ALL COLLECTED PAPERS
Papers · page 4
1040 papers · newest first · 50 per page · page 4 of 21
Looking for a title? Use site search.
- SituRecBench: Evaluating Frontier Models as Situated Recommendation Assistants in 3D Environments
- Close and Sort: Exact Maximum-Likelihood Aggregation of Cyclic Rank-Two Preferences
- SepLRM: A Foundation Model Paradigm for Recommendation
- Proactive Dimension-Adaptive Denoising for Graph Collaborative Filtering via Representation Coherence
- OptiCover: A Scalable and Multi-Surface Framework for Cold-Start Visual Optimization under Semantic Constraints
- Query- and Candidate-Aware Long User Sequence Modeling for Sponsored Product Ranking in Search
- Slim Foundation Models for Latency-Critical Recommendation Serving
- CHO-Bench: How Do Context Hints Affect Ad Rankings in LLM Advertising?
- Not Yet in the Profile: Uncertainty-Aware Dynamic User Profiling by Learning from Future Interactions
- Your Algorithm: Giving People More Ways to Personalize Facebook Recommendations
- An Adaptive, Context-Aware, and Stacked Attention Network-Based Recommendation System to Capture Users' Temporal Preference
- UCB-min: Combining Bandits Under Variance Heterogeneity (Extended Version)
- Yuanbao-Reranker: Document-Grounded Synthesis and Preference Distillation for Text Reranking
- Beyond Ranking: Are Decision Models Calibrated Relevance Scorers?
- Lightfoot: Graph Retrieval-Augmented Generation with Exact, Model-Free Document Deletion
- PatternBloom: Empowering Agentic RAG with Externalized RL-Distilled Graph Patterns
- Search-by-Answer Bias in Retrieval Models
- CoRA-Bench: Evaluating Evidence Preservation by Context Selectors Under Token Budgets
- TRIAD: Multimodal Retrieval across Abstraction, Constraints, and State
- NIFT-SQL: Customer-Supervised Table Scoring for Enterprise Text-to-SQL Retrieval
- Two-Sided Conformal Evidence Sets for Retrieval-Augmented Generation
- Calibrating Document-Local Boundaries for Contextual Chunk Retrieval
- RecoGEM: A Serving System for Production-Scale Generative Recommendation
- Firepool: Brokering Warm GPU Capacity for Agentic and RL Workloads at LinkedIn
- How We Built TLX: A Hardware-Native GPU Compiler for Production ML at Scale
- Detent: Batch-Invariant LLM Serving and RL Rollouts at Near-Stock Speed
- Multi-GPU MoE Inference with Adaptive Expert Offloading
- PACE: Keeping the Right Tokens in the KV Cache Is Not Enough for Long-Horizon LLM Agents
- Hibana: Fast Agentic Inference on Unified-Memory Devices
- MACaQ: Fast, Model Agnostic Calibrated Quantization for Low-Precision Weights and Activations
- Meituan LongCat-2.5 Officially Open-Sourced: From Seeing to Arriving
- Start and Restore GPU Workloads in Seconds with NVIDIA Snapshot
- Practice Makes Precise: At CoRL, NVIDIA and Partners Reveal How Robots Rehearse Delicate Work in Simulation
- Learn the Task, Not the Schedule: Reducing Spurious Cross-Arm Coupling in Bimanual Imitation Learning
- Kimodo-Policy: Learning Kinematic Action Models for Humanoid Loco-Manipulation
- SimDuoReal: Object-Centric Bimanual Policy for Emergent Dexterity
- Tactile Sensors Are an Effective Substitute for Wrist Cameras in Contact-Rich or Occluded Manipulation
- Compass 1: Towards Open-World and Persistent Embodied Navigation from Monocular RGB Videos
- Gemini Robotics 2.5 accelerates real-world general dexterity
- SWAM: Scaling World Action Models with Cross-Modal Alignment
- Decoupled Asynchronous System for Humanoids (DASH): Latency-Agnostic Scaling of Vision-Language-Action Models for Humanoid Manipulation
- Sample-Efficient Reinforcement Learning for Policy Improvement via Flow-Reversed Action Anchors
- Generative Search and Recommendation at Shopify
- Rethinking Latent Reasoning for Generative Recommendation: Beyond Teacher-Generated CoT and Recurrent Hidden-State Feedback
- CascadeRec: Deployed Adaptive LLM Compute Allocation for Multi-Tenant Content Recommendation
- SteerGR: Steering Generative Recommendation via Sparse Autoencoders for Controllable Game Discovery
- Memory-Aware Multi-Agent Architecture with LLM-based Orchestration for Conversational Recommendation
- STCRank: Spatio-temporal Collaborative Ranking for Interactive Recommender System at Kuaishou E-shop
- SAGE-PAIR: Source-Pretrained Routed Residual Adaptation for Sparse-Feedback Recommendation
- Not Your Diary, Just Your Topic: Grading the Wrong-User Control