ALL COLLECTED PAPERS

Papers · page 5

1040 papers · newest first · 50 per page · page 5 of 21

Looking for a title? Use site search.

  1. What Matters for LLM Persona Simulation: Signal Form in Cold-Start E-Commerce Advertising2026-11-10 · Personalization
  2. PAGSL: Path-Augmenting Graph Structure Learning for explainable scholar recommendation2026-11-10 · Personalization
  3. Learning from How Users Interpret: Personalizing Recommendation Explanation Order2026-11-10 · Personalization
  4. SPARSEUP: Towards Better Recipes for Training Modern Learned Sparse Retrievers2026-11-10 · AI Search
  5. FondueQA: A Benchmark for Evaluating Parametric Compensation in Multi-Hop QA2026-11-10 · AI Search
  6. MARS: Training Multilingual Search Agents for Retriever-Free Evidence Acquisition2026-11-10 · AI Search
  7. EAGR: Evidence-Guided Adaptive Graph Retrieval2026-11-10 · AI Search
  8. Orthogonal Norm Growth in Two-Tower Retrieval: A Popularity Mechanism for Unified Discovery2026-11-10 · AI Search
  9. Whispers from the Neighbors: Rethinking Caption Consensus as Inference-Time Evidence for Vision-Language Retrieval2026-11-10 · AI Search
  10. Differentially Private GraphRAG: Protecting Relation Connectivity and Semantics2026-11-10 · AI Search
  11. Less Is More: Graph-free Multimodal RAG via Multi-signal Late Fusion2026-11-10 · AI Search
  12. Improving Contextual Retrieval for Long Documents using Semantic Chunking and Hybrid Retrieval Strategies2026-11-10 · AI Search
  13. SkinMind: Equipping Agentic RAG with Human-Inspired Graph Probing for Reliable Dermatology AI2026-11-10 · AI Search
  14. Structure and Lineage Evidence for Vietnamese Statutory Article Retrieval on DRiLL2026-11-10 · AI Search
  15. A Taxonomy-Driven Synthetic Dataset for Retrieval Effectiveness and Fairness Evaluation in Hiring2026-11-10 · AI Search
  16. Inside the Trap: A Renewal Law for Prefix-Cache Collapse in LLM Agent Serving2026-11-10 · Infra
  17. e-means: outperforming k-means (in one-tenth the epochs)2026-11-10 · Infra
  18. ResServe: Accurate and Efficient FP4 LLM Inference with Residue Compensation2026-11-10 · Infra
  19. FOSCAR: Accelerating Decode Attention over 2- and 4-Bit KV Caches through Affine Folding2026-11-10 · Infra
  20. A Controlled Experimental Evaluation of Configuration and Cache Architecture in LLM Serving Engines2026-11-10 · Infra
  21. Accelerating Offloading-Based MoE Inference by Interleaving Concurrent Requests2026-11-10 · Infra
  22. ResQAdam: Residual-Preserving Adaptive Optimization for Memory-Efficient Quantization Aware Training2026-11-10 · Infra
  23. DARIC: A Position-Independent KV Cache Reuse System with Distribution-Aware Recomputation2026-11-10 · Infra
  24. Extending LLDB to Debug Applications That Span CPUs and GPUs2026-11-10 · Infra
  25. CodeQuant2: Enhanced Outlier Mitigation and Adaptive Clustering for Low-Precision LRMs2026-11-10 · Infra
  26. SpecPilot: Autonomous Algorithm Discovery and Systems Optimization for Speculative Decoding2026-11-10 · Infra
  27. PagedMoE: Cross-Precision Expert Caching for Token-Level Dynamic Precision in SSD-Resident MoE Inference2026-11-10 · Infra
  28. Supermicro Launches KV Cache Solution with IBM and NVIDIA Demonstrating Significant Inference Performance Benefits2026-11-10 · Infra
  29. Should You Split Decode? Disaggregation Across Future Models and Accelerators2026-11-10 · Infra
  30. Meituan-Robotics-0: A Vision-Language-Action Foundation Model for Desktop Manipulation2026-11-10 · Embodied AI
  31. On Agentic Manipulation Policies2026-11-10 · Embodied AI
  32. VICTR: Value-Informed In-Context Learning for Vision-Language-Action Models2026-11-10 · Embodied AI
  33. SURE:Spatiotemporal Uncertainty Representation for Efficient Vision-Language-Action Learning2026-11-10 · Embodied AI
  34. ForPC: Force-Aware Whole-Body Control for Precise Humanoid Cart Pushing2026-11-10 · Embodied AI
  35. Horizon-Coupled Obstacle Guidance for Relative-Action Diffusion Policies2026-11-10 · Embodied AI
  36. STEP: Spatiotemporal Training with Explicit Prediction for Perceptive Humanoid Locomotion2026-11-10 · Embodied AI
  37. ODEAction: From Predicting Chunks to Evolving Actions2026-11-10 · Embodied AI
  38. DKWBC: Decoupling Motion Tracking and Balancing for Humanoid Whole-Body Control2026-11-10 · Embodied AI
  39. Spatial-UMI-Dream: Scaling World Action Models with Metric Geometry for UMI Manipulation2026-11-10 · Embodied AI
  40. Should the Action Expert Train the VLM? Action-Token Supervision and Gradient Routing in Mixture-of-Transformer VLAs2026-11-10 · Embodied AI
  41. From Pixels to Actions -- Towards Native Vision-Language-Action Policies2026-11-10 · Embodied AI
  42. WorldContact: A Contact-Centric World Model for Scalable Robot Learning2026-11-10 · Embodied AI
  43. SLA: Scaling Spatial-Language-Action Model via Continual Pre-training2026-11-10 · Embodied AI
  44. Boston Dynamics adds wheels to Atlas humanoid to test whole-body control2026-11-10 · Embodied AI
  45. Make a Robot Arm Feel Weightless with NVIDIA Holoscan 52026-11-10 · Embodied AI
  46. AI WAVE Wrap-Up: AgiBot Reports Results of Its 24-Hour Convenience-Store Livestream, Moving Physical AI Into Real Settings2026-11-10 · Embodied AI
  47. RecGroupMemory: Feedback-Aware Cohort Memory for E-Commerce Recommendation2026-11-09 · Generative
  48. Preprocessing Choices in Fine-Tuning Data Matter: Utility and Demographic Sensitivity in LLM-Based Recommendation2026-11-09 · Generative
  49. Generative Chain of Behavior for User Trajectory Prediction2026-11-09 · Generative
  50. SIDRec: End-to-End Semantic ID Representation and Modeling for Recommendation2026-11-09 · Generative