DINOSAUR augments ANN indices with sampled embeddings to marginalize uncertainty, recovering standard retrieval at zero uncertainty while expanding coverage for uncertain items.
Title resolution pending
14 Pith papers cite this work, alongside 3,364 external citations. Polarity classification is still indexing.
14
Pith papers citing it
3,364
external citations · external index
citation-role summary
background 2
citation-polarity summary
roles
background 2polarities
background 2representative citing papers
LoopCTR trains CTR models with recursive layer reuse and process supervision so that zero-loop inference outperforms baselines on public and industrial datasets.
Large-scale HPC evaluation of Qdrant, Milvus, and Weaviate reveals that workload patterns limit scaling and extra cores can reduce throughput, exposing a cloud-to-HPC design mismatch.
Gryphon unifies Semantic-ID generation with direct item-level scoring in a single encoder-decoder pass, attaining higher Recall@1000 than vanilla and collision-resolved generative retrieval baselines on an industrial music dataset while simplifying the candidate pipeline in a live A/B test.
FLUID introduces LUCID semantic codes from a multimodal encoder to retire item IDs in livestreaming rankers, with staged warmup yielding online gains of +0.55% watch duration and +2.05% cold-start views.
TAI2Vec learns item embeddings by adapting temporal context definitions to each user's interaction pace, either via personalized session segmentation or continuous decay weighting, and shows gains over static baselines on eight datasets.
David-GRPO improves low-budget RL training for multi-hop QA agents by bootstrapping expert trajectories and converting on-policy partial successes into evidence-coverage signals that increase retrieval depth.
RetrievalAttention approximates full attention in long-context LLMs by retrieving relevant KV vectors from CPU-based ANNS indexes with an attention-aware algorithm, achieving near-full accuracy while accessing only 1-3% of the data.
Constructs multi-video summarization benchmark and evaluates nine MLLMs showing positional bias is domain- and model-dependent with middle positions often weaker and budgets not uniformly fixing it.
DeGRe decouples offline exploration via a lookahead evaluator using beam search and cumulative regression to distill dense supervision into an online generator that approximates optimal reranking sequences with greedy decoding.
Modeling recommender systems as control systems shows that time-optimized fairness interventions can improve overall long-term performance rather than merely trading off against utility.
SafeScreen enforces individualized safety constraints as a prerequisite for video retrieval by using profile extraction, adaptive VideoRAG analysis, and LLM decision-making to approve content for vulnerable users.
DNR is an adversarial denoising neural reranker that extends score error minimization with three objectives to denoise retriever scores and align them with user feedback in two-stage recommender systems.
Fine-tuned LLM acts as ancillary advertiser predictor in production ads RecSys, augmenting retrieval and ranking with measurable offline and online gains.
citing papers explorer
-
Distributional Approximate Nearest Neighbour Search for Uncertainty-Aware Retrieval
DINOSAUR augments ANN indices with sampled embeddings to marginalize uncertainty, recovering standard retrieval at zero uncertainty while expanding coverage for uncertain items.
-
LoopCTR: Unlocking the Loop Scaling Power for Click-Through Rate Prediction
LoopCTR trains CTR models with recursive layer reuse and process supervision so that zero-loop inference outperforms baselines on public and industrial datasets.
-
When More Cores Hurts: The Vector Database Scaling Paradox in HPC
Large-scale HPC evaluation of Qdrant, Milvus, and Weaviate reveals that workload patterns limit scaling and extra cores can reduce throughput, exposing a cloud-to-HPC design mismatch.
-
Gryphon: A Unified Architecture for Semantic-ID Generation and Item-Level Scoring in Industrial Recommendations
Gryphon unifies Semantic-ID generation with direct item-level scoring in a single encoder-decoder pass, attaining higher Recall@1000 than vanilla and collision-resolved generative retrieval baselines on an industrial music dataset while simplifying the candidate pipeline in a live A/B test.
-
FLUID: From Ephemeral IDs to Multimodal Semantic Codes for Industrial-Scale Livestreaming Recommendation
FLUID introduces LUCID semantic codes from a multimodal encoder to retire item IDs in livestreaming rankers, with staged warmup yielding online gains of +0.55% watch duration and +2.05% cold-start views.
-
Learning Behaviorally Grounded Item Embeddings via Personalized Temporal Contexts
TAI2Vec learns item embeddings by adapting temporal context definitions to each user's interaction pace, either via personalized session segmentation or continuous decay weighting, and shows gains over static baselines on eight datasets.
-
Can David Beat Goliath? On Multi-Hop Reasoning with Resource-Constrained Agents
David-GRPO improves low-budget RL training for multi-hop QA agents by bootstrapping expert trajectories and converting on-policy partial successes into evidence-coverage signals that increase retrieval depth.
-
RetrievalAttention: Accelerating Long-Context LLM Inference via Vector Retrieval
RetrievalAttention approximates full attention in long-context LLMs by retrieving relevant KV vectors from CPU-based ANNS indexes with an attention-aware algorithm, achieving near-full accuracy while accessing only 1-3% of the data.
-
A Systematic Evaluation of Positional Bias in Multi-Video Summarization with MLLMs
Constructs multi-video summarization benchmark and evaluates nine MLLMs showing positional bias is domain- and model-dependent with middle positions often weaker and budgets not uniformly fixing it.
-
DeGRe: Dense-supervised Generative Reranking for Recommendation
DeGRe decouples offline exploration via a lookahead evaluator using beam search and cumulative regression to distill dense supervision into an online generator that approximates optimal reranking sequences with greedy decoding.
-
Recommender Systems as Control Systems
Modeling recommender systems as control systems shows that time-optimized fairness interventions can improve overall long-term performance rather than merely trading off against utility.
-
SafeScreen: A Safety-First Screening Framework for Personalized Video Retrieval for Vulnerable Users
SafeScreen enforces individualized safety constraints as a prerequisite for video retrieval by using profile extraction, adaptive VideoRAG analysis, and LLM decision-making to approve content for vulnerable users.
-
Denoising Neural Reranker for Recommender Systems
DNR is an adversarial denoising neural reranker that extends score error minimization with three objectives to denoise retriever scores and align them with user feedback in two-stage recommender systems.
-
Fine-Tuned LLM as a Complementary Predictor Improving Ads System
Fine-tuned LLM acts as ancillary advertiser predictor in production ads RecSys, augmenting retrieval and ranking with measurable offline and online gains.