全部收录论文
论文 · 第 100 页
共 7039 篇 · 按日期新到旧 · 每页 50 篇 · 第 100 / 141 页
查找论文请用站内搜索。
- OpenSearch-VL: An Open Recipe for Frontier Multimodal Search Agents
- DoGMaTiQ: Automated Generation of Question-and-Answer Nuggets for Report Evaluation
- Reproducing Complex Set-Compositional Information Retrieval
- TabEmbed: Benchmarking and Learning Generalist Embeddings for Tabular Understanding
- Caesar: Deep Agentic Web Exploration for Creative Answer Synthesis
- SCOUT: Active Information Foraging for Long-Text Understanding with Decoupled Epistemic States
- Meituan LongCat-Flash-Thinking-2601: Open-Source SOTA on Agentic Search & Tool Use
- GEM: Graph-Enhanced Mixture-of-Experts with ReAct Agents for Dialogue State Tracking
- ProMMSearchAgent: A Generalizable Multimodal Search Agent Trained with Process-Oriented Rewards
- Free Energy-Driven Reinforcement Learning with Adaptive Advantage Shaping for Unsupervised Reasoning in LLMs
- CreativityBench: Evaluating Agent Creative Reasoning via Affordance-Based Tool Repurposing
- SWE-WebDevBench: Evaluating Coding Agent Application Platforms as Virtual Software Agencies
- Adapt to Thrive! Adaptive Power-Mean Policy Optimization for Improved LLM Reasoning
- RLearner-LLM: Balancing Logical Grounding and Fluency in LLMs via Hybrid DPO
- Distilling Bayesian Belief States into Language Models for Auditable Negotiation
- Telegraph English: Semantic Prompt Compression via Structured Symbolic Rewriting
- The First Token Knows: Single-Decode Confidence for Hallucination Detection
- NVIDIA: Real-Time Performance Monitoring and Faster Debugging with NCCL Inspector and Prometheus
- Gradients with Respect to Semantics Preserving Embeddings Tell the Uncertainty of Large Language Models
- Paraphrase-Induced Output-Mode Collapse: When LLMs Break Character Under Semantically Equivalent Inputs
- Lightning Unified Video Editing via In-Context Sparse Attention
- PhysForge: Generating Physics-Grounded 3D Assets for Interactive Virtual World
- zkGPT: An Efficient Non-interactive Zero-knowledge Proof Framework for LLM Inference
- Stream-T1: Test-Time Scaling for Streaming Video Generation
- D-OPSD: On-Policy Self-Distillation for Continuously Tuning Step-Distilled Diffusion Models
- Beyond Similarity Search: A Unified Data Layer for Production RAG Systems
- OpenSeeker-v2: Pushing the Limits of Search Agents with Informative and High-Difficulty Trajectories
- Revisiting General Map Search via Generative Point-of-Interest Retrieval
- Sparse Memory Finetuning as a Low-Forgetting Alternative to LoRA and Full Finetuning
- RAG over Thinking Traces Can Improve Reasoning Tasks
- Rethinking Reasoning-Intensive Retrieval: Evaluating and Advancing Retrievers in Agentic Search Systems
- Revisiting Graph-Tokenizing Large Language Models: A Systematic Evaluation of Graph Token Understanding
- A Benchmark for Interactive World Models with a Unified Action Generation Framework
- STORM: A Spatio-Temporal Factor Model Based on Dual Vector Quantized Variational Autoencoders for Financial Trading
- Frozen LVLMs for Micro-Video Recommendation: A Systematic Study of Feature Extraction and Fusion
- Federated User Behavior Modeling for Privacy-Preserving LLM Recommendation
- WPGRec: Wavelet Packet Guided Graph Enhanced Sequential Recommendation
- LambdaRankIC: Directly Optimizing Rank IC for Financial Prediction
- Ensembles at Any Cost? Accuracy-Energy Trade-offs in Recommender Systems
- Aspect-Aware Content-Based Recommendations for Mathematical Research Papers
- Adaptive Long-term Embedding with Denoising and Augmentation for Recommendation
- CPGRec+: A Balance-oriented Framework for Personalized Video Game Recommendations
- Domain-Adaptive Dense Retrieval for Brazilian Legal Search
- Evaluating Reasoning Models for Queries with Presuppositions
- Geometric Deviation as an Unsupervised Pre-Generation Reliability Signal: Probing LLM Representations for Answerability
- SERE: Structural Example Retrieval for Enhancing LLMs in Event Causality Identification
- SAM-NER: Semantic Archetype Mediation for Zero-Shot Named Entity Recognition
- Rose-SQL: Role-State Evolution Guided Structured Reasoning for Multi-Turn Text-to-SQL
- CuraView: A Multi-Agent Framework for Medical Hallucination Detection with GraphRAG-Enhanced Knowledge Verification
- How Language Models Process Negation