全部收录论文
论文 · 第 96 页
共 7039 篇 · 按日期新到旧 · 每页 50 篇 · 第 96 / 141 页
查找论文请用站内搜索。
- How the NVIDIA Vera Rubin Platform is Solving Agentic AI's Scale-Up Problem
- AgentLens: Revealing the Lucky Pass Problem in SWE-Agent Evaluation
- Deep Reasoning in General Purpose Agents via Structured Meta-Cognition
- Agent-BRACE: Decoupling Beliefs from Actions in Long-Horizon Tasks via Verbalized State Uncertainty
- Revisiting DAgger in the Era of LLM-Agents
- An Empirical Study of Automating Agent Evaluation
- EVA-Bench: A New End-to-end Framework for Evaluating Voice Agents
- Taming Extreme Tokens: Covariance-Aware GRPO with Gaussian-Kernel Advantage Reweighting
- IdeaForge: A Knowledge Graph-Grounded Multi-Agent Framework for Cross-Methodology Innovation Analysis and Patent Claim Generation
- AutoScout24 scales engineering with AI-powered workflows
- RoboEvolve: Co-Evolving Planner-Simulator for Robotic Manipulation with Limited Data
- MinT: Managed Infrastructure for Training and Serving Millions of LLMs
- SOMA: Efficient Multi-turn LLM Serving via Small Language Model
- HEBATRON: A Hebrew-Specialized Open-Weight Mixture-of-Experts Language Model
- ReAD: Reinforcement-Guided Capability Distillation for Large Language Models
- FeatCal: Feature Calibration for Post-Merging Models
- A Study on Hidden Layer Distillation for Large Language Model Pre-Training
- Freeze Deep, Train Shallow: Interpretable Layer Allocation for Continued Pre-Training
- Qwen-Image-VAE-2.0 Technical Report
- AnyFlow: Any-Step Video Diffusion Model with On-Policy Flow Map Distillation
- Benchmarking the Open Science Data Federation services to develop XRootD best practices
- Design Your Ad: Personalized Advertising Image and Text Generation with Unified Autoregressive Models
- ORBIT: Preserving Foundational Language Capabilities in GenRetrieval via Origin-Regulated Merging
- Reel Friends: Building Social Discovery that Scales to Billions
- Democratizing News Recommenders: Modeling Multiple Perspectives for News Candidate Generation with VQ-VAE
- Very Efficient Listwise Multimodal Reranking for Long Documents
- Test-Time Compute for Dense Retrieval: Agentic Program Generation with Frozen Embedding Models
- Task-Adaptive Embedding Refinement via Test-time LLM Guidance
- Beyond Similarity Search: Tenure and the Case for Structured Belief State in LLM Memory
- Make It Long, Keep It Fast: End-to-End 10k-Sequence Modeling at Billion Scale on Douyin Recommendation
- LEAPS: An LLM-Empowered Adaptive Plugin in Taobao AI Search
- Conditional Memory Enhanced Item Representation for Generative Recommendation
- A Cascaded Generative Approach for e-Commerce Recommendations
- TwiSTAR: Think Fast, Think Slow, Then Act — Generative Recommendation with Adaptive Reasoning
- RecRM-Bench: Benchmarking Multidimensional Reward Modeling for Agentic Recommender Systems
- HSUGA: LLM-Enhanced Recommendation with Hierarchical Semantic Understanding and Group-Aware Alignment
- FedMM: Federated Collaborative Signal Quantization for Multi-Market CTR Prediction
- Debiasing Message Passing to Mitigate Popularity Bias in GNN-based Collaborative Filtering
- Localization Boosting for Growth Markets: Mitigating Cross-Locale Behavioral Bias in Learning-to-Rank
- MIRA: An LLM-Assisted Benchmark for Multi-Category Integrated Retrieval
- Caraman at SemEval-2026 Task 8: Three-Stage Multi-Turn Retrieval with Query Rewriting, Hybrid Search, and Cross-Encoder Reranking
- Much of Geospatial Web Search Is Beyond Traditional GIS
- AgentDisCo: Towards Disentanglement and Collaboration in Open-ended Deep Research Agents
- ClinicalBench: Stress-Testing Assertion-Aware Retrieval for Cross-Admission Clinical QA on MIMIC-IV
- Matching Meaning at Scale: Evaluating Semantic Search for 18th-Century Intellectual History through the Case of Locke
- EHR-RAGp: Retrieval-Augmented Prototype-Guided Foundation Model for Electronic Health Records
- MedHopQA: A Disease-Centered Multi-Hop Reasoning Benchmark and Evaluation Framework for LLM-Based Biomedical Question Answering
- Context Convergence Improves Answering Inferential Questions
- Transform Video Into Instantly Searchable, Actionable Intelligence with AI Agents and Skills
- ReVision: Scaling Computer-Use Agents via Temporal Visual Redundancy Reduction