|
25 | 25 | }, |
26 | 26 | { |
27 | 27 | "category": ["CodeGeneration"], |
28 | | - "title": "BRIGHT: A Realistic and Challenging Benchmark for Reasoning-Intensive Retrieval", |
29 | | - "authors": "Hongjin Su, Howard Yen, Mengzhou Xia, Weijia Shi, Niklas Muennighoff, Han-yu Wang, Haisu Liu, Quan Shi, Zachary S. Siegel, Michael Tang, Ruoxi Sun, Jinsung Yoon, Sercan O. Arik, Danqi Chen, Tao Yu", |
| 28 | + "title": "Spider 2.0: Evaluating Language Models on Real-World Enterprise Text-to-SQL Workflows", |
| 29 | + "authors": "Fangyu Lei, Jixuan Chen, Yuxiao Ye, Ruisheng Cao, Dongchan Shin, Hongjin Su, Zhaoqing Suo, Hongcheng Gao, Wenjing Hu, Pengcheng Yin, Victor Zhong, Caiming Xiong, Ruoxi Sun, Qian Liu, Sida Wang, Tao Yu", |
30 | 30 | "publication": "Preprint", |
31 | | - "paperLink": "https://arxiv.org/abs/2407.12883", |
32 | | - "codeLink": "https://github.com/xlang-ai/BRIGHT", |
| 31 | + "paperLink": "https://www.arxiv.org/abs/2411.07763", |
| 32 | + "codeLink": "https://github.com/xlang-ai/Spider2", |
33 | 33 | "dataLink": "", |
34 | 34 | "blogLink": "", |
35 | 35 | "twitterLink": "", |
36 | | - "image": "/research/bright.jpg" |
37 | | - }, |
38 | | - { |
39 | | - "category": ["CodeGeneration"], |
40 | | - "title": "Spider2-V: How Far Are Multimodal Agents From Automating Data Science and Engineering Workflows?", |
41 | | - "authors": "Ruisheng Cao, Fangyu Lei, Haoyuan Wu, Jixuan Chen, Yeqiao Fu, Hongcheng Gao, Xinzhuang Xiong, Hanchong Zhang, Yuchen Mao, Wenjing Hu, Tianbao Xie, Hongshen Xu, Danyang Zhang, Sida Wang, Ruoxi Sun, Pengcheng Yin, Caiming Xiong, Ansong Ni, Qian Liu, Victor Zhong, Lu Chen, Kai Yu, Tao Yu", |
42 | | - "publication": "NeurIPS 2024, Spotlight", |
43 | | - "paperLink": "https://arxiv.org/abs/2407.10956", |
44 | | - "codeLink": "https://github.com/xlang-ai/Spider2-V", |
45 | | - "dataLink": "", |
46 | | - "blogLink": "https://spider2-v.github.io/", |
47 | | - "twitterLink": "", |
48 | | - "image": "/research/spider2v.jpg" |
| 36 | + "image": "/research/spider2.jpg" |
49 | 37 | }, |
50 | 38 | { |
51 | 39 | "category": ["DigitalAIAgents"], |
|
61 | 49 | }, |
62 | 50 | { |
63 | 51 | "category": ["CodeGeneration"], |
64 | | - "title": "Spider 2.0: Evaluating Language Models on Real-World Enterprise Text-to-SQL Workflows", |
65 | | - "authors": "Fangyu Lei, Jixuan Chen, Yuxiao Ye, Ruisheng Cao, Dongchan Shin, Hongjin Su, Zhaoqing Suo, Hongcheng Gao, Wenjing Hu, Pengcheng Yin, Victor Zhong, Caiming Xiong, Ruoxi Sun, Qian Liu, Sida Wang, Tao Yu", |
| 52 | + "title": "BRIGHT: A Realistic and Challenging Benchmark for Reasoning-Intensive Retrieval", |
| 53 | + "authors": "Hongjin Su, Howard Yen, Mengzhou Xia, Weijia Shi, Niklas Muennighoff, Han-yu Wang, Haisu Liu, Quan Shi, Zachary S. Siegel, Michael Tang, Ruoxi Sun, Jinsung Yoon, Sercan O. Arik, Danqi Chen, Tao Yu", |
66 | 54 | "publication": "Preprint", |
67 | | - "paperLink": "https://www.arxiv.org/abs/2411.07763", |
68 | | - "codeLink": "https://github.com/xlang-ai/Spider2", |
| 55 | + "paperLink": "https://arxiv.org/abs/2407.12883", |
| 56 | + "codeLink": "https://github.com/xlang-ai/BRIGHT", |
69 | 57 | "dataLink": "", |
70 | 58 | "blogLink": "", |
71 | 59 | "twitterLink": "", |
72 | | - "image": "/research/spider2.jpg" |
| 60 | + "image": "/research/bright.jpg" |
| 61 | + }, |
| 62 | + { |
| 63 | + "category": ["CodeGeneration"], |
| 64 | + "title": "Generative Representational Instruction Tuning", |
| 65 | + "authors": "Niklas Muennighoff, Hongjin Su, Liang Wang, Nan Yang, Furu Wei, Tao Yu, Amanpreet Singh, Douwe Kiela", |
| 66 | + "publication": "ICLR 2024 AGI Workshop, Best Paper Award", |
| 67 | + "paperLink": "https://arxiv.org/abs/2402.09906", |
| 68 | + "codeLink": "https://github.com/ContextualAI/gritlm", |
| 69 | + "dataLink": "", |
| 70 | + "blogLink": "", |
| 71 | + "twitterLink": "https://twitter.com/Muennighoff/status/1758307967802224770", |
| 72 | + "image": "/research/grit.jpeg" |
73 | 73 | }, |
74 | 74 | { |
75 | 75 | "category": ["DigitalAIAgents"], |
|
83 | 83 | "twitterLink": "https://twitter.com/TianbaoX/status/1778781521253667267", |
84 | 84 | "image": "/research/osworld.png" |
85 | 85 | }, |
| 86 | + { |
| 87 | + "category": ["CodeGeneration"], |
| 88 | + "title": "Spider2-V: How Far Are Multimodal Agents From Automating Data Science and Engineering Workflows?", |
| 89 | + "authors": "Ruisheng Cao, Fangyu Lei, Haoyuan Wu, Jixuan Chen, Yeqiao Fu, Hongcheng Gao, Xinzhuang Xiong, Hanchong Zhang, Yuchen Mao, Wenjing Hu, Tianbao Xie, Hongshen Xu, Danyang Zhang, Sida Wang, Ruoxi Sun, Pengcheng Yin, Caiming Xiong, Ansong Ni, Qian Liu, Victor Zhong, Lu Chen, Kai Yu, Tao Yu", |
| 90 | + "publication": "NeurIPS 2024, Spotlight", |
| 91 | + "paperLink": "https://arxiv.org/abs/2407.10956", |
| 92 | + "codeLink": "https://github.com/xlang-ai/Spider2-V", |
| 93 | + "dataLink": "", |
| 94 | + "blogLink": "https://spider2-v.github.io/", |
| 95 | + "twitterLink": "", |
| 96 | + "image": "/research/spider2v.jpg" |
| 97 | + }, |
86 | 98 | { |
87 | 99 | "category": ["CodeGeneration"], |
88 | 100 | "title": "EvoR: Evolving Retrieval for Code Generation", |
89 | 101 | "authors": "Hongjin Su, Shuyang Jiang, Yuhang Lai, Haoyuan Wu, Boao Shi, Che Liu, Qian Liu, Tao Yu", |
90 | | - "publication": "Preprint", |
| 102 | + "publication": "EMNLP Findings 2024", |
91 | 103 | "paperLink": "https://arxiv.org/abs/2307.07047", |
92 | 104 | "codeLink": "https://github.com/xlang-ai/EVOR", |
93 | 105 | "dataLink": "https://huggingface.co/datasets/xlangai/arks_data", |
94 | 106 | "blogLink": "https://arks-codegen.github.io/", |
95 | 107 | "twitterLink": "https://twitter.com/hongjin_su/status/1759978005525643466", |
96 | 108 | "image": "/research/ark.jpeg" |
97 | 109 | }, |
98 | | - { |
99 | | - "category": ["CodeGeneration"], |
100 | | - "title": "Generative Representational Instruction Tuning", |
101 | | - "authors": "Niklas Muennighoff, Hongjin Su, Liang Wang, Nan Yang, Furu Wei, Tao Yu, Amanpreet Singh, Douwe Kiela", |
102 | | - "publication": "Preprint", |
103 | | - "paperLink": "https://arxiv.org/abs/2402.09906", |
104 | | - "codeLink": "https://github.com/ContextualAI/gritlm", |
105 | | - "dataLink": "", |
106 | | - "blogLink": "", |
107 | | - "twitterLink": "https://twitter.com/Muennighoff/status/1758307967802224770", |
108 | | - "image": "/research/grit.jpeg" |
109 | | - }, |
110 | 110 | { |
111 | 111 | "category": ["DigitalAIAgents"], |
112 | 112 | "title": "OS-Copilot: Towards Generalist Computer Agents with Self-Improvement", |
|
117 | 117 | "dataLink": "", |
118 | 118 | "blogLink": "", |
119 | 119 | "twitterLink": "https://twitter.com/zywu_hku/status/1758014688779244002", |
120 | | - "image": "/research/os-copilot.png" |
| 120 | + "image": "/research/os_copilot.png" |
121 | 121 | }, |
122 | 122 | { |
123 | 123 | "category": ["DigitalAIAgents"], |
124 | 124 | "title": "OpenAgents: An Open Platform for Language Agents in the Wild", |
125 | 125 | "authors": "Tianbao Xie*, Fan Zhou*, Zhoujun Cheng*, Peng Shi*, Luoxuan Weng*, Yitao Liu*, Toh Jing Hua, Junning Zhao, Qian Liu, Che Liu, Leo Z. Liu, Yiheng Xu, Hongjin Su, Dongchan Shin, Caiming Xiong, Tao Yu", |
126 | | - "publication": "Preprint", |
| 126 | + "publication": "COLM 2024", |
127 | 127 | "paperLink": "https://arxiv.org/abs/2310.10634", |
128 | 128 | "codeLink": "https://github.com/xlang-ai/OpenAgents", |
129 | 129 | "dataLink": "https://github.com/xlang-ai/OpenAgents", |
130 | 130 | "blogLink": "https://www.xlang.ai/blog/xlang-intro", |
131 | 131 | "twitterLink": "https://twitter.com/ChengZhoujun/status/1714343204148113860", |
132 | 132 | "image": "/research/openagents.png" |
133 | 133 | }, |
| 134 | + { |
| 135 | + "category": ["DigitalAIAgents"], |
| 136 | + "title": "Does Collaborative Human-LM Dialogue Generation Help Information Extraction from Human Dialogues?", |
| 137 | + "authors": "Bo-Ru Lu, Nikita Haduong, Chia-Hsuan Lee, Zeqiu Wu, Hao Cheng, Paul Koester, Jean Utke, Tao Yu, Noah A. Smith, Mari Ostendorf", |
| 138 | + "publication": "COLM 2024", |
| 139 | + "paperLink": "https://arxiv.org/abs/2307.07047", |
| 140 | + "codeLink": "", |
| 141 | + "dataLink": "", |
| 142 | + "blogLink": "", |
| 143 | + "twitterLink": "", |
| 144 | + "image": "/research/os-copilot.png" |
| 145 | + }, |
134 | 146 | { |
135 | 147 | "category": ["PhysicalAIAgents"], |
136 | 148 | "title": "Lemur: Harmonizing Natural Language and Code for Language Agents", |
|
212 | 224 | "twitterLink": "", |
213 | 225 | "image": "/research/ce-icl.png" |
214 | 226 | }, |
| 227 | + { |
| 228 | + "category": ["CodeGeneration"], |
| 229 | + "title": "Batch Prompting: Efficient Inference with Large Language Model APIs", |
| 230 | + "authors": "Zhoujun Cheng, Jungo Kasai, Tao Yu", |
| 231 | + "publication": "EMNLP 2023 Industry Track", |
| 232 | + "paperLink": "https://arxiv.org/abs/2301.08721", |
| 233 | + "codeLink": "", |
| 234 | + "dataLink": "", |
| 235 | + "blogLink": "", |
| 236 | + "twitterLink": "", |
| 237 | + "image": "/research/batch.png" |
| 238 | + }, |
215 | 239 | { |
216 | 240 | "category": ["CodeGeneration"], |
217 | 241 | "title": "Binder: Binding Language Models in Symbolic Languages", |
|
271 | 295 | "twitterLink": "", |
272 | 296 | "image": "/research/ic-dst.jpg" |
273 | 297 | }, |
274 | | - { |
275 | | - "category": ["DigitalAIAgents"], |
276 | | - "title": "NL2INTERFACE: Interactive Visualization Interface Generation from Natural Language Queries", |
277 | | - "authors": "Yiru Chen, Ryan Li, Austin Mac, Tianbao Xie, Tao Yu, Eugene Wu", |
278 | | - "publication": "IEEE Visualization Conference NLVIZ Workshop 2022", |
279 | | - "paperLink": "https://arxiv.org/abs/2209.08834", |
280 | | - "codeLink": "https://github.com/learnedinterfaces/PI2", |
281 | | - "dataLink": "", |
282 | | - "blogLink": "", |
283 | | - "twitterLink": "", |
284 | | - "image": "/research/nl2interface.jpg" |
285 | | - }, |
286 | | - { |
287 | | - "category": ["CodeGeneration"], |
288 | | - "title": "GraPPa: Grammar-Augmented Pre-Training for Table Semantic Parsing", |
289 | | - "authors": "Tao Yu, Chien-Sheng Wu, Xi Victoria Lin, Bailin Wang, Yi Chern Tan, Xinyi Yang, Dragomir Radev, Richard Socher, Caiming Xiong", |
290 | | - "publication": "ICLR 2021", |
291 | | - "paperLink": "https://arxiv.org/abs/2009.13845", |
292 | | - "codeLink": "https://github.com/taoyds/grappa", |
293 | | - "dataLink": "", |
294 | | - "blogLink": "", |
295 | | - "twitterLink": "", |
296 | | - "image": "/research/grappa.jpg" |
297 | | - }, |
298 | | - { |
299 | | - "category": ["CodeGeneration"], |
300 | | - "title": "Semantic Evaluation for Text-to-SQL with Distilled Test Suites", |
301 | | - "authors": "Ruiqi Zhong, Tao Yu, Dan Klein", |
302 | | - "publication": "EMNLP 2020", |
303 | | - "paperLink": "https://arxiv.org/abs/2010.02840", |
304 | | - "codeLink": "https://github.com/taoyds/test-suite-sql-eval", |
305 | | - "dataLink": "", |
306 | | - "blogLink": "", |
307 | | - "twitterLink": "", |
308 | | - "image": "/research/test-suite.jpg" |
309 | | - }, |
310 | | - { |
311 | | - "category": ["CodeGeneration"], |
312 | | - "title": "CoSQL: A Conversational Text-to-SQL Challenge Towards Cross-Domain Natural Language Interfaces to Databases", |
313 | | - "authors": "Tao Yu, Rui Zhang, Heyang Er, Suyi Li, Eric Xue, Bo Pang, Xi Victoria Lin, Yi Chern Tan, Tianze Shi, Zihan Li, Youxuan Jiang, Michihiro Yasunaga, Sungrok Shim, Tao Chen, Alexander Fabbri, Zifan Li, Luyao Chen, Yuwen Zhang, Shreya Dixit, Vincent Zhang, Caiming Xiong, Richard Socher, Walter Lasecki, Dragomir Radev", |
314 | | - "publication": "EMNLP 2019", |
315 | | - "paperLink": "https://arxiv.org/abs/1909.05378", |
316 | | - "codeLink": "https://github.com/taoyds/cosql", |
317 | | - "dataLink": "https://drive.google.com/uc?export=download&id=1Y3ydpFiQQ3FC0bzdfy3groV95O_f1nXF", |
318 | | - "blogLink": "https://yale-lily.github.io/cosql", |
319 | | - "twitterLink": "", |
320 | | - "image": "/research/cosql.jpg" |
321 | | - }, |
322 | | - { |
323 | | - "category": ["CodeGeneration"], |
324 | | - "title": "SParC: Cross-Domain Semantic Parsing in Context", |
325 | | - "authors": "Tao Yu, Rui Zhang, Michihiro Yasunaga, Yi Chern Tan, Xi Victoria Lin, Suyi Li, Heyang Er, Irene Li, Bo Pang, Tao Chen, Emily Ji, Shreya Dixit, David Proctor, Sungrok Shim, Jonathan Kraft, Vincent Zhang, Caiming Xiong, Richard Socher, Dragomir Radev", |
326 | | - "publication": "ACL 2018", |
327 | | - "paperLink": "https://arxiv.org/abs/1906.02285", |
328 | | - "codeLink": "https://github.com/taoyds/sparc", |
329 | | - "dataLink": "https://drive.google.com/uc?export=download&id=1Uu7NMHTR1tdQw1t7bAuM7OPU4LElVKfg", |
330 | | - "blogLink": "https://yale-lily.github.io/sparc", |
331 | | - "twitterLink": "", |
332 | | - "image": "/research/sparc.jpg" |
333 | | - }, |
334 | 298 | { |
335 | 299 | "category": ["CodeGeneration"], |
336 | 300 | "title": "Spider: A Large-Scale Human-Labeled Dataset for Complex and Cross-Domain Semantic Parsing and Text-to-SQL Task", |
|
0 commit comments