ALL COLLECTED PAPERS
Papers · page 8
1040 papers · newest first · 50 per page · page 8 of 21
Looking for a title? Use site search.
- IntentGEO: Intent-aware Generative Engine Optimization for Recommendation
- Voluntary Servitude: Weaponized Safety Warning Mechanisms for Controlling AI Agents
- Auditing a Model-Hub Benchmark: Data Quality, Training Budgets, and Side Information in HuggingBench
- When Category Means Move: A Paired-Support Audit of Recommendation Logs with Random Insertions
- Learning to Rank Explanations for Recommendation with Language Models
- DualEvolve: Dual-Level Self-Evolution of Mechanism and Orchestration for Recommendation
- DualClusterNet: Personalized Pattern-Space Composition for Next-POI Recommendation
- Dataset Recommendation for Heterogeneous and Dynamic Scholarly Graphs via Multimodal Representation Learning
- From Logs to Faults: Reference-Free Fault Localization for Retrieval-Augmented Generation Pipelines
- QueryFlow: Multi-Hop Graph Retrieval with Adaptive Query Evolution
- Scaling Laws For Data-Constrained Dense Retrieval
- Characterizing Adversarial GEO via Implicit Brand Injection
- Factorized MLLM Embeddings for Composed Image Retrieval
- EMBERS: Empirically Motivated Robustness Testing of Deep Research Systems via Defect-Guided Fuzzing
- When Self-Verification Hurts: Calibrated Answer Repair for Financial Question Answering
- Shared Geometry As A Rosetta Stone: Cross-Modal Alignment Without Paired Data
- SPELUNKA: A Framework for Finding Unanticipated Associations in Vision-Language Models
- Reliability Stress Testing of RAG Retrieval under Query-Relevant Corpus Poisoning
- Look Before You Launch: Learned Throughput Prediction for Hardware Selection in a Production Training Fleet
- Modular and Efficient Approximate Nearest Neighbors Search with Vectorium and kANNolo
- FlagRot: Selective Rotation for Low-Bit KV Caches
- Testing Processor Contracts in Speculative Decoding Engines
- What Sets the Serving Speed of Looped Language Models? Measurements and Optimizations Graded by Exactness
- HybridSpec: Throughput-Aware Speculative Decoding for Hybrid GDN-MoE Models
- ROCm InferaSim: Cut LLM Serving Trial Costs and Deploy the Best Configuration
- EpiLoRA: Fusing Many LoRA Adapters into Low-Precision GEMMs for Serving and RL
- GC-MoE: Overlapping Expert-Parallel Token Dispatch with FP8/FP4 Grouped GEMM via CUDA Green Contexts
- Diagnose Distributed AI Workload Failures with NVIDIA Attribution
- AIRoA-0: Long-Horizon, Precise, Cross-Embodiment Manipulation from Handheld Data
- RAFT: Reasoning-Aligned Fine-Tuning Improves Robustness of VLA Post-Training
- Pretraining Knows What, Simulation Teaches How: Compositional Generalization for Agentic Robotics
- Asynchronous Robot Policies
- DexHOT: Learning Hand-Object Configuration Transfer for Dexterous Manipulation
- FEIJOA: Task-Driven Grounding and Execution for Mobile Manipulation
- All-For-One: Distilling Visual Foundation Models to a Fast, Memory-Efficient Visuomotor Policy
- Robot-Matched Soft Fingers for UMI Data Collection: Lessons from 100 Hours of Pick and Place
- GUILD: Guided Iterative Data Collection for Imitation Learning
- LiberAI Unveils Liber-0, a World Action Model That Grounds Human Experience in Robot Action
- Diverse-Teacher On-Policy Distillation for Generative Recommendation
- Utility-Aware Generative Recommendation: Utility-Enriched Semantic Codes and Utility-Guided Decoding
- Large Language Model as Universal Retriever in Industrial-Scale Recommender System
- Beyond Semantic IDs: Atomic Creator Tokens for Large-Scale Generative Recommendation
- Where Beam Search Loses Top-Ranked Items:First-Step Coverage in Generative Recommendation
- Think Globally, Generate Personally: Multi-View Thinking with Adaptive Generation for Generative Recommendation
- Beyond Uniform Token Training: A Multi-Target Framework for Learning Token-Weighted Objectives in Generative Recommenders
- Search-Aware On-Policy Self-Distillation with Sibling Alignment for Generative Recommendation
- HiGenTrans: Hierarchical LLM Knowledge Transfer for Generative Recommendation
- Neutralizing Popularity Bias in LLM-based Recommendation via Counterfactual Reasoning Guidelines
- Numerical Embeddings for CTR Prediction: A Taxonomy, Unified Benchmark, and Open-Source FuxiCTR Extension
- Improving Ads Ranking Models with Auxiliary Supervision: Techniques and Insights