全部收录论文
论文 · 第 94 页
共 7039 篇 · 按日期新到旧 · 每页 50 篇 · 第 94 / 141 页
查找论文请用站内搜索。
- MementoGUI: Learning Agentic Multimodal Memory Control for Long-Horizon GUI Agents
- RAPT: Retrieval-Augmented Post-hoc Thresholding for Multi-Label Classification
- SkillsVote: Lifecycle Governance of Agent Skills from Collection, Recommendation to Evolution
- AI for Auto-Research: Roadmap & User Guide
- AtlasVA: Self-Evolving Visual Skill Memory for Teacher-Free VLM Agents
- OSCAR: Offline Spectral Covariance-Aware Rotation for 2-bit KV Cache Quantization
- Post-Trained MoE Can Skip Half Experts via Self-Distillation
- SNLP: Layer-Parallel Inference via Structured Newton Corrections
- Symmetry-Compatible Principle for Optimizer Design: Embeddings, LM Heads, SwiGLU MLPs, and MoE Routers
- LongLive-2.0: An NVFP4 Parallel Infrastructure for Long Video Generation
- Lance: Unified Multimodal Modeling by Multi-Task Synergy
- A Reference Model and Patterns for Production Event Data Enrichment
- Position: LLM Serving Needs Mathematical Optimization and Algorithmic Foundations, Not Just Heuristics
- An LLM-RAG Approach for Healthy Eating Index-Informed Personalized Food Recommendations
- Generative Long-term User Interest Modeling for Click-Through Rate Prediction
- Fortress: A Case Study in Stabilizing Search Recommendations via Temporal Data Augmentation and Feature Pruning
- LLM-EDT: Large Language Model Enhanced Cross-domain Sequential Recommendation with Dual-phase Training
- Agent4POI: Agentic Context-Conditioned Affordance Reasoning for Multimodal Point-of-Interest Recommendation
- Logging Policy Design for Off-Policy Evaluation
- On the Factual Consistency of Text-based Explainable Recommendation Models
- Ascend-RaBitQ: Heterogeneous NPU-CPU Acceleration of Billion-Scale Similarity Search with 1-bit Quantization
- Fairness-Aware Retrieval Optimization for Retrieval-Augmented Generation
- X-SYNTH: Beyond Retrieval -- Enterprise Context Synthesis from Observed Human Attention
- Retrieval-Augmented Large Language Models for Schema-Constrained Clinical Information Extraction
- Argus: Evidence Assembly for Scalable Deep Research Agents
- Process Rewards with Learned Reliability
- Response-Conditioned Parallel-to-Sequential Orchestration for Multi-Agent Systems
- DeepSlide: From Artifacts to Presentation Delivery
- Calibrating LLMs with Semantic-level Reward
- Falkor-IRAC: Graph-Constrained Generation for Verified Legal Reasoning in Indian Judicial AI
- OpenAI and Dell partner to bring Codex to hybrid and on-premise enterprise environments
- PSD: Pushing the Pareto Frontier of Diffusion LLMs via Parallel Speculative Decoding
- Measuring Maximum Activations in Open Large Language Models
- Always Learning, Always Mixing: Efficient and Simple Data Mixing All The Time
- RoPE Distinguishes Neither Positions Nor Tokens in Long Contexts, Provably
- Differentially Private Motif-Preserving Multi-modal Hashing
- Dynamic Chunking for Diffusion Language Models
- paper.json: A Coordination Convention for LLM-Agent-Actionable Papers
- Efficient Generative Retrieval for E-commerce Search with Semantic Cluster IDs and Expert-Guided RL
- Making LLMs faster without sacrificing accuracy (Surefire architectural scaling law)
- Asymmetric Generative Recommendation via Multi-Expert Projection and Multi-Faceted Hierarchical Quantization
- MATT-CTR: Unleashing a Model-Agnostic Test-Time Paradigm for CTR Prediction with Confidence-Guided Inference Paths
- LongRetriever: Towards Ultra-Long Sequence based Candidate Retrieval for Recommendation
- TADT-CSA: Temporal Advantage Decision Transformer with Contrastive State Abstraction for Generative Recommendation
- Thinking Broad, Acting Fast: Latent Reasoning Distillation from Multi-Perspective Chain-of-Thought for E-Commerce Relevance
- From Reasoning LLMs to BERT: A Two-Stage Distillation Framework for Search Relevance
- IterQR: An Iterative Framework for LLM-based Query Rewrite in e-Commercial Search System
- LREF: A Novel LLM-based Relevance Framework for E-commerce Search
- Mira-Embeddings-V1: Domain-Adapted Semantic Reranking for Recruitment via LLM-Synthesized Data
- PairSem: LLM-Guided Pairwise Semantic Matching for Scientific Document Retrieval