative Sampling.

Position-Aware Drafting for Inference Acceleration in LLM-Based Generative List-Wise Recommendation Accelerating Large Language Model Decoding with Speculative Sampling

Reference 11

Resolution: verified exact; local_arxiv, observed 2026-05-12T10:06:29.891667Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation ee4d2755-e4e4-451c-a62b-6ad3bb613513 · outbound

This paper cites Specinfer: Accelerating large language model serving with tree-based speculative inference and ver- ification.

Position-Aware Drafting for Inference Acceleration in LLM-Based Generative List-Wise Recommendation Specinfer: Accelerating large language model serving with tree-based speculative inference and ver- ification

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-05-27T09:28:54.250871Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 20436695-608a-40d5-901a-457577fd7c1c · outbound

This paper cites DistillSpec: Improving Speculative Decoding via Knowledge Distillation.

Position-Aware Drafting for Inference Acceleration in LLM-Based Generative List-Wise Recommendation DistillSpec: Improving Speculative Decoding via Knowledge Distillation

Reference 13

Resolution: verified exact; arxiv_id, observed 2026-05-12T10:06:29.899708Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 73990dbe-a379-461a-80b9-312fc25d7f16 · outbound

This paper cites Eagle: Speculative sampling requires rethinking feature uncertainty.

Position-Aware Drafting for Inference Acceleration in LLM-Based Generative List-Wise Recommendation Eagle: Speculative sampling requires rethinking feature uncertainty

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-05-27T09:28:54.237330Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 5ad440f3-6f73-45d7-8eda-bc97bc154366 · outbound

This paper cites Learning harmonized rep- resentations for speculative sampling.

Position-Aware Drafting for Inference Acceleration in LLM-Based Generative List-Wise Recommendation Learning harmonized rep- resentations for speculative sampling

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-05-27T09:28:54.222469Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 1aa4c6c1-1440-4e4b-98e0-13489a045b1c · outbound

This paper cites Tokenrec: Learning to tokenize id for llm-based generative recommendations.

Position-Aware Drafting for Inference Acceleration in LLM-Based Generative List-Wise Recommendation Tokenrec: Learning to tokenize id for llm-based generative recommendations

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-05-27T09:28:54.205906Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 546e092e-6081-4435-a44f-5de73ae45449 · outbound

This paper cites Adapting large language models by integrating collaborative semantics for recommendation.

Position-Aware Drafting for Inference Acceleration in LLM-Based Generative List-Wise Recommendation Adapting large language models by integrating collaborative semantics for recommendation

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-05-27T09:28:54.202444Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 6d7b01e3-6c73-4fec-89a3-b6e686d4b8ba · outbound

This paper cites Autoregressive image generation using residual quantization.

Position-Aware Drafting for Inference Acceleration in LLM-Based Generative List-Wise Recommendation Autoregressive image generation using residual quantization

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-05-27T09:28:54.172514Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 12140ae8-0e99-41cd-8568-95d2d61d1740 · outbound

This paper cites Blockwise parallel decoding for deep autoregressive models.

Position-Aware Drafting for Inference Acceleration in LLM-Based Generative List-Wise Recommendation Blockwise parallel decoding for deep autoregressive models

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-05-27T09:28:54.272339Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 5806231e-8c2c-4088-b2f6-11c00b27ff9e · outbound

This paper cites Eagle-2: Faster inference of language models with dynamic draft trees.

Position-Aware Drafting for Inference Acceleration in LLM-Based Generative List-Wise Recommendation Eagle-2: Faster inference of language models with dynamic draft trees

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-05-27T09:28:54.133117Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 615d321e-d21c-4849-a3d1-bafd50b10521 · outbound

This paper cites Sequoia: Scalable, robust, and hardware-aware speculative decoding.

Position-Aware Drafting for Inference Acceleration in LLM-Based Generative List-Wise Recommendation Sequoia: Scalable, robust, and hardware-aware speculative decoding

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-05-27T09:28:54.129079Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation ae4474a0-e374-4643-ade2-4a24c20469e2 · outbound

This paper cites Specexec: Massively parallel speculative decoding for interactive llm inference on consumer devices.

Position-Aware Drafting for Inference Acceleration in LLM-Based Generative List-Wise Recommendation Specexec: Massively parallel speculative decoding for interactive llm inference on consumer devices

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-05-27T09:28:54.275663Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 0158217d-1e6b-473b-98f7-ecee20737343 · outbound

This paper cites Break the sequential de- pendency of llm inference using lookahead decoding.

Position-Aware Drafting for Inference Acceleration in LLM-Based Generative List-Wise Recommendation Break the sequential de- pendency of llm inference using lookahead decoding

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-05-27T09:28:54.289044Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 80ee3c1b-e644-4373-a042-75603652d67f · outbound

This paper cites Cllms: Consistency large language models.

Position-Aware Drafting for Inference Acceleration in LLM-Based Generative List-Wise Recommendation Cllms: Consistency large language models

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-05-27T09:28:54.240744Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 413e5b16-0e87-41d2-92f0-51147bdcbebc · outbound

This paper cites Rest: Retrieval- based speculative decoding.

Position-Aware Drafting for Inference Acceleration in LLM-Based Generative List-Wise Recommendation Rest: Retrieval- based speculative decoding

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-05-27T09:28:54.258525Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 1fb7d90f-2a76-444e-bc95-59cc2b53bad9 · outbound

This paper cites Ouroboros: Generating longer drafts phrase by phrase for faster speculative decoding.

Position-Aware Drafting for Inference Acceleration in LLM-Based Generative List-Wise Recommendation Ouroboros: Generating longer drafts phrase by phrase for faster speculative decoding

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-05-27T09:28:54.176731Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 73db22a3-fc50-4b9f-940f-d39fd897ef9e · outbound

This paper cites Medusa: Simple llm inference acceleration framework with multiple decoding heads.

Position-Aware Drafting for Inference Acceleration in LLM-Based Generative List-Wise Recommendation Medusa: Simple llm inference acceleration framework with multiple decoding heads

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-05-27T09:28:54.219564Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 3cd53210-084a-42ee-a65e-938242bfa5b3 · outbound

This paper cites Hydra: Sequentially-dependent draft heads for medusa decoding.

Position-Aware Drafting for Inference Acceleration in LLM-Based Generative List-Wise Recommendation Hydra: Sequentially-dependent draft heads for medusa decoding

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-05-27T09:28:54.278832Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 8a298b37-7ab6-4baf-b354-6a9ca9f15185 · outbound

This paper cites Griffin: Effective token alignment for faster speculative decoding.arXiv preprint arXiv:2502.11018, 2025a.

Position-Aware Drafting for Inference Acceleration in LLM-Based Generative List-Wise Recommendation Griffin: Effective token alignment for faster speculative decoding.arXiv preprint arXiv:2502.11018, 2025a

Reference 29

Resolution: verified exact; arxiv_id, observed 2026-05-12T10:06:30.198524Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation b1032ac3-1c44-4fed-8111-ba6b5f4d0ba9 · outbound

This paper cites Boosting Lossless Speculative Decoding via Feature Sampling and Partial Alignment Distillation.

Position-Aware Drafting for Inference Acceleration in LLM-Based Generative List-Wise Recommendation Boosting Lossless Speculative Decoding via Feature Sampling and Partial Alignment Distillation

Reference 30

Resolution: verified exact; arxiv_id, observed 2026-05-12T10:06:30.243035Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 5e5a82c0-9f92-4c46-94ec-3a2516ebc520 · outbound

This paper cites CORAL: Learning Consistent Representations across Multi-step Training with Lighter Speculative Drafter.

Position-Aware Drafting for Inference Acceleration in LLM-Based Generative List-Wise Recommendation CORAL: Learning Consistent Representations across Multi-step Training with Lighter Speculative Drafter

Reference 31

Resolution: verified exact; arxiv_id, observed 2026-05-12T10:06:29.865081Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation b8a2e4bf-96cf-48a7-b633-5bff191870f7 · outbound

This paper cites How speculative can speculative decoding be?.

Position-Aware Drafting for Inference Acceleration in LLM-Based Generative List-Wise Recommendation How speculative can speculative decoding be?

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-05-27T09:28:54.180538Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation fd82ee0f-7577-4b08-b95d-b329e92b1c80 · outbound

This paper cites Heterospec: Leveraging con- textual heterogeneity for efficient speculative decoding.

Position-Aware Drafting for Inference Acceleration in LLM-Based Generative List-Wise Recommendation Heterospec: Leveraging con- textual heterogeneity for efficient speculative decoding

Reference 33

Resolution: verified exact; arxiv_id, observed 2026-05-12T10:06:29.886601Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 9690de99-d5b6-44e1-9d36-6770af8ec623 · outbound

This paper cites H2o: Heavy-hitter oracle for efficient generative inference of large language models.

Position-Aware Drafting for Inference Acceleration in LLM-Based Generative List-Wise Recommendation H2o: Heavy-hitter oracle for efficient generative inference of large language models

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-05-27T09:28:54.195060Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 8633d075-2006-4ee0-8a8e-7dbe81562684 · outbound

This paper cites A bi-step grounding paradigm for large language mod- els in recommendation systems.

Position-Aware Drafting for Inference Acceleration in LLM-Based Generative List-Wise Recommendation A bi-step grounding paradigm for large language mod- els in recommendation systems

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-05-27T09:28:54.186470Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation e6ee1658-c903-4837-a11d-d39d042f7526 · outbound

This paper cites Large language models are learnable planners for long-term recommendation.

Position-Aware Drafting for Inference Acceleration in LLM-Based Generative List-Wise Recommendation Large language models are learnable planners for long-term recommendation

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-05-27T09:28:54.161057Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation fdc0672d-d3b9-42b4-bd0a-42fec5d3b1a5 · outbound

This paper cites arXiv preprint arXiv:2505.19092 (2025).

Position-Aware Drafting for Inference Acceleration in LLM-Based Generative List-Wise Recommendation arXiv preprint arXiv:2505.19092 (2025)

Reference 37

Resolution: metadata mismatch; arxiv_id, observed 2026-05-12T10:06:30.236804Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 986c789a-50c2-4e7e-b21b-4d7259389f65 · outbound

This paper cites Recommender systems with generative retrieval.

Position-Aware Drafting for Inference Acceleration in LLM-Based Generative List-Wise Recommendation Recommender systems with generative retrieval

Reference 38

Resolution: verified fuzzy; raw_fallback, observed 2026-05-27T09:28:54.244072Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation f9af480d-8064-4dca-af9f-020a70c5992c · outbound

This paper cites ActionPiece: Contextually Tokenizing Action Sequences for Generative Recommendation.

Position-Aware Drafting for Inference Acceleration in LLM-Based Generative List-Wise Recommendation ActionPiece: Contextually Tokenizing Action Sequences for Generative Recommendation

Reference 39

Resolution: verified exact; arxiv_id, observed 2026-05-12T10:06:30.248571Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 03b7c38b-faee-4235-98e1-654675ea2aab · outbound

This paper cites Learnable item tokenization for generative recommendation.

Position-Aware Drafting for Inference Acceleration in LLM-Based Generative List-Wise Recommendation Learnable item tokenization for generative recommendation

Reference 40

Resolution: verified fuzzy; raw_fallback, observed 2026-05-27T09:28:54.292050Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 7c322a6f-11fe-4295-a86f-00111a1d82d7 · outbound

This paper cites How to index item ids for recommendation foundation models.

Position-Aware Drafting for Inference Acceleration in LLM-Based Generative List-Wise Recommendation How to index item ids for recommendation foundation models

Reference 41

Resolution: verified fuzzy; raw_fallback, observed 2026-05-27T09:28:54.156875Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 53e4e53b-12f6-4c2e-b62e-3c9aefcf6478 · outbound

This paper cites Recommendation as language processing (rlp): A unified pretrain, personalized prompt & predict paradigm (p5).

Position-Aware Drafting for Inference Acceleration in LLM-Based Generative List-Wise Recommendation Recommendation as language processing (rlp): A unified pretrain, personalized prompt & predict paradigm (p5)

Reference 42

Resolution: verified fuzzy; raw_fallback, observed 2026-05-27T09:28:54.168794Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 07bde36d-8eaa-48e6-b8f2-dba70125f70d · outbound

This paper cites Eager: Two-stream generative recommender with behavior-semantic collaboration.

Position-Aware Drafting for Inference Acceleration in LLM-Based Generative List-Wise Recommendation Eager: Two-stream generative recommender with behavior-semantic collaboration

Reference 43

Resolution: verified fuzzy; raw_fallback, observed 2026-05-27T09:28:54.226066Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 65fc0211-49e9-4dc6-882c-e6a46f9cceb6 · outbound

This paper cites Actions Speak Louder than Words: Trillion-Parameter Sequential Transducers for Generative Recommendations.

Position-Aware Drafting for Inference Acceleration in LLM-Based Generative List-Wise Recommendation Actions Speak Louder than Words: Trillion-Parameter Sequential Transducers for Generative Recommendations

Reference 44

Resolution: verified exact; arxiv_id, observed 2026-05-13T19:39:33.082504Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 86e4deea-82f2-4278-8c42-247ec6d51a15 · outbound

This paper cites Sprec: Self- play to debias llm-based recommendation.

Position-Aware Drafting for Inference Acceleration in LLM-Based Generative List-Wise Recommendation Sprec: Self- play to debias llm-based recommendation

Reference 45

Resolution: verified fuzzy; raw_fallback, observed 2026-05-27T09:28:54.183633Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation e6205265-dad3-4e70-8255-a5af0d59e094 · outbound

This paper cites Process- supervised llm recommenders via flow-guided tuning.

Position-Aware Drafting for Inference Acceleration in LLM-Based Generative List-Wise Recommendation Process- supervised llm recommenders via flow-guided tuning

Reference 46

Resolution: verified fuzzy; raw_fallback, observed 2026-05-27T09:28:54.247454Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 5a7de5c2-3b1c-49f2-8f5c-57ede7095d87 · outbound

This paper cites Nextquill: Causal preference modeling for enhancing llm personalization.

Position-Aware Drafting for Inference Acceleration in LLM-Based Generative List-Wise Recommendation Nextquill: Causal preference modeling for enhancing llm personalization

Reference 47

Resolution: verified exact; arxiv_id, observed 2026-05-12T10:06:30.218617Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation cd0301b7-eee4-4b35-82b1-244d590e497d · outbound

This paper cites Don’t start over: A cost-effective framework for migrating personalized prompts between llms.

Position-Aware Drafting for Inference Acceleration in LLM-Based Generative List-Wise Recommendation Don’t start over: A cost-effective framework for migrating personalized prompts between llms

Reference 48

Resolution: verified exact; arxiv_id, observed 2026-05-12T10:06:30.224646Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 1356707f-47fe-4ec8-8235-31a7201f256e · outbound

This paper cites Think-While-Generating: On-the-Fly Reasoning for Personalized Long-Form Generation.arXiv preprint arXiv:2512.06690.2025.

Position-Aware Drafting for Inference Acceleration in LLM-Based Generative List-Wise Recommendation Think-While-Generating: On-the-Fly Reasoning for Personalized Long-Form Generation.arXiv preprint arXiv:2512.06690.2025

Reference 49

Resolution: verified exact; arxiv_id, observed 2026-05-12T10:06:30.205546Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation fd4e0302-9129-4df9-a5b5-13577fa35f70 · outbound

This paper cites Integrating large language models with reinforcement learning: A survey of llm-rl synergistic recommendation.

Position-Aware Drafting for Inference Acceleration in LLM-Based Generative List-Wise Recommendation Integrating large language models with reinforcement learning: A survey of llm-rl synergistic recommendation

Reference 50

Resolution: verified fuzzy; raw_fallback, observed 2026-05-27T09:28:54.229947Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 46f50316-c351-477b-b2cc-863897b32485 · outbound

This paper cites Generative retrieval with semantic tree-structured identifiers and contrastive learning.

Position-Aware Drafting for Inference Acceleration in LLM-Based Generative List-Wise Recommendation Generative retrieval with semantic tree-structured identifiers and contrastive learning

Reference 51

Resolution: verified fuzzy; raw_fallback, observed 2026-05-27T09:28:54.140971Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation e20fa4b2-284a-4b30-b92b-f9ee65f9815e · outbound

This paper cites Idgenrec: Llm- recsys alignment with textual id learning.

Position-Aware Drafting for Inference Acceleration in LLM-Based Generative List-Wise Recommendation Idgenrec: Llm- recsys alignment with textual id learning

Reference 52

Resolution: verified fuzzy; raw_fallback, observed 2026-05-27T09:28:54.209302Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 732cbecb-e851-46ef-9708-c05e12ef2e1a · outbound

This paper cites Wide & deep learning for recommender systems.

Position-Aware Drafting for Inference Acceleration in LLM-Based Generative List-Wise Recommendation Wide & deep learning for recommender systems

Reference 53

Resolution: verified fuzzy; raw_fallback, observed 2026-05-27T09:28:54.261750Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 7ba00ccc-2175-4a4c-ab3b-af04067d801e · outbound

This paper cites Lightgcn: Simplifying and powering graph convolution network for recommenda- tion.

Position-Aware Drafting for Inference Acceleration in LLM-Based Generative List-Wise Recommendation Lightgcn: Simplifying and powering graph convolution network for recommenda- tion

Reference 54

Resolution: verified fuzzy; raw_fallback, observed 2026-05-27T09:28:54.282832Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 126bc32d-07b8-4764-8e51-69ab8293032a · outbound

This paper cites Second order derivatives for network pruning: Optimal brain surgeon.

Position-Aware Drafting for Inference Acceleration in LLM-Based Generative List-Wise Recommendation Second order derivatives for network pruning: Optimal brain surgeon

Reference 55

Resolution: verified fuzzy; raw_fallback, observed 2026-05-27T09:28:54.198930Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 7d303553-74b8-48d9-898f-a269db93f897 · outbound

This paper cites Boosting Parameter Efficiency in LLM-Based Recommendation through Sophisticated Pruning.

Position-Aware Drafting for Inference Acceleration in LLM-Based Generative List-Wise Recommendation Boosting Parameter Efficiency in LLM-Based Recommendation through Sophisticated Pruning

Reference 56

Resolution: verified exact; arxiv_id, observed 2026-05-12T10:06:30.212147Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 221e6220-3a08-49ed-96ac-bc232c7c8eac · outbound

This paper cites Smoothquant: Accurate and efficient post-training quantization for large language models.

Position-Aware Drafting for Inference Acceleration in LLM-Based Generative List-Wise Recommendation Smoothquant: Accurate and efficient post-training quantization for large language models

Reference 57

Resolution: verified fuzzy; raw_fallback, observed 2026-05-27T09:28:54.190671Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 5d4bd148-b2a7-452b-937d-40dc05deae7b · outbound

This paper cites Inductive generative recom- mendation via retrieval-based speculation.

Position-Aware Drafting for Inference Acceleration in LLM-Based Generative List-Wise Recommendation Inductive generative recom- mendation via retrieval-based speculation

Reference 58

Resolution: verified fuzzy; raw_fallback, observed 2026-05-27T09:28:54.212673Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 10456410-26dd-46ed-b2c9-15544ad62923 · outbound

This paper cites Nezha: A zero-sacrifice and hyperspeed decoding architecture for generative recommendations.

Position-Aware Drafting for Inference Acceleration in LLM-Based Generative List-Wise Recommendation Nezha: A zero-sacrifice and hyperspeed decoding architecture for generative recommendations

Reference 59

Resolution: verified fuzzy; raw_fallback, observed 2026-05-27T09:28:54.233589Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 037f22a4-d86c-4f6e-85f4-a79bebd3951e · outbound

This paper cites Earn: Efficient inference acceleration for llm-based generative recom- mendation by register tokens.

Position-Aware Drafting for Inference Acceleration in LLM-Based Generative List-Wise Recommendation Earn: Efficient inference acceleration for llm-based generative recom- mendation by register tokens

Reference 60

Resolution: verified fuzzy; raw_fallback, observed 2026-05-27T09:28:54.216140Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation f3a0ddc1-07c3-4da0-b298-196fadc7d9d9 · outbound

This paper cites Justifying recommendations using distantly-labeled reviews and fine-grained aspects.

Position-Aware Drafting for Inference Acceleration in LLM-Based Generative List-Wise Recommendation Justifying recommendations using distantly-labeled reviews and fine-grained aspects

Reference 61

Resolution: verified fuzzy; raw_fallback, observed 2026-05-27T09:28:54.265337Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 9120ed13-f557-4aeb-b7f5-bb7d5917b393 · outbound

This paper cites The llama 3 herd of models.

Position-Aware Drafting for Inference Acceleration in LLM-Based Generative List-Wise Recommendation The llama 3 herd of models

Reference 62

Resolution: verified fuzzy; raw_fallback, observed 2026-05-27T09:28:54.164808Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Coverage vector

Reference resolution

Outbound references

Pith citing papers