全部收录论文
论文 · 第 133 页
共 7039 篇 · 按日期新到旧 · 每页 50 篇 · 第 133 / 141 页
查找论文请用站内搜索。
- CMRAG: Co-modality-based visual document retrieval and question answering
- Beyond Rows to Reasoning: Agentic Retrieval for Multimodal Spreadsheet Understanding and Editing
- Exploratory Memory-Augmented LLM Agent via Hybrid On- and Off-Policy Optimization
- ReflexiCoder: Teaching Large Language Models to Self-Reflect on Generated Code and Self-Correct It via Reinforcement Learning
- RM-R1: Reward Modeling as Reasoning
- Agentic retrieval-augmented reasoning reshapes collective reliability under model variability in radiology question answering
- Reinforcement Learning for Long-Horizon Multi-Turn Search Agents
- AutothinkRAG: Complexity-Aware Control of Retrieval-Augmented Reasoning for Image-Text Interaction
- Latent Poincaré Shaping for Agentic Reinforcement Learning
- Partial Policy Gradients for RL in LLMs
- MASFactory: A Graph-centric Framework for Orchestrating LLM-Based Multi-Agent Systems with Vibe Graphing
- FlashPrefill: Instantaneous Pattern Discovery and Thresholding for Ultra-Fast Long-Context Prefilling
- EvoESAP: Non-Uniform Expert Pruning for Sparse MoE
- StreamWise: Serving Multi-Modal Generation in Real-Time at Scale
- λScale: Enabling Fast Scaling for Serverless Large Language Model Inference
- Parallelization Strategies for Dense LLM Deployment: Navigating Through Application-Specific Tradeoffs and Bottlenecks
- ROSE: Reordered SparseGPT for More Accurate One-Shot Large Language Models Pruning
- FAST: An Efficient Scheduler for All-to-All GPU Communication
- Omni-Masked Gradient Descent: Memory-Efficient Optimization via Mask Traversal with Improved Convergence
- A Persistent-State Dataflow Accelerator for Memory-Bound Linear Attention Decode on FPGA
- Disaggregation in Large Language Models: the Next Evolution in AI Infrastructure
- PinRec: Outcome-Conditioned, Multi-Token Generative Retrieval for Industry-Scale Recommendation Systems
- Can LLMs Outshine Conventional Recommenders? A Comparative Evaluation
- Rec-R1: Bridging Generative Large Language Models and User-Centric Recommendation Systems via Reinforcement Learning
- Process-Supervised LLM Recommenders via Flow-guided Tuning
- Towards Next-Generation Recommender Systems: a Benchmark for Personalized Recommendation Assistant with LLMs
- REGEN: A Dataset and Benchmarks with Natural Language Critiques and Narratives
- ChatSearch: a Dataset and a Generative Retrieval Model for General Conversational Image Retrieval
- A Survey of Large Language Model Empowered Agents for Recommendation and Search: Towards Next-Generation Information Retrieval
- A Long-term Value Prediction Framework In Video Ranking
- Learning to Alleviate Familiarity Bias in Video Recommendation
- RGAlign-Rec: Ranking-Guided Alignment for Latent Query Reasoning in Recommendation Systems
- Length-Adaptive Interest Network for Balancing Long and Short Sequence Modeling in CTR Prediction
- Cold-Start Personalization via Training-Free Priors from Structured World Models
- Scaling Sequential Recommendation Models with Transformers
- SafeCRS: Personalized Safety Alignment for LLM-Based Conversational Recommender Systems
- Optimizing Generative Ranking Relevance via Reinforcement Learning in Xiaohongshu Search
- Automatic In-Domain Exemplar Construction and LLM-Based Refinement of Multi-LLM Expansions for Query Expansion
- Exploring the Effectiveness of Multi-stage Fine-tuning for Cross-encoder Re-rankers
- Still Fresh? Evaluating Temporal Drift in Retrieval Benchmarks
- Autoregressive Ranking: Bridging the Gap Between Dual and Cross Encoders
- SIGHT: Reinforcement Learning with Self-Evidence and Information-Gain Diverse Branching for Search Agent
- Exploring Reasoning Reward Model for Agents
- DeerFlow: A Modular Multi-Agent Framework for Deep Research Automation
- Agentic Reasoning for Large Language Models
- Step-DeepResearch Technical Report
- Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation Models
- PilotANN: Memory-Bounded GPU Acceleration for Vector Search
- Collaborative Speculative Inference for Efficient LLM Inference Serving
- Dynamic Model Routing and Cascading for Efficient LLM Inference: A Survey