全部收录论文
论文 · 第 109 页
共 7039 篇 · 按日期新到旧 · 每页 50 篇 · 第 109 / 141 页
查找论文请用站内搜索。
- TEMPO: Scaling Test-time Training for Large Reasoning Models
- Personalized Benchmarking: Evaluating LLMs by Individual Preferences
- Prioritizing the Best: Incentivizing Reliable Multimodal Reasoning by Rewarding Beyond Answer Correctness
- LoopCTR: Unlocking the Loop Scaling Power for Click-Through Rate Prediction
- CS3: Efficient Online Capability Synergy for Two-Tower Recommendation
- A Mechanism and Optimization Study on the Impact of Information Density on User-Generated Content Named Entity Recognition
- GraphRAG-IRL: Personalized Recommendation with Graph-Grounded Inverse Reinforcement Learning and LLM Re-ranking
- From Top-1 to Top-K: A Reproducibility Study and Benchmarking of Counterfactual Explanations for Recommender Systems
- CAST: Modeling Semantic-Level Transitions for Complementary-Aware Sequential Recommendation
- AutoAdapt: Automated domain adaptation for large language models
- VoteGCL: Enhancing Graph-based Recommendations with Majority-Voting LLM-Rerank Augmentation
- Dual-View Training for Instruction-Following Information Retrieval
- ECLASS-Augmented Semantic Product Search for Electronic Components
- RARE: Redundancy-Aware Retrieval Evaluation Framework for High-Similarity Corpora
- Semantic Needles in Document Haystacks: Sensitivity Testing of LLM-as-a-Judge Similarity Scoring
- Diagnosable ColBERT: Debugging Late-Interaction Retrieval Models Using a Learned Latent Space as Reference
- LogosKG: Hardware-Optimized Scalable and Interpretable Knowledge Graph Retrieval
- Mango: Multi-Agent Web Navigation via Global-View Optimization
- Evaluation-driven Scaling for Scientific Discovery
- Temporal Leakage in Search-Engine Date-Filtered Web Retrieval: A Retrospective Forecasting Case Study
- What Makes an LLM a Good Optimizer? A Trajectory Analysis of LLM-Guided Evolutionary Search
- ClawNet: Human-Symbiotic Agent Network for Cross-User Autonomous Cooperation
- Chat2Workflow: A Benchmark for Generating Executable Visual Workflows with Natural Language
- From Verbatim to Gist: Distilling Pyramidal Multimodal Memory via Semantic Information Bottleneck for Long-Horizon Video Agents
- Characterizing AlphaEarth Embedding Geometry for Agentic Environmental Reasoning
- STAR-Teaming: A Strategy-Response Multiplex Network Approach to Automated LLM Red Teaming
- Alloc-MoE: Budget-Aware Expert Activation Allocation for Efficient Mixture-of-Experts Inference
- Open-TQ-Metal: Fused Compressed-Domain Attention for Long-Context LLM Inference on Apple Silicon
- ShadowPEFT: Shadow Network for Parameter-Efficient Fine-Tuning
- Micro Language Models Enable Instant Responses
- Two-dimensional early exit optimisation of LLM inference
- Don't Waste Bits! Adaptive KV-Cache Quantization for Lightweight On-Device LLMs
- KV Cache Offloading for Context-Intensive Tasks
- The Generative Recommender Behind Shopify's Commerce Engine
- R3A: Reinforced Reasoning for Relevance Assessment for RAG in User-Generated Content Platforms
- HeadRank: Decoding-Free Passage Reranking via Preference-Aligned Attention Heads
- Bridging Language and Items for Retrieval and Recommendation: Benchmarking LLMs as Semantic Encoders
- LLMAR: A Tuning-Free Recommendation Framework for Sparse and Text-Rich Industrial Domains
- Bayesian Active Learning with Gaussian Processes Guided by LLM Relevance Scoring for Dense Passage Retrieval
- Transparent and Controllable Recommendation Filtering via Multimodal Multi-Agent Collaboration
- COSEARCH: Joint Training of Reasoning and Document Ranking via Reinforcement Learning for Agentic Search
- Latent Preference Modeling for Cross-Session Personalized Tool Calling
- Hypercomplex Knowledge Graph-Aware Recommendation
- RankUp: Towards High-rank Representations for Large Scale Advertising Recommender Systems
- Modular Representation Compression: Adapting LLMs for Efficient and Effective Recommendations
- Modernizing the Facebook Groups Search to Unlock the Power of Community Knowledge
- HORIZON: A Benchmark for In-the-wild User Behaviour Modeling
- Diagnosing LLM-based Rerankers in Cold-Start Recommender Systems: Coverage, Exposure and Practical Mitigations
- Response-Aware User Memory Selection for LLM Personalization
- Modeling User Exploration Saturation: When Recommender Systems Should Stop Pushing Novelty