ALL COLLECTED PAPERS
Papers · page 11
1040 papers · newest first · 50 per page · page 11 of 21
Looking for a title? Use site search.
- DeFT-RAG: Incrementally Decomposing Multi-Hop Questions into Self-Contained Sub-Questions with Reusable Answers
- Decompose, Estimate, Select: Coverage-Aware Context Construction for Long-Form RAG
- xPRT: Cross-Passage Retrieval Pretraining
- Glance: The Generator Is Its Own Reranker
- How Specific Do I Need to Be? Effects of User Query Underspecification on Deep Research Agents
- Relevance-Guided Residual Calibration for Spectral Compression of Dense Retrieval Embeddings
- Quantum-Inspired Pairwise Ranking Aggregation via Active LLM Feedback
- Feedback-Assisted Trust Propagation over Document Relation Graphs for Retrieval-Augmented Generation
- TableTune: Measured, Self-Correcting Draft-Length Tables for Dynamic Speculative Decoding
- FlatCake: A Flat KVCache Storage Architecture for LLM Serving
- ConfluxServe: Reconciling Resource Utilization and Parallelism Efficiency across Prefill and Decode in LLM Serving
- Nemotron 3.5 Super and Lightning: Open, Efficient Mixture-of-Experts Hybrid Mamba-Transformer Models for Agentic AI
- The Endgame of FSDP Communication: Layout-Aware Collectives on Copy Engines, RDMA, and NVSwitch
- Rimuru: Unified Memory Management for Modern LLM Serving via Elastic Expert Offloading
- SGLang security update: improving request isolation
- DualQuant: Dual-scale Calibration-free Weight-and-Activation Quantization for LLMs
- A Unified Hessian-Guided Framework for Post-Training Quantization
- DWISE: Denoising Workload-Informed Scheduling Engine
- UMI-Live for In-The-Wild Bimanual Robotics Data Collection
- FORGE: Feasible Online Reduced-Order Reference Generation and Whole-Body Execution for Agile Humanoid Locomotion
- Vector-Quantized World Model: Latent Feedback Motion Planning for Robot Manipulation
- Catch It All!: Generalizable Dynamic Catching with a Dexterous Hand
- METATRON: A Promptable Whole-Body Execution Layer for Humanoids
- ProWorld: Multi-View World Model with Proprioceptive Feedback for Closed-Loop Policy Evaluation
- Cross-Controller Transfer via In-Context Behavior Adaptation
- LocoManiLab: A Unified Testbed for Data, Policies, Controllers, and Deployment in Humanoid Loco-Manipulation
- JEDI: Joint-Embedding Demonstration Compression for In-Context Imitation Learning
- AgiBot Innovation Day 2026: Full-Stack Releases for Real-World Embodied Deployment
- Multi-Branch Cooperation Networks for Enhanced Click-Through Rate Prediction in Large-Scale E-Commerce Search
- When Is Additional Retrieval Worthwhile? A Cost-Aware Study of Evidence Gain and Answer Reliability in RAG
- Governed Sovereign RAG for Public Administration: Tripartite Epistemic Routing, Facet-Guided Clarification, and Deterministic Numeric Verification in Citizen Services
- SpectRAG: Weighted Chunk Graphs for Token-Budgeted Context Selection in Multi-Hop Retrieval-Augmented Generation
- Structure Is All You Need to Reuse: Accelerating GraphRAG via Meta-Structure-Aware KV Caching
- Announcing Humming: Fast, Flexible Kernels for Quantized Inference
- Day 0 support for Mistral Large 4 on vLLM
- vLLM Delivers Day-0 Support for MiniMax-M3.1-Flash
- Introducing vLLM TorchTPU
- Black-Box Embedding Inversion Attack on Vector Databases
- SuperMimic: Scaling Humanoid Whole-Body Control with One Differentiable World Model
- Causal Analysis of Robot Foundation Models Enables Efficiency Gains
- Compositional Diffusion Policy for Vision–Language–Action Agents
- Online Robot Manipulation Error Detection and Description
- HARP-Bench: Benchmarking Robot Manipulation Around Active Humans
- Towards Human-like Physical Intelligence: Lifelong Vision-Language-Action Learning for Robotic Manipulation
- HARP-VLA: Human-Robot Aligned Representation Learning for Vision-Language-Action Model
- SERF: Spatiotemporal Environment and Robot Feature Map for Long-Horizon Mobile Manipulation
- In-Context Learning World Models for Robot Dual-Arm Manipulation of Soft Garment with Partial Observations
- AGIBOT introduces Worken to measure robot productivity at AGIBOT Innovation Day 2026
- PailitaoMMSearch2.0 Technical Report: Scaling Generative Retrieval to Unified End-to-End Multimodal Search
- Latent Residual Reasoning for Ranking in Generative Recommendation