ICLR2025 retrieval 相关论文

ICLR2025 retrieval 相关论文

1. STRAP: Robot Sub-Trajectory Retrieval for Augmented Policy Learning
   STRAP：增强策略学习的机器人子轨迹检索 https://arxiv.org/pdf/2412.15182
2. Streaming Video Question-Answering with In-context Video KV-Cache Retrieval
   基于上下文视频KV缓存检索的流媒体视频问答 https://arxiv.org/pdf/2503.00540
3. Sufficient Context: A New Lens on Retrieval Augmented Generation Systems
   足够的上下文：对检索增强生成系统的新视角 https://arxiv.org/pdf/2411.06037
4. TempMe: Video Temporal Token Merging for Efficient Text-Video Retrieval
   TempMe：用于高效文本-视频检索的视频时间性标记合并 https://arxiv.org/pdf/2409.01156
5. Test-time Adaptation for Cross-modal Retrieval with Query Shift
   测试时适应：带有查询偏移的跨模态检索 https://arxiv.org/abs/2410.15624
6. VisRAG: Vision-based Retrieval-augmented Generation on Multi-modality Documents
   VisRAG：基于视觉的多模态文档检索增强生成 https://arxiv.org/abs/2410.10594
7. Universal Multimodal Retrieval with Multimodal LLMs
   使用多模态LLMs的通用多模态检索 https://openreview.net/forum?id=i45NQb2iKO
8. Think-on-Graph 2.0: Deep and Faithful Large Language Model Reasoning with Knowledge-guided Retrieval Augmented Generation
   Think-on-Graph 2.0：基于知识引导的检索增强生成的大型语言模型深度推理与忠实性 https://arxiv.org/pdf/2407.10805
9. TIGeR: Unifying Text-to-Image Generation and Retrieval with Large Multimodal Models
   TIGeR：统一文本到图像生成和检索的多模态大型模型 https://openreview.net/pdf?id=mr2icR6dpD
10. ToolGen: Unified Tool Retrieval and Calling via Generation
    ToolGen：通过生成统一工具检索与调用 https://arxiv.org/pdf/2410.03439?
11. Training Large Language Models for Retrieval-Augmented Question Answering through Backtracking Correction
    通过回溯修正训练大型语言模型进行检索增强问答 https://openreview.net/pdf?id=IOg47mg74i
12. SRSA: Skill Retrieval and Adaptation for Robotic Assembly Tasks
    SRSA：机器人组装任务的技能检索与适应 https://arxiv.org/pdf/2503.04538
13. Accelerating Inference of Retrieval-Augmented Generation via Sparse Context Selection
    通过稀疏上下文选择加速检索增强生成的推理 https://arxiv.org/pdf/2405.16178
14. Not All Heads Matter: A Head-Level KV Cache Compression Method with Integrated Retrieval and Reasoning
    并非所有的头都重要：一种集成检索与推理的头级KV缓存压缩方法 https://arxiv.org/pdf/2410.19258
15. NUDGE: Lightweight Non-Parametric Fine-Tuning of Embeddings for Retrieval
    NUDGE：用于检索的轻量级非参数嵌入微调 https://arxiv.org/abs/2409.02343
16. On the Convergence of No-Regret Dynamics in Information Retrieval Games with Proportional Ranking Functions
    关于信息检索游戏中无悔动态收敛与比例排名函数 https://arxiv.org/pdf/2405.11517
17. Provence: Efficient and Robust Context Pruning for Retrieval-Augmented Generation
    Provence：检索增强生成的高效且强健的上下文修剪 https://arxiv.org/pdf/2501.16214
18. RAG-DDR: Optimizing Retrieval-Augmented Generation Using Differentiable Data Rewards
    RAG-DDR：使用可微分数据奖励优化检索增强生成 https://arxiv.org/pdf/2410.13509
19. RAG-SR: Retrieval-Augmented Generation for Neural Symbolic Regression
    RAG-SR：用于神经符号回归的检索增强生成 https://openreview.net/pdf?id=NdHka08uWn
20. RAPID: Retrieval Augmented Training of Differentially Private Diffusion Models
    RAPID：差分隐私扩散模型的检索增强训练 https://arxiv.org/pdf/2502.12794
21. RA-TTA: Retrieval-Augmented Test-Time Adaptation for Vision-Language Models
    RA-TTA：视觉-语言模型的检索增强测试时适应 https://openreview.net/pdf?id=V3zobHnS61
22. RazorAttention: Efficient KV Cache Compression Through Retrieval Heads
    RazorAttention：通过检索头高效压缩KV缓存 https://arxiv.org/pdf/2407.15891
23. Reasoning-Enhanced Healthcare Predictions with Knowledge Graph Community Retrieval
    基于知识图谱社区检索的推理增强型医疗预测 https://arxiv.org/pdf/2410.04585
24. ReDeEP: Detecting Hallucination in Retrieval-Augmented Generation via Mechanistic Interpretability
    ReDeEP：通过机制可解释性检测检索增强生成中的幻觉 https://arxiv.org/pdf/2410.11414
25. ReNovo: Retrieval-Based De Novo Mass Spectrometry Peptide Sequencing
    ReNovo：基于检索的去新质谱肽序列测定 https://openreview.net/pdf?id=uQnvYP7yX9
26. REGENT: A Retrieval-Augmented Generalist Agent That Can Act In-Context in New Environments
    REGENT：一款可以在新环境中上下文行动的检索增强型通用智能体 https://arxiv.org/pdf/2412.04759
27. Rethinking and Improving Autoformalization: Towards a Faithful Metric and a Dependency Retrieval-based Approach
    重新思考和改进自动格式化：面向一个忠实的度量标准和基于依赖检索的方法
28. Retri3D: 3D Neural Graphics Representation Retrieval
    Retri3D：3D神经图形表示检索
29. Retrieval Augmented Diffusion Model for Structure-informed Antibody Design and Optimization
    用于结构信息化抗体设计与优化的检索增强扩散模型
30. Retrieval Head Mechanistically Explains Long-Context Factuality
    检索头机制性地解释了长上下文的真实性
31. RNNs are not Transformers (Yet): The Key Bottleneck on In-Context Retrieval
    RNNs还不是Transformers：上下文检索的关键瓶颈
32. Simple is Effective: The Roles of Graphs and Large Language Models in Knowledge-Graph-Based Retrieval-Augmented Generation
    简单有效：图谱和大型语言模型在基于知识图谱的检索增强生成中的作用
33. Semi-Parametric Retrieval via Binary Bag-of-Tokens Index
    通过二进制标记袋索引的半参数检索
34. Speculative RAG: Enhancing Retrieval Augmented Generation through Drafting
    推测性RAG：通过草拟增强检索增强生成 https://arxiv.org/abs/2407.08223
35. SePer: Measure Retrieval Utility Through The Lens Of Semantic Perplexity Reduction
    SePer：通过语义困惑度降低来度量检索效用
36. SeCom: On Memory Construction and Retrieval for Personalized Conversational Agents
    SeCom：关于个性化对话代理的记忆构建与检索
37. A Theory for Token-Level Harmonization in Retrieval-Augmented Generation
    检索增强生成中标记级别协调的理论
38. Auto-GDA: Automatic Domain Adaptation for Efficient Grounding Verification in Retrieval Augmented Generation
    Auto-GDA：用于检索增强生成中高效基础验证的自动领域适应
39. Beyond Content Relevance: Evaluating Instruction Following in Retrieval Models
    超越内容相关性：在检索模型中评估指令遵循
40. Bridging Information Asymmetry in Text-video Retrieval: A Data-centric Approach
    缩小文本视频检索中的信息不对称：一种数据中心化方法
41. BRIGHT: A Realistic and Challenging Benchmark for Reasoning-Intensive Retrieval
    BRIGHT：一种现实且具有挑战性的推理密集型检索基准
42. ColPali: Efficient Document Retrieval with Vision Language Models
    ColPali：使用视觉语言模型进行高效文档检索
43. Benchmarking Multimodal Retrieval Augmented Generation with Dynamic VQA Dataset and Self-adaptive Planning Agent
    使用动态VQA数据集和自适应规划代理对多模态检索增强生成进行基准测试 https://arxiv.org/abs/2411.02937
44. DRoC: Elevating Large Language Models for Complex Vehicle Routing via Decomposed Retrieval of Constraints
    DRoC：通过分解约束的检索提升大型语言模型处理复杂车辆路径规划
45. DuoAttention: Efficient Long-Context LLM Inference with Retrieval and Streaming Heads
    DuoAttention：通过检索和流式头进行高效长上下文LLM推理
46. EXPLOITING DISTRIBUTION CONSTRAINTS FOR SCALABLE AND EFFICIENT IMAGE RETRIEVAL
    利用分布约束实现可扩展和高效的图像检索 https://arxiv.org/abs/2410.07022
47. Follow My Instruction and Spill the Beans: Scalable Data Extraction from Retrieval-Augmented Generation Systems
    跟随我的指令，泄露信息：从检索增强生成系统中可扩展的数据提取
48. From Artificial Needles to Real Haystacks: Improving Retrieval Capabilities in LLMs by Finetuning on Synthetic Data
    从人工针到真正的干草堆：通过在合成数据上微调提升LLM中的检索能力
49. Generalized Video Moment Retrieval
    广义视频时刻检索
50. Grounding by Trying: LLMs with Reinforcement Learning-Enhanced Retrieval
    通过尝试进行基础化：增强型强化学习的LLMs与检索
51. Inference Scaling for Long-Context Retrieval Augmented Generation
    长上下文检索增强生成的推理扩展
52. InstructRAG: Instructing Retrieval-Augmented Generation via Self-Synthesized Rationales
    InstructRAG：通过自我合成的推理指导检索增强生成
53. LaMP: Language-Motion Pretraining for Motion Generation, Retrieval, and Captioning
    LaMP：用于动作生成、检索和字幕的语言-运动预训练 https://arxiv.org/abs/2410.07093
54. Learning Fine-Grained Representations through Textual Token Disentanglement in Composed Video Retrieval
    通过文本标记解缠学习细粒度表示在复合视频检索中的应用
55. Look Before You Leap: Universal Emergent Mechanism for Retrieval in Language Models
    三思而后行：语言模型中检索的普遍突现机制
56. MAI: A Multi-turn Aggregation-Iteration Model for Composed Image Retrieval
    MAI：复合图像检索的多轮聚合迭代模型
57. MLLM as Retriever: Interactively Learning Multimodal Retrieval for Embodied Agents
    MLLM作为检索器：交互式学习多模态检索用于具身智能体 https://arxiv.org/abs/2410.03450
58. MRAG-Bench: Vision-Centric Evaluation for Retrieval-Augmented Multimodal Models
    MRAG-Bench：基于视觉的检索增强多模态模型评估 https://arxiv.org/abs/2410.08182
59. Multi-Field Adaptive Retrieval
    多领域自适应检索 https://arxiv.org/abs/2410.20056
60. CoRNStack: High-Quality Contrastive Data for Better Code Retrieval and Reranking
    CoRNStack：更好的代码检索和重排序的高质量对比数据