·
DataBubble
  • Home
  • Models
  • News
  • Compare
  • Boards
  • Pricing
  • About
  • Newsletter
  • Methodology
  • Contact
Latest
A satellite just learned to find things on its own — here’s what that means1h◆The AI layoff wave is becoming a powder keg5h◆ChronoID: Infusing Explicit Temporal Signals into Semantic IDs for Generative Recommendation9h◆Small LLMs: Pruning vs. Training from Scratch9h◆EqCollide: Equivariant and Collision-Aware Deformable Objects Neural Simulator9h◆Towards Efficient Large Language Reasoning Models via Extreme-Ratio Chain-of-Thought Compression9h◆GAGPO: Generalized Advantage Grouped Policy Optimization9h◆Moonlight in Latent Space: Chirality and Structural Correspondence Between Beethoven's Op. 27 No. 2 and Machine Learning Mechanisms9h◆Efficient Temporal Modeling for Mobile Sleep Staging via Lightweight Random Attention9h◆Numbers Already Carry Their Own Embeddings9h◆From Prompts to Responses: Dual-Sided Data Leakage and Defense in Split Large Language Models9h◆Universal Manipulation Exoskeleton: Learning Compliant Whole-body Policies with Real-time Torque Feedback9h◆When Good Verifiers Go Bad: Self-Improving VLMs Can Regress on New Tasks9h◆From Self-Supervised Speech Models to Mixture-of-Experts for Robust Anti-Spoofing9h◆Giving AI a Headache: Acoustic Adversarial Attacks to Computer Vision Applications9h◆Simulating Students' Java Programming Errors with Large Language Models9h◆CoRe: A Continuously Reward-Finetuned LLM Query Rewriter for Multi-Stage Context-Aware Relevance in Web-Scale Video Search9h◆A theoretical model for task routing in mixture-of-expert transformers9h◆Beyond task performance: Decoding bioacoustic embeddings with speech features9h◆A Complexity Measure for Active Learning in Multi-group Mean Estimation9h◆A satellite just learned to find things on its own — here’s what that means1h◆The AI layoff wave is becoming a powder keg5h◆ChronoID: Infusing Explicit Temporal Signals into Semantic IDs for Generative Recommendation9h◆Small LLMs: Pruning vs. Training from Scratch9h◆EqCollide: Equivariant and Collision-Aware Deformable Objects Neural Simulator9h◆Towards Efficient Large Language Reasoning Models via Extreme-Ratio Chain-of-Thought Compression9h◆GAGPO: Generalized Advantage Grouped Policy Optimization9h◆Moonlight in Latent Space: Chirality and Structural Correspondence Between Beethoven's Op. 27 No. 2 and Machine Learning Mechanisms9h◆Efficient Temporal Modeling for Mobile Sleep Staging via Lightweight Random Attention9h◆Numbers Already Carry Their Own Embeddings9h◆From Prompts to Responses: Dual-Sided Data Leakage and Defense in Split Large Language Models9h◆Universal Manipulation Exoskeleton: Learning Compliant Whole-body Policies with Real-time Torque Feedback9h◆When Good Verifiers Go Bad: Self-Improving VLMs Can Regress on New Tasks9h◆From Self-Supervised Speech Models to Mixture-of-Experts for Robust Anti-Spoofing9h◆Giving AI a Headache: Acoustic Adversarial Attacks to Computer Vision Applications9h◆Simulating Students' Java Programming Errors with Large Language Models9h◆CoRe: A Continuously Reward-Finetuned LLM Query Rewriter for Multi-Stage Context-Aware Relevance in Web-Scale Video Search9h◆A theoretical model for task routing in mixture-of-expert transformers9h◆Beyond task performance: Decoding bioacoustic embeddings with speech features9h◆A Complexity Measure for Active Learning in Multi-group Mean Estimation9h◆
News/CoRe: A Continuously Reward-Finetuned LLM Query Rewriter for Multi-Stage Context-Aware Relevance in Web-Scale Video Search
arxiv
PublishedJune 15, 2026 at 4:00 AM
—neutral

CoRe: A Continuously Reward-Finetuned LLM Query Rewriter for Multi-Stage Context-Aware Relevance in Web-Scale Video Search

Source
arxiv.orgfull article ↗
Read on arxiv→
Publisher summary· verbatim

arXiv:2606.14127v1 Announce Type: cross Abstract: LLM-based query rewriters in production face a tension: the training reward must reflect how the rewrite is consumed by the production ranker, yet the training procedure must be cheap enough to support continuous redeployment as data drifts. We prese

Stay posted· Newsletter

A 5-min weekly brief — top movers, price watch, story of the week.

// no spam · unsubscribe one-click · free forever

Discussion
Source
↗
arxiv
Read original ↗All from arxiv →

No replies yet. Be first.

Source
↗
arxiv
Read original ↗All from arxiv →

Related coverage

More from ARXIV
arxivChronoID: Infusing Explicit Temporal Signals into Semantic IDs for Generative Recommendation9harxivSmall LLMs: Pruning vs. Training from Scratch9harxivEqCollide: Equivariant and Collision-Aware Deformable Objects Neural Simulator9harxivTowards Efficient Large Language Reasoning Models via Extreme-Ratio Chain-of-Thought Compression9h
The Bubble Brief
WEEKLY

Read AI insights every Tuesday — top movers, new releases, story of the week.

// no spam · unsubscribe one-click · free forever

Originally published on arxiv ↗
HomeModelsNews