Weiqi Wang (@MightyWeaver2) header
Weiqi Wang (@MightyWeaver2) profile picture

Research Scientist @TencentHunyuan | PhD @HKUSTKnowComp supervised by @yqsong

Beijing, China
Joined August 2021
Photo by Weiqi Wang (@MightyWeaver2)Photo by Weiqi Wang (@MightyWeaver2)Photo by Weiqi Wang (@MightyWeaver2)Photo by Weiqi Wang (@MightyWeaver2)Photo by Weiqi Wang (@MightyWeaver2)Photo by Weiqi Wang (@MightyWeaver2)Photo by Weiqi Wang (@MightyWeaver2)
Weiqi Wang retweeted
🚀 Hy4 preview is here. 770B, 49B active, 1M context. Built for productivity. Open source frontier. Consistent affordable price. Use it. Tell us what breaks. More on Hy blog:hy.tencent.ai/research/hy4-p… HuggingFace:huggingface.co/tencent/Hy4-p… Github:github.com/Tencent-Hunyuan/H…
337
556
421
5,341
2,852,422
Weiqi Wang retweeted
🚀Hy3 is here. 295B MoE. Best in its size class. Rivals trillion-scale flagships. Reliable and affordable for most agentic usecases. Apache 2.0. Friendly for commercial use. FREE API for 2 weeks → openrouter.ai/tencent/hy3:fr… 🤗 huggingface.co/tencent/Hy3 📖 hy.tencent.com/research/hy3
190
383
226
2,875
1,227,339
🚀 We are thrilled to release a new open-source Deep Research Agent, Cognitive Kernel-Pro, from Tencent AI Lab! We focus on building a fully open-source agent with (to the maximum extent) free tools, showcasing impressive performance on GAIA with Claude-3.7-sonnet and surpass the counterpart, SmolAgents by a large margin. In addition, we study the training recipe for an open-source Deep Research Agent Foundation Model. We curate high-quality training data (queries, trajectories, and verifiable answers across web, file, code, and reasoning domains). Our finetuned Qwen3-8B (CK-Pro-8B) surpasses WebDancer and WebSailor with the similar model size on the text-only subset of GAIA. 📜 Paper: arxiv.org/pdf/2508.00414 🔧 Code: github.com/Tencent/Cognitive… 🤗 Data & Model: huggingface.co/datasets/Cogn… huggingface.co/CognitiveKern… This work builds on the previous efforts of Tencent AI Lab (Fig. 2). Be sure to check them out if you're interested!
24
4
87
9,249
Weiqi Wang retweeted
“Concepts are the glue that holds our mental world together.”– Murphy (2004) I started to work on conceptualization in 2010 when I joined #MSRA to work on #Probase (haixun.github.io/probase.htm…) with Haixun Wang @haixunwang . At that time, we leveraged Probase to conceptualize things in the world through contextualization and composition. We started to think what if we can also conceptualize events? I worked with my intern Fangting Xia, however, we met much difficulty. Later when I joined #HKUST, I started my project, #ASER (Activities, States, Events, and their Relations, github.com/HKUST-KnowComp/AS…), with my students Hongming Zhang @hongming110 , Xin Liu, and Haojie Pan. We use IE to find a lot discourse relations for events, and we prove that we can transfer such knowledge to commonsense knowledge such as #TransOMCS (github.com/HKUST-KnowComp/Tr…) and #DISCOS (github.com/HKUST-KnowComp/DI…). In ASER, we started to build on our idea of conceptualization. Then we initiated the new project, #AbstractATOMIC (github.com/HKUST-KnowComp/at…), in which we conceptualize both entities and events in #ATOMIC knowledge base. Now, I am so happy that the paper has been eventually accepted by Artificial Intelligence (doi.org/10.1016/j.artint.202…). Big thanks to my students Mutian He, Tianqing Fang @TFang229, and Weiqi Wang @MightyWeaver2 . In fact, the review took 2 years, but we have been working on conceptualization without waiting for the outcome. Here is the list of what we have been doing: On the Role of Entity and Event Level Conceptualization in Generalizable Reasoning: A Survey of Tasks, Methods, Applications, and Future Directions AbsInstruct: Eliciting Abstraction Ability from LLMs through Explanation Tuning with Plausibility Estimation (github.com/HKUST-KnowComp/Ab…) AbsPyramid: Benchmarking the Abstraction Ability of Language Models with a Unified Entailment Graph (github.com/HKUST-KnowComp/Ab…) 🕯️CANDLE: Iterative Conceptualization and Instantiation Distillation from Large Language Models for Commonsense Reasoning (github.com/HKUST-KnowComp/CA…) 🚗CAR: Conceptualization-Augmented Reasoner for Zero-Shot Commonsense Question Answering (github.com/HKUST-KnowComp/CA…) 🐈CAT: A Contextualized Conceptualization and Instantiation Framework for Commonsense Reasoning (github.com/HKUST-KnowComp/CA…) Moving forward, we are now working on something beyond social and physical knowledge reasoning, which we call metaphysical reasoning (github.com/HKUST-KnowComp/MA…). The essential building block of such reasoning is again, conceptualization. I am really excited about the development we have done. It's something like your 10+ year dream coming true. I really appreciate all my collaborators, especially my genius students working on related stuff, trusting me and pushing this direction to be even more interesting!
8
1
24
2,628
It's only been 1 day of CES 2024, and the tech developments have been incredible. The 10 most impressive reveals of CES 2024 so far: 1. The world's first transparent MICROLED screen by Samsung
439
4,398
847
39,509
14,728,302
Weiqi Wang retweeted
Excited to announce our NeurIPS paper on for querying KGs and improving logical inference! Traditional approaches mainly focus on entity KGs, but in the real world, we need to reason about events, states, and activities too. #NeurIPS2023 #KnowledgeGraphs #LogicalInference – at Central Region, Singapore
3
5
12
1,345
I'll be attending #EMNLP 2023@Singapore in person to present my new paper 🚗CAR about conceptualization for zero-shot commonsense QA on Dec 9th at 9:00AM in Conference Room: East Foyer! Catch me up if you are around :)
2
3
19
2,812
Exciting experiment results reveal our achievement of a new SOTA with ATOMIC-styled CSKBs, surpassing all previous baselines and LLMs, such as GPT-3.5 and ChatGPT.
1
218
Further evaluation has confirmed that conceptualization serves as a powerful augmentation method, significantly expanding the diversity & plausibility and reducing false negative rate.
2
152
705
1,372
470
25,172
1,787,192
The wait is almost over. #GTAVI
Readers added context they thought people might want to know
This account is not official nor affiliated in any way with Rockstar Games or Take-Two. x.com/GTA6Intel
660
8,763
1,784
135,613
15,317,879
Weiqi Wang retweeted
May there be prosperity for all
25,090
27,009
7,669
434,820
68,731,842
So, I wrote about my experience as a Senior Area Chair for EMNLP, hoping to offer some insights on the processes around conference paper decisions. The Impossible Task of Conference SACs/PCs or How I lost 3 Nights of Sleep gist.github.com/antonisa/215… comments/feedback welcome!
5
48
5
202
60,329
2023 is 80% complete.
99
3,536
566
18,745
1,673,708
Weiqi Wang retweeted
📢 Excited to share our latest research accepted at #EMNLP2023 @emnlpmeeting on addressing the hallucination problem in language models (LMs) with "KCTS: Knowledge-Constrained Tree Search Decoding with Token-Level Hallucination Detection"! 🌐🔍
1
6
4
23
6,903
LLMs are used for knowledge-intensive tasks with atomic or linear (multi-hop) QA. But Knowledge often comes with more complex structures. Can LLMs reason with structured knowledge bounded by geometric constraints? Introducing KNOWLEDGE CROSSWORDS🧵[1/n] arxiv.org/abs/2310.01290
1
3
1
11
3,490