ALL COLLECTED PAPERS
Papers · page 3
1040 papers · newest first · 50 per page · page 3 of 21
Looking for a title? Use site search.
- UniLatent: Cross-Embodiment Transfer via Latent Observation Alignment
- ReSkill: Selective Self-Improvement for Robot Manipulation
- GUARD: Anomaly-Informed Q-Steering for Generative Robot Policies in Dexterous Manipulation
- Rho: A Foundation for Efficiently Adaptable VLA Models
- Benchmarking LLM Next-Step Recommendations with Knowledge Space Theory
- Exploiting Feature-invariant Scaling Laws for Efficient A/B Experimentation in Recommendation Systems
- SeqFold: Timestamp-Addressable Compressed States for User Action Sequence Backbones
- INTENT: Out-of-Sample, Out-of-Time, and Cold-Start Evaluation on User Event Sequences
- Beyond Interaction Scores: Selecting Feature Interactions via Independent Replication
- LUMIR: Decoupled Multimodal Representation Learning from Heterogeneous Data for Next-POI Recommendation
- A Technique to Model Product Information and User Reviews (MPIUR)
- Auditing LLM Pseudo-Label Distillation for Review Informativeness at E-Commerce Scale
- Intelligent Delivery: Making Every Unit of Compute Serve Better Ads
- Multimodal Graph Learning: A Survey of Models, Benchmarks, and Frontiers
- Data Quality Challenges in Multimodal Tourism Recommender Systems
- DocFS: File Systems as Agentic Reasoning Environments for Complex Multimodal Document Question Answering
- OpticalRAG: Pixel-Space Compression for Token-Efficient Retrieval-Augmented Generation
- FERN: Cross-Benchmark Table Retrieval for Text-to-SQL with Frozen Retrievers and Learned Ranking
- StaRSE: Compact Russian Sentence Embeddings with a Sign-Coded Static Encoder
- CLADE: Category-Level Answering from Deficient Evidence in Retrieval-Augmented Language Models
- Point-in-Time Encoders for Earnings Calls
- Fine-grained authorization for Elasticsearch RAG with SpiceDB
- Graph Visualizations in Prompts for Knowledge Graph Question Answering
- Multimodal Abstention That Preserves Acquired Correct Answers
- Ontology-Guided Knowledge Graph Construction and Robust Evidence Retrieval for Indian Knowledge Systems
- Bursts That Outlast Themselves: Persistent Degradation in Prefix-Cached Agent Serving
- ForeSpark: Joint Draft and Verification Budget Scheduling for Parallel Speculative Decoding
- One-Sided Expert-Parallel All-to-All for Mixture-of-Experts Inference over NVLink
- SHADOWPREFILL: Keeping Your Next Model Warm for Per-Step Model Routing in Agentic LLM Serving
- Decode Token Parallelism: Memory-Efficient Distributed Attention Parallelism for Scalable LLM Decoding
- ADIndex: Layer-Adaptive Sparse Attention Indexing via Group-Level Distillation
- Placing LLM Lookup Tables by Per-Layer Prefetch Deadlines
- VeRL-Omni v0.3.0: Async Training and Broader Multimodal Post-Training
- Validating GPU Platforms with Runtime AI Inventory via the NVIDIA DSX AI Factory
- Manage Kubernetes Clusters for GPU Infrastructure with NVIDIA Kubernetes Engine
- From Video Frames to Robot Meta-Frames: A Unified Latent Interface for World Action Models
- APS-VLA: Action-Guided and Future-Aware Token Pruning for Efficient Vision-Language-Action Models
- CIALLO: Learning Shared Intent Representations for Cross-Embodiment Manipulation
- ReACT: Reflection-Consistent Modulation and Cross-Load Consistency for Humanoid Velocity Tracking Under Asymmetric Loads
- DexSeed: Expanding Human Hand-Object Interactions into Robot Demonstrations for Dexterous Policy Learning
- How Much of Your VLA Is kNN
- DexForesight: Grounding Dexterous Policies with Implicit Spatial Foresight
- LEASH: Stay Safe in Agentic Robotics
- Can AI agents program industrial robots without training data? Berkeley says yes
- NTT Develops Physical AI Technology That Predicts the Future Before Robots Move to Prevent Failures
- TS-GEAR: Taobao Shangou GEnerative Ad Retrieval
- Not All Branches Are Equal: Adaptive Semantic ID Construction for Generative Recommendation
- IntentLens: Grounding Underspecified Multimodal Queries for Recommendation via Tool-Augmented Reasoning
- RoutingTrie: Metadata Routing for Constrained Generative Retrieval
- LEGIT: Live Eligibility Gating over Identifier Tries for Constrained Decoding of Heterogeneous Pages