ALL COLLECTED PAPERS
Papers · page 16
1040 papers · newest first · 50 per page · page 16 of 21
Looking for a title? Use site search.
- OneLatent: Latent Reasoning for Efficient Foundation Recommendation Models
- GenPage: Towards End-to-End Generative Homepage Construction at Netflix
- Coarse-to-Fine Long-term Interest Modeling for Generative Recommendation
- CSG4Rec: Collaborative-Similarity Guided Semantic IDs Tokenization for Generative Sequential Recommendation
- Evaluating LLM-based conversational recommenders with semantic and genre-aware metrics
- Integrating implicit desire fusion for proactive conversational recommendation systems with LLMs
- A Framework for Value-Aligned Modeling and Robust Experimentation
- scikit-rec: A Unified, Extensible Recommendation Library with scikit-rec-agent, a Conversational Interface
- Generalized Position-Based Model: Rethinking Position Weights in Ranking Off-Policy Evaluation
- The Fusion Tax: A Diagnostic Analysis of When Hybrid Retrieval Hurts
- Chunk Recomputation under Real Document Revisions: Measuring Update Cost and Retrieval Quality of Fixed, Recursive, and Content-Defined Chunking
- Lean Finder V2: Semantic Search for Mathlib That Disambiguates User Queries
- CANOPY: Adaptive-Granularity Evidence Compression for Multimodal RAG
- From VDBBench to the Top of MMEB: Full-Stack Optimization of Alibaba Cloud AI Search, from Engine to Model
- Web Search on TokenHub, Tencent Cloud's Model Serving Platform
- Joint Constraint Aggregation for Qualifier-Sensitive Retrieval-Augmented QA
- Compiling Autoregressive LLM Control into Policy-Exact Parallel Inference for Hierarchical RAG
- SurveyGraph: Generating Academic Surveys via Methods-Entity Knowledge Graphs
- Automated Enrichment Analysis with GraphRAG: Efficient Multi-Database ORA Extraction and Biological Interpretation
- llm-d 1.0, an open source stack for distributed inference
- SweepANN: A GPU-Accelerated Large-K Approximate Vector Search for Drug Discovery
- llm-d 1.0 hardens open-source AI inference for production
- Amazon targets Trainium gains with new TorchNeuron developer tool
- FastLLM: a C++ LLM inference engine
- Choosing a Vector Retrieval Database: The Built-in Vector Engine of Tair (Redis Enterprise Edition)
- Scaling LLM Inference via Parallelism: Throughput-Latency Trade-off
- Introducing Superfluid: the local-AI native LLM server for multi-agent inference
- Controllable Generative Recommendation via Guided Token Refinement
- From Habits to Discovery: Deploying LLMs for Personalized Generative Recommendations at Spotify
- Where Do LLMs Learn to Recommend AI?
- Transaction Foundation Models for Retrieval-Augmented Generation over Financial Transaction Data: A Comparative Evaluation with Text Embeddings
- A Diagnostic Study of Faithfulness in Diffusion Language Models for Table-to-Text Generation
- Don't Stop Long-Context Continual Pre-Training Too Early: An Empirical Scaling Law
- CSD: Common-Support Distillation for Cross-Tokenizer Knowledge Transfer
- DiffResearch: Accelerating Deep Research with Diffusion Language Models
- TraceForge: Distilling with Your Own Thinking
- Build more responsive apps with the Decisions API
- Progressive Learning from Content to Relevance to Personalization for CTR Prediction
- Generative Recommenders Forget the Long Tail: Restoring Memorization in Retrieval and Ranking
- PerSPL: Personalized Semi-supervised Preference Learning
- Think Harder Where It Matters: Item-Level Adaptive Recursion for Sequential Recommendation
- RESEARCHHUB: A Personalized Literature Discovery System for Biomedical Preprints
- PreCoMem: Predictive Cognitive Memory for Self-Evolving Long-Term Dialogue Agents
- SOAR: Social and Opinion-Aware Recommendations
- Retrieval Augmented Generation Compositionality
- From LOOP to Graph Exploration: Evolution of an AutoResearch System Architecture for Algorithm Models
- Memory-Centric Continual Learning for AI Agents
- pplx-embed-v2-late Technical Report
- Directional Posterior Feedback Fusion for Query Reformulation in Dense Retrieval
- Scan or Index? large Evidence Coverage, Answer Quality, and Cost in Long-Document RAG