@dqwang122

PhD student in CMU LTI

 Pittsburgh, PA
dqwang122.github.io
Joined May 2023
  • Tweets37
  • Following92
  • Followers164
13Media
Your coding agent’s code can pass every test and still be exploitable, but users rarely know👾 🤔SFT, RL, or OPD: which teaches security best? 🔥SecureVibe helps vibe coding plan, code, and test for security, +6.9 pts BaxBench, +11.5 unseen CWEs SusVibes, +4.1 SWE-bench Verified
3
11
3
28
2,987
more replies
📄 Paper: arxiv.org/abs/2609.38606 🌐 Website: microsoft.github.io/Orchard-… 💻 Code: github.com/MSR-Orchard/Secur… 📊 Dataset: huggingface.co/datasets/dqwa… Joint work with a wonderful team at Microsoft Research and CMU.

SecureVibe: Making Vibe Coding More Secure

As vibe coding becomes increasingly capable and widespread, security vulnerabilities in even functionally correct solutions are a growing concern. When investigating functionally correct but...

arxiv.org
1
1
3
79
Thanks to my wonderful collaborators Baolin Peng, @weizhepei,@isadorcw,@YaoWenlin, Hao Cheng, @5000hui, @kim__minseon, @ericxyuan, @lileics @JianfengGao0217
2
70
Ever tried a multi-agent system and been shocked by the cost? 💸 HANDRAISER lets listeners interrupt: “Got it. Stop.” ✋ 32.2% lower communication cost. Performance intact. A CMU × Meta FAIR collaboration, accepted to #CoLM2026 🎉 arxiv.org/abs/2604.06452
3
6
1
34
3,682
more replies
7/8 It also generalizes: → to an unseen GPT-4o speaker, without extra fine-tuning → across tasks → to settings where multiple agents may interrupt So HandRaiser is not tied to one model, task, or conversation pattern.
1
2
2
287
8/8 The broader lesson: Efficient multi-agent communication isn't only about making speakers shorter. “I have enough information. Let's act.” Thank all my wonderful collaborators: @Wade_Yin9712 @rutadesai @lileics @real_asli @AnsongNi
2
3
299
Danqing Wang retweeted
Kexun Zhang
@kexun_zhang31 Oct 2024
Everyone talks about scaling inference compute after o1. But how exactly should we do that? We studied compute allocation for sampling -- a basic operation in most LLM meta-generators, and found that optimized allocation can save as much as 128x compute! arxiv.org/abs/2410.22480
6
23
2
107
16,237
Experience 🚀accelerated, 🔝next-level performance with our latest paper on end-to-end story generation! More powerful💪 and faster⚡ than ever. It's a pleasure to work on this exciting project with my amazing collaborators!
Hanlin Zhu@zhuhl982 Nov 2023
Generate a high quality story plot containing thousands of tokens automatically with one click and less than 30 seconds! 😺 Introducing our end-to-end story plot generator, E2EPlot, which is fast in speed and easy to fine-tune! arxiv.org/abs/2310.08796
6
786
📚🌟 Evaluate any story to your heart's content with our new personalized story evaluation model, PerSE! No more worries about diverse preferences - get your own story evaluation report now! 📝🎯 arxiv.org/abs/2310.03304 1/5
1
9
4
31
19,162
more replies
🚀✨ Experience the 𝗯𝗲𝘀𝘁 performances with PerSE! 📊🎯 It outshines in all correction metrics with 𝗵𝘂𝗺𝗮𝗻 𝗿𝗮𝘁𝗶𝗻𝗴, and boasts the highest accuracy in predicting preferred stories across five different aspects. 🔝💯 4/5
1
1
4
865
Great thanks to my excellent collaborators @kevinyang41 Hanlin Zhu, Xiaomeng Yang, @andrew_e_cohen @tydsh @lileics 5/5
4
301
Load more