Add new papers

Author: Zhaoyang-Chu

README.md

@@ -14,6 +14,14 @@
     github: ""
     website: ""
 
+- title: "Learning Object Placement Programs for Indoor Scene Synthesis with Iterative Self Training"
+  authors: "Adrian Chang, Kai Wang, Yuanbo Li, Manolis Savva, Angel X. Chang, Daniel Ritchie"
+  venue: "arXiv 2025"
+  links:
+    paper: "https://www.arxiv.org/abs/2503.04496"
+    github: ""
+    website: ""
+
 - title: "HSM: Hierarchical Scene Motifs for Multi-Scale Indoor Scene Generation"
   authors: "Hou In Derek Pun, Hou In Ivan Tam, Austin T. Wang, Xiaoliang Huo, Angel X. Chang, Manolis Savva"
   venue: "arXiv 2025"
@@ -62,6 +70,14 @@
     github: "https://github.com/richard-guyunqi/BlenderGym-Open"
     website: "https://blendergym.github.io/"
 
+- title: "CAD-Editor: A Locate-then-Infill Framework with Automated Training Data Synthesis for Text-Based CAD Editing"
+  authors: "Yu Yuan, Shizhao Sun, Qi Liu, Jiang Bian"
+  venue: "ICML 2025"
+  links:
+    paper: "https://arxiv.org/abs/2502.03997"
+    github: "https://github.com/microsoft/CAD-Editor"
+    website: "https://cad-editor.github.io/"
+
 - title: "IR3D-Bench: Evaluating Vision-Language Model Scene Understanding as Agentic Inverse Rendering"
   authors: "Parker Liu, Chenxin Li, Zhengxin Li, Yipeng Wu, Wuyang Li, Zhiqin Yang, Zhenyuan Zhang, Yunlong Lin, Sirui Han, Brandon Y. Feng"
   venue: "NeurIPS 2025 Datasets and Benchmarks Track"
@@ -94,6 +110,14 @@
     github: "https://github.com/THUDM/SceneGenAgent"
     website: ""
 
+- title: "CADTalk: An Algorithm and Benchmark for Semantic Commenting of CAD Programs"
+  authors: "Haocheng Yuan, Jing Xu, Hao Pan, Adrien Bousseau, Niloy J. Mitra, Changjian Li"
+  venue: "CVPR 2024"
+  links:
+    paper: "https://openaccess.thecvf.com/content/CVPR2024/html/Yuan_CADTalk_An_Algorithm_and_Benchmark_for_Semantic_Commenting_of_CAD_CVPR_2024_paper.html"
+    github: "https://github.com/YYYYYHC/CADTalk"
+    website: "https://enigma-li.github.io/CADTalk/"
+
 - title: "SceneCraft: An LLM Agent for Synthesizing 3D Scene as Blender Code"
   authors: "Ziniu Hu, Ahmet Iscen, Aashi Jain, Thomas Kipf, Yisong Yue, David A. Ross, Cordelia Schmid, Alireza Fathi"
   venue: "ICML 2024"

data/papers_3d_object_design.yaml

@@ -0,0 +1,15 @@
+- title: "Plot2Code: A Comprehensive Benchmark for Evaluating Multi-modal Large Language Models in Code Generation from Scientific Plots"
+  authors: "Chengyue Wu, Yixiao Ge, Qiushan Guo, Jiahao Wang, Zhixuan Liang, Zeyu Lu, Ying Shan, Ping Luo"
+  venue: "arXiv 2025"
+  links:
+    paper: "https://arxiv.org/abs/2405.07990"
+    github: "https://github.com/TencentARC/Plot2Code"
+    website: "https://huggingface.co/datasets/TencentARC/Plot2Code"
+
+- title: "Chart-CoCa: Self-Improving Chart Understanding of Vision LMs via Code-Driven Synthesis and Candidate-Conditioned Answering"
+  authors: "Gongyao Jiang, Qiong Luo"
+  venue: "CIKM 2025"
+  links:
+    paper: "https://arxiv.org/abs/2508.11975"
+    github: ""
+    website: ""

data/papers_agentic_visualization.yaml

@@ -1,3 +1,19 @@
+- title: "DeepAnalyze: Agentic Large Language Models for Autonomous Data Science"
+  authors: "Shaolei Zhang, Ju Fan, Meihao Fan, Guoliang Li, Xiaoyong Du"
+  venue: "arXiv 2025"
+  links:
+    paper: "https://arxiv.org/abs/2510.16872"
+    github: "https://github.com/ruc-datalab/DeepAnalyze"
+    website: "https://ruc-deepanalyze.github.io/"
+
+- title: "WebDS: An End-to-End Benchmark for Web-based Data Science"
+  authors: "Ethan Hsu, Hong Meng Yam, Ines Bouissou, Aaron Murali John, Raj Thota, Josh Koe, Vivek Sarath Putta, G K Dharesan, Alexander Spangher, Shikhar Murty, Tenghao Huang, Christopher D. Manning"
+  venue: "arXiv 2025"
+  links:
+    paper: "https://arxiv.org/abs/2508.01222"
+    github: ""
+    website: ""
+
 - title: "AutoMind: Adaptive Knowledgeable Agent for Automated Data Science"
   authors: "Yixin Ou, Yujie Luo, Jingsheng Zheng, Lanning Wei, Zhuoyun Yu, Shuofei Qiao, Jintian Zhang, Da Zheng, Yuren Mao, Yunjun Gao, Huajun Chen, Ningyu Zhang"
   venue: "arXiv 2025"

data/papers_automated_data_science.yaml

@@ -22,6 +22,14 @@
     github: "https://github.com/amazon-science/SWE-PolyBench"
     website: "https://amazon-science.github.io/SWE-PolyBench/"
 
+- title: "MORSE-500: A Programmatically Controllable Video Benchmark to Stress-Test Multimodal Reasoning"
+  authors: "Zikui Cai, Andrew Wang, Anirudh Satheesh, Ankit Nakhawa, Hyunwoo Jae, Keenan Powell, Minghui Liu, Neel Jay, Sungbin Oh, Xiyao Wang, Yongyuan Liang, Tom Goldstein, Furong Huang"
+  venue: "arXiv 2025"
+  links:
+    paper: "https://arxiv.org/abs/2506.05523"
+    github: "https://github.com/morse-benchmark/morse-500"
+    website: "https://morse-500.github.io/"
+
 - title: "SWE-SQL: Illuminating LLM Pathways to Solve User SQL Issues in Real-World Applications"
   authors: "Jinyang Li, Xiaolong Li, Ge Qu, Per Jacobsson, Bowen Qin, Binyuan Hui, Shuzheng Si, Nan Huo, Xiaohan Xu, Yue Zhang, Ziwei Tang, Yuanshuai Li, Florensia Widjaja, Xintong Zhu, Feige Zhou, Yongfeng Huang, Yannis Papakonstantinou, Fatma Ozcan, Chenhao Ma, Reynold Cheng"
   venue: "arXiv 2025"
@@ -46,6 +54,30 @@
     github: "https://github.com/swe-perf/swe-perf"
     website: "https://swe-perf.github.io"
 
+- title: "MetaGen: A DSL, Database, and Benchmark for VLM-Assisted Metamaterial Generation"
+  authors: "Liane Makatura, Benjamin Jones, Siyuan Bian, Wojciech Matusik"
+  venue: "arXiv 2025"
+  links:
+    paper: "https://arxiv.org/abs/2508.17568"
+    github: ""
+    website: ""
+
+- title: "WebDS: An End-to-End Benchmark for Web-based Data Science"
+  authors: "Ethan Hsu, Hong Meng Yam, Ines Bouissou, Aaron Murali John, Raj Thota, Josh Koe, Vivek Sarath Putta, G K Dharesan, Alexander Spangher, Shikhar Murty, Tenghao Huang, Christopher D. Manning"
+  venue: "arXiv 2025"
+  links:
+    paper: "https://arxiv.org/abs/2508.01222"
+    github: ""
+    website: ""
+
+- title: "Plot2Code: A Comprehensive Benchmark for Evaluating Multi-modal Large Language Models in Code Generation from Scientific Plots"
+  authors: "Chengyue Wu, Yixiao Ge, Qiushan Guo, Jiahao Wang, Zhixuan Liang, Zeyu Lu, Ying Shan, Ping Luo"
+  venue: "arXiv 2025"
+  links:
+    paper: "https://arxiv.org/abs/2405.07990"
+    github: "https://github.com/TencentARC/Plot2Code"
+    website: "https://huggingface.co/datasets/TencentARC/Plot2Code"
+
 - title: "SWE-rebench: An Automated Pipeline for Task Collection and Decontaminated Evaluation of Software Engineering Agents"
   authors: "Ibragim Badertdinov, Alexander Golubev, Maksim Nekrashevich, Anton Shevtsov, Simon Karasik, Andrei Andriushchenko, Maria Trofimova, Daria Litvintseva, Boris Yangel"
   venue: "arXiv 2025"
@@ -70,6 +102,14 @@
     github: "https://centre-for-software-excellence.github.io/SWE-Effi/"  
     website: "https://github.com/Centre-for-Software-Excellence/SWE-Effi"
 
+- title: "PReview: A Benchmark Dataset for Pull Request Outcomes and Quality Analysis"
+  authors: "Anonymous Authors"
+  venue: "2025"  
+  links:
+    paper: "https://openreview.net/forum?id=cdwp8BXTVV"
+    github: ""  
+    website: ""
+
 - title: "SEC-bench: Automated Benchmarking of LLM Agents on Real-World Software Security Tasks"
   authors: "Hwiwon Lee, Ziqi Zhang, Hanxiao Lu, Lingming Zhang"
   venue: "arXiv 2025"
@@ -118,6 +158,14 @@
     github: "https://github.com/LiuHengyu321/IR3D-Bench"
     website: "https://ir3d-bench.github.io/"
 
+- title: "BlenderGym: Benchmarking Foundational Model Systems for Graphics Editing"
+  authors: "Yunqi Gu, Ian Huang, Jihyeon Je, Guandao Yang, Leonidas Guiba"
+  venue: "CVPR 2025"
+  links:
+    paper: "https://openaccess.thecvf.com/content/CVPR2025/html/Gu_BlenderGym_Benchmarking_Foundational_Model_Systems_for_Graphics_Editing_CVPR_2025_paper.html"
+    github: "https://github.com/richard-guyunqi/BlenderGym-Open"
+    website: "https://blendergym.github.io/"
+
 - title: "SyncMind: Measuring Agent Out-of-Sync Recovery in Collaborative Software Engineering"
   authors: "Xuehang Guo, Xingyao Wang, Yangyi Chen, Sha Li, Chi Han, Manling Li, Heng Ji"
   venue: "ICML 2025"
@@ -150,6 +198,14 @@
     github: "https://github.com/uiuc-kang-lab/cve-bench"
     website: ""
 
+- title: "WebMMU: A Benchmark for Multimodal Multilingual Website Understanding and Code Generation"
+  authors: "Rabiul Awal, Mahsa Massoud, Aarash Feizi, Zichao Li, Suyuchen Wang, Christopher Pal, Aishwarya Agrawal, David Vazquez, Siva Reddy, Juan A. Rodriguez, Perouz Taslakian, Spandana Gella, Sai Rajeswar"
+  venue: "EMNLP 2025"
+  links:
+    paper: "https://arxiv.org/abs/2508.16763"
+    github: ""
+    website: "https://webmmu-paper.github.io/"
+
 - title: "CVE-Bench: Benchmarking LLM-based Software Engineering Agent’s Ability to Repair Real-World CVE Vulnerabilities"
   authors: "Peiran Wang, Xiaogeng Liu, Chaowei Xiao"
   venue: "NAACL 2025"
@@ -166,6 +222,22 @@
     github: "https://github.com/FSoft-AI4Code/RepoExec"
     website: "https://fsoft-ai4code.github.io/repoexec/"
 
+- title: "FEA-Bench: A Benchmark for Evaluating Repository-Level Code Generation for Feature Implementation"
+  authors: "Wei Li, Xin Zhang, Zhongxin Guo, Shaoguang Mao, Wen Luo, Guangyue Peng, Yangyu Huang, Houfeng Wang, Scarlett Li"
+  venue: "ACL 2025"  
+  links:
+    paper: "https://arxiv.org/abs/2503.06680"
+    github: "https://github.com/microsoft/FEA-Bench"
+    website: "https://gmago-leway.github.io/fea-bench.github.io/"
+
+- title: "ProjectEval: A Benchmark for Programming Agents Automated Evaluation on Project-Level Code Generation"
+  authors: "Kaiyuan Liu, Youcheng Pan, Yang Xiang, Daojing He, Jing Li, Yexing Du, Tianrun Gao"
+  venue: "ACL 2025 Findings"
+  links:
+    paper: "https://aclanthology.org/2025.findings-acl.1036/"
+    github: "https://github.com/RyanLoil/ProjectEval/"
+    website: ""
+
 - title: "EnvBench: A Benchmark for Automated Environment Setup"
   authors: "Aleksandra Eliseeva, Alexander Kovrigin, Ilia Kholkin, Egor Bogomolov, Yaroslav Zharov"
   venue: "ICLR 2025 Workshop"
@@ -189,3 +261,19 @@
     paper: "https://arxiv.org/abs/2310.06770"
     github: "https://github.com/SWE-bench/SWE-bench"
     website: "https://www.swebench.com/"
+
+- title: "CADTalk: An Algorithm and Benchmark for Semantic Commenting of CAD Programs"
+  authors: "Haocheng Yuan, Jing Xu, Hao Pan, Adrien Bousseau, Niloy J. Mitra, Changjian Li"
+  venue: "CVPR 2024"
+  links:
+    paper: "https://openaccess.thecvf.com/content/CVPR2024/html/Yuan_CADTalk_An_Algorithm_and_Benchmark_for_Semantic_Commenting_of_CAD_CVPR_2024_paper.html"
+    github: "https://github.com/YYYYYHC/CADTalk"
+    website: "https://enigma-li.github.io/CADTalk/"
+
+- title: "DA-Code: Agent Data Science Code Generation Benchmark for Large Language Models"
+  authors: "Yiming Huang, Jianwen Luo, Yan Yu, Yitong Zhang, Fangyu Lei, Yifan Wei, Shizhu He, Lifu Huang, Xiao Liu, Jun Zhao, Kang Liu"
+  venue: "EMNLP 2024"
+  links:
+    paper: "https://aclanthology.org/2024.emnlp-main.748/"
+    github: "https://github.com/yiyihum/da-code"
+    website: "https://da-code-bench.github.io/"

data/papers_benchmarks.yaml

@@ -1,3 +1,19 @@
+- title: "MORSE-500: A Programmatically Controllable Video Benchmark to Stress-Test Multimodal Reasoning"
+  authors: "Zikui Cai, Andrew Wang, Anirudh Satheesh, Ankit Nakhawa, Hyunwoo Jae, Keenan Powell, Minghui Liu, Neel Jay, Sungbin Oh, Xiyao Wang, Yongyuan Liang, Tom Goldstein, Furong Huang"
+  venue: "arXiv 2025"
+  links:
+    paper: "https://arxiv.org/abs/2506.05523"
+    github: "https://github.com/morse-benchmark/morse-500"
+    website: "https://morse-500.github.io/"
+
+- title: "Chain-of-Modality: Learning Manipulation Programs from Multimodal Human Videos with Vision-Language-Models"
+  authors: "Chen Wang, Fei Xia, Wenhao Yu, Tingnan Zhang, Ruohan Zhang, C. Karen Liu, Li Fei-Fei, Jie Tan, Jacky Liang"
+  venue: "ICRA 2025"
+  links:
+    paper: "https://arxiv.org/abs/2504.13351"
+    github: ""
+    website: "https://chain-of-modality.github.io/"
+
 - title: "Visual Agentic AI for Spatial Reasoning with a Dynamic API"
   authors: "Damiano Marsili, Rohun Agrawal, Yisong Yue, Georgia Gkioxari"
   venue: "CVPR 2025"
@@ -38,6 +54,14 @@
     github: "https://github.com/haotang1995/WorldCoder"
     website: "https://haotang1995.github.io/projects/worldcoder"
 
+- title: "RoboCodeX: Multimodal Code Generation for Robotic Behavior Synthesis"
+  authors: "Yao Mu, Junting Chen, Qinglong Zhang, Shoufa Chen, Qiaojun Yu, Chongjian Ge, Runjian Chen, Zhixuan Liang, Mengkang Hu, Chaofan Tao, Peize Sun, Haibao Yu, Chao Yang, Wenqi Shao, Wenhai Wang, Jifeng Dai, Yu Qiao, Mingyu Ding, Ping Luo"
+  venue: "ICML 2024"
+  links:
+    paper: "https://dl.acm.org/doi/10.5555/3692070.3693552"
+    github: "https://github.com/RoboCodeX-source/RoboCodeX_code"
+    website: "https://sites.google.com/view/robocodexplus"
+
 - title: "RoboScript: Code Generation for Free-Form Manipulation Tasks across Real and Simulation"
   authors: "Junting Chen, Yao Mu, Qiaojun Yu, Tianming Wei, Silang Wu, Zhecheng Yuan, Zhixuan Liang, Chao Yang, Kaipeng Zhang, Wenqi Shao, Yu Qiao, Huazhe Xu, Mingyu Ding, Ping Luo"
   venue: "arXiv 2024"
@@ -69,3 +93,11 @@
     paper: "https://arxiv.org/abs/2209.07753"
     github: "https://github.com/google-research/google-research/tree/master/code_as_policies"
     website: "https://code-as-policies.github.io/"
+
+- title: "Instruct2Act: Mapping Multi-modality Instructions to Robotic Actions with Large Language Model"
+  authors: "Siyuan Huang, Zhengkai Jiang, Hao Dong, Yu Qiao, Peng Gao, Hongsheng Li"
+  venue: "arXiv 2023"
+  links:
+    paper: "https://arxiv.org/abs/2305.11176"
+    github: "https://github.com/OpenGVLab/Instruct2Act"
+    website: ""

data/papers_code_executing_embodied.yaml

@@ -1,3 +1,19 @@
+- title: "SkillWeaver: Web Agents can Self-Improve by Discovering and Honing Skills"
+  authors: "Boyuan Zheng, Michael Y. Fatemi, Xiaolong Jin, Zora Zhiruo Wang, Apurva Gandhi, Yueqi Song, Yu Gu, Jayanth Srinivasa, Gaowen Liu, Graham Neubig, Yu Su"
+  venue: "arXiv 2025"
+  links:
+    paper: "https://arxiv.org/abs/2504.07079"
+    github: "https://github.com/OSU-NLP-Group/SkillWeaver"
+    website: "https://osu-nlp-group.github.io/SkillWeaver/"
+
+- title: "WebDS: An End-to-End Benchmark for Web-based Data Science"
+  authors: "Ethan Hsu, Hong Meng Yam, Ines Bouissou, Aaron Murali John, Raj Thota, Josh Koe, Vivek Sarath Putta, G K Dharesan, Alexander Spangher, Shikhar Murty, Tenghao Huang, Christopher D. Manning"
+  venue: "arXiv 2025"
+  links:
+    paper: "https://arxiv.org/abs/2508.01222"
+    github: ""
+    website: ""
+
 - title: "Tree-of-Code: A Self-Growing Tree Framework for End-to-End Code Generation and Execution in Complex Tasks"
   authors: "Ziyi Ni, Yifan Li, Ning Yang, Dou Shen, Pin Lyu, Daxiang Dong"
   venue: "ACL 2025 Findings"

data/papers_code_executing_web.yaml

@@ -1,3 +1,11 @@
+- title: "Improving Cursor Tab with online RL"
+  authors: "Jacob Jackson, Phillip Kravtsov, Shomil Jain"
+  venue: "2025"
+  links:
+    paper: "https://cursor.com/blog/tab-rl"
+    github: ""
+    website: ""
+
 - title: "EvoAgentX: An Automated Framework for Evolving Agentic Workflows"
   authors: "Yingxu Wang, Siwei Liu, Jinyuan Fang, Zaiqiao Meng"
   venue: "arXiv 2025"
@@ -102,6 +110,14 @@
     github: "https://github.com/OpenBMB/ChatDev/tree/macnet"
     website: ""
 
+- title: "Commit0: Library Generation from Scratch"
+  authors: "Wenting Zhao, Nan Jiang, Celine Lee, Justin T Chiu, Claire Cardie, Matthias Gallé, Alexander M Rush"
+  venue: "ICLR 2025"
+  links:
+    paper: "https://openreview.net/forum?id=MMwaQEVsAg"
+    github: "https://github.com/commit-0/commit0"
+    website: "https://commit-0.github.io/"
+
 - title: "AgentVerse: Facilitating Multi-Agent Collaboration and Exploring Emergent Behaviors"
   authors: "Weize Chen, Yusheng Su, Jingwei Zuo, Cheng Yang, Chenfei Yuan, Chi-Min Chan, Heyang Yu, Yaxi Lu, Yi-Hsin Hung, Chen Qian, Yujia Qin, Xin Cong, Ruobing Xie, Zhiyuan Liu, Maosong Sun, Jie Zhou"
   venue: "ICLR 2024"

data/papers_code_generation.yaml

@@ -61,3 +61,11 @@
     paper: "https://openreview.net/forum?id=qnE2m3pIAb"
     github: ""
     website: ""
+
+- title: "AgentGen: Enhancing Planning Abilities for Large Language Model based Agent via Environment and Task Generation"
+  authors: "Mengkang Hu, Pu Zhao, Can Xu, Qingfeng Sun, Jianguang Lou, Qingwei Lin, Ping Luo, Saravan Rajmohan"
+  venue: "KDD 2025"
+  links:
+    paper: "https://dl.acm.org/doi/abs/10.1145/3690624.3709321"
+    github: "https://github.com/Aaron617/AgentGen"
+    website: "https://agent-gen.github.io/"

data/papers_data_synthesis.yaml

@@ -0,0 +1,7 @@
+- title: "Measuring the Impact of Early-2025 AI on Experienced Open-Source Developer Productivity"
+  authors: "Joel Becker, Nate Rush, Elizabeth Barnes, David Rein"
+  venue: "arxiv 2025"
+  links:
+    paper: "https://arxiv.org/abs/2507.09089"
+    github: ""
+    website: ""