你可能會喜歡
Haystack Engineering: Context Engineering for Heterogeneous and Agentic Long-Context Evaluation. arxiv.org/abs/2510.07414
🚨Releasing 𝗥𝗔𝗚 𝗼𝘃𝗲𝗿 𝗧𝗮𝗯𝗹𝗲𝘀: 𝗛𝗶𝗲𝗿𝗮𝗿𝗰𝗵𝗶𝗰𝗮𝗹 𝗠𝗲𝗺𝗼𝗿𝘆 𝗜𝗻𝗱𝗲𝘅, 𝗠𝘂𝗹𝘁𝗶-𝗦𝘁𝗮𝗴𝗲 𝗥𝗲𝘁𝗿𝗶𝗲𝘃𝗮𝗹, 𝗮𝗻𝗱 𝗕𝗲𝗻𝗰𝗵𝗺𝗮𝗿𝗸𝗶𝗻𝗴. 🚀 We push RAG to Multi-tables! 🌐Code: github.com/jiaruzouu/T-RAG 📄Paper: arxiv.org/abs/2504.01346
RAG over Tables 🛫
🚨Releasing 𝗥𝗔𝗚 𝗼𝘃𝗲𝗿 𝗧𝗮𝗯𝗹𝗲𝘀: 𝗛𝗶𝗲𝗿𝗮𝗿𝗰𝗵𝗶𝗰𝗮𝗹 𝗠𝗲𝗺𝗼𝗿𝘆 𝗜𝗻𝗱𝗲𝘅, 𝗠𝘂𝗹𝘁𝗶-𝗦𝘁𝗮𝗴𝗲 𝗥𝗲𝘁𝗿𝗶𝗲𝘃𝗮𝗹, 𝗮𝗻𝗱 𝗕𝗲𝗻𝗰𝗵𝗺𝗮𝗿𝗸𝗶𝗻𝗴. 🚀 We push RAG to Multi-tables! 🌐Code: github.com/jiaruzouu/T-RAG 📄Paper: arxiv.org/abs/2504.01346
Haystack Engineering: Context Engineering for Heterogeneous and Agentic Long-Context Evaluation @Mufei_Li et al. present a benchmark built on Wikipedia's hyperlink network. 📝arxiv.org/abs/2510.07414 👨🏽💻github.com/Graph-COM/Hays…
Very inspiring work! Congrats!
🌠Flow Matching Meets Biology and Life Science: A Survey Flow matching is emerging as a powerful generative paradigm. We comprehensively review its foundations and applications across biology & life science🧬 📚Paper: arxiv.org/abs/2507.17731 💻Resource: github.com/Violet24K/Awes…
‼️We propose to learn temporal positional encodings for spatial-temporal graphs, L-STEP, in our #ICML2025 paper. Even simple MLPs can achieve leading performance in various temporal link prediction settings! 📄 Paper: arxiv.org/pdf/2506.08309 💻 Code: github.com/kthrn22/L-STEP
Interesting to see the analysis between Inference scaling and LLM safety!
😲 Not only reasoning?! Inference scaling can now boost LLM safety! 🚀 Introducing Saffron-1: - Reduces attack success rate from 66% to 17.5% - Uses only 59.7 TFLOP compute - Counters latest jailbreak attacks - No model finetuning On the AI2 Refusals benchmark. 📖 Paper:…
Thrilled to have 3 #ICML and 1 #ACL accepted! Congrats all collaborators 🎉🎉🎉 Studying graph representation learning, multimodal alignment, and generative material design😄 Stay tuned🤔
Identify Invariant Subgraphs for Spatial-Temporal OOD Problems 👏👏👏
Solving Out-of-Distribution problem of Spatial-Temporal Graphs❓ Check out our #AISTATS2025 paper, our method distinguishes invariant components during training and makes link predictions robust to distribution shifts Paper: raw.githubusercontent.com/mlresearch/v25…
We'll present 4 papers and 1 keynote talk at #ICLR2025. Prof. Jingrui He and Prof. Hanghang Tong will be at the conference. Let's connect! ☕️
🔥various graph types and various evaluation metrics
🔬Graph Self-Supervised Learning Toolkit 🔥We release PyG-SSL, offering a unified framework of 10+ self-supervised choices to pretrain your graph foundation models. 📜Paper: arxiv.org/abs/2412.21151 💻Code: github.com/iDEA-iSAIL-Lab… Have fun!
Beyond numerical-only time series models, let’s see how language can help time series forecasting and imputation🤹
📈 Your time-series-paired texts are secretly a time series! 🙌 Real-world time series (stock prices) and texts (financial reports) share similar periodicity and spectrum, unlocking seamless multimodal learning using existing TS models. 🔬 Read more: arxiv.org/abs/2502.08942
💡 How can we describe a graph to LLMs ? 🧐 For example, G(n, p) uses number of nodes and connection probability to describe a graph. 📑 Please check out our survey, What Do LLMs Need to Understand Graphs: A Survey of Parametric Representation of Graphs arxiv.org/pdf/2410.12126
Excited to know our #ICLR2025 paper is selected as Spotlight 🎉🎉🎉 We studied how to generate large-scale temporal heterogeneous graphs balancing privacy, utility, and efficiency We also found diffusion model may not be the solution to answer them all openreview.net/forum?id=tj5xJ…
This thursday, Feb 13th, 11am ET, at the Reading group, @kthrn_uiuc will present: Temporal Graph Neural Tangent Kernel with Graphon-Guaranteed (NeurIPS 2024). Looking forward to seeing you there! 🎉🎉 Zoom link on website openreview.net/forum?id=266nH…
Can we obtain temporal graph neural representation without neural network❓ Check out our #NeurIPS2024 paper, Temporal Graph Neural Tangent Kernel with Graphon-Guaranteed 🎉 Paper: openreview.net/pdf?id=266nH7k… Code: github.com/kthrn22/TempGN…
2 papers accepted by #ICLR2025, 1 paper by #AISTATS2025, and 1 paper by #KDD2025, congrats all collaborators 🎉 TL;DR 1️⃣ How to generate temporal heterogeneous graphs 2️⃣ How to tokenize a graph 3️⃣ How to infer invariant subgraphs 4️⃣ How to compress an evolving knowledge graph
Can we obtain temporal graph neural representation without neural network❓ Check out our #NeurIPS2024 paper, Temporal Graph Neural Tangent Kernel with Graphon-Guaranteed 🎉 Paper: openreview.net/pdf?id=266nH7k… Code: github.com/kthrn22/TempGN…
We will present 6 papers at #NeurIPS2024 covering active learning, graph learning, time series and trustworthy ML. Come and have a chat during the poster sessions!🚀
United States 趨勢
- 1. #BaddiesUSA 56.4K posts
- 2. Rams 28.8K posts
- 3. Scotty 9,440 posts
- 4. #TROLLBOY 1,843 posts
- 5. Chip Kelly 8,344 posts
- 6. #LAShortnSweet 17.4K posts
- 7. Cowboys 99.4K posts
- 8. Eagles 139K posts
- 9. Stafford 14.6K posts
- 10. Raiders 66.7K posts
- 11. Bucs 12.2K posts
- 12. Baker 20.8K posts
- 13. #RHOP 11.5K posts
- 14. #ITWelcomeToDerry 14.5K posts
- 15. Stacey 28K posts
- 16. Ahna 6,666 posts
- 17. Teddy Bridgewater 1,198 posts
- 18. Vin Diesel 1,108 posts
- 19. DOGE 163K posts
- 20. Todd Bowles 2,002 posts
你可能會喜歡
-
Wei Jin
@weisshelter -
Yu Zhang
@yuz9yuz -
Hejie Cui
@HennyJieCC -
Jian Kang
@jiank_uiuc -
Ziniu Hu
@acbuller -
Elio (Keqiang) Yan
@KeqiangY -
Yi Liu
@iamyiliu -
Meng Liu
@mengliu_1998 -
Hua Wei
@realhuawei -
Jundong Li
@LiJundong -
Yuqiang Xie
@IndexFziQ -
Canyu Chen
@CanyuChen3 -
Jiayuan Ding
@JiayuanDing -
Yuanqi Du
@YuanqiD -
Ruocheng Guo
@rguo_asu
Something went wrong.
Something went wrong.