Look for any podcast host, guest or anyone
Showing episodes and shows of

Cihang Ma

Shows

Daily Paper Cast
Daily Paper CastAutoResearchClaw: Self-Reinforcing Autonomous Research with Human-AI Collaboration 🤗 Upvotes: 53 | cs.AI Authors: Jiaqi Liu, Shi Qiu, Mairui Li, Bingzhou Li, Haonian Ji, Siwei Han, Xinyu Ye, Peng Xia, Zihan Dong, Congyu Zhang, Letian Zhang, Guiming Chen, Haoqin Tu, Xinyu Yang, Lu Feng, Xujiang Zhao, Haifeng Chen, Jiawei Zhou, Xiao Wang, Weitong Zhang, Hongtu Zhu, Yun Li, Jieru Mei, Hongliang Fei, Jiaheng Zhang, Linjie Li, Linjun Zhang, Yuyin Zhou, Sheng Wang, Caiming Xiong, James Zou, Zeyu Zheng, Cihang Xie, Mingyu Ding, Huaxiu Yao Title: AutoResearchClaw: Self-Reinforcing Autonomous Research with Human-AI Collaboration Arxiv: http://arxiv.org/abs/2605.20025v1 Abs...
2026-05-2123 minDaily Paper Cast
Daily Paper CastClawMark: A Living-World Benchmark for Multi-Turn, Multi-Day, Multimodal Coworker Agents 🤗 Upvotes: 27 | cs.CV, cs.SE Authors: Fanqing Meng, Lingxiao Du, Zijian Wu, Guanzheng Chen, Xiangyan Liu, Jiaqi Liao, Chonghe Jiang, Zhenglin Wan, Jiawei Gu, Pengfei Zhou, Rui Huang, Ziqi Zhao, Shengyuan Ding, Ailing Yu, Bo Peng, Bowei Xia, Hao Sun, Haotian Liang, Ji Xie, Jiajun Chen, Jiajun Song, Liu Yang, Ming Xu, Qionglin Qiu, Runhao Fu, Shengfang Zhai, Shijian Wang, Tengfei Ma, Tianyi Wu, Weiyang Jin, Yan Wang, Yang Dai, Yao Lai, Youwei Shu, Yue Liu, Yunzhuo Hao, Yuwei Niu, Jinkai Huang, Jiayuan Zhuo, Zhennan Shen, Linyu Wu, Cihang Xie, Yuyin Zhou, Jiaheng Zhang, Zeyu Zheng, Men...
2026-04-2922 minDaily Paper Cast
Daily Paper CastClawArena: Benchmarking AI Agents in Evolving Information Environments 🤗 Upvotes: 27 | cs.LG, cs.AI, cs.CL Authors: Haonian Ji, Kaiwen Xiong, Siwei Han, Peng Xia, Shi Qiu, Yiyang Zhou, Jiaqi Liu, Jinlong Li, Bingzhou Li, Zeyu Zheng, Cihang Xie, Huaxiu Yao Title: ClawArena: Benchmarking AI Agents in Evolving Information Environments Arxiv: http://arxiv.org/abs/2604.04202v1 Abstract: AI agents deployed as persistent assistants must maintain correct beliefs as their information environment evolves. In practice, evidence is scattered across heterogeneous sources that often contradict one another, new information can invalidate earlier conclusions, and user preferences surface through cor...
2026-04-0821 minAI Post Transformers
AI Post TransformersMetaClaw: Just Talk and Continual Agent AdaptationThis episode takes up the thread from the published episode "MAML and the Basics of Meta-Learning" and shows how those ideas reappear in a much messier setting: a live agent that has to keep improving while it is already deployed. Instead of treating meta-learning as a clean laboratory exercise, the discussion follows MetaClaw as a continual agent system built for changing real workloads, where coding assistants, research agents, and other LLM-based tools face drift in tasks, tools, and failure modes. The hosts frame the paper as a concrete answer to a practical question: how an agent can keep learning on...
2026-03-3100 minDaily Paper Cast
Daily Paper CastMetaClaw: Just Talk -- An Agent That Meta-Learns and Evolves in the Wild 🤗 Upvotes: 97 | cs.LG Authors: Peng Xia, Jianwen Chen, Xinyu Yang, Haoqin Tu, Jiaqi Liu, Kaiwen Xiong, Siwei Han, Shi Qiu, Haonian Ji, Yuyin Zhou, Zeyu Zheng, Cihang Xie, Huaxiu Yao Title: MetaClaw: Just Talk -- An Agent That Meta-Learns and Evolves in the Wild Arxiv: http://arxiv.org/abs/2603.17187v1 Abstract: Large language model (LLM) agents are increasingly used for complex tasks, yet deployed agents often remain static, failing to adapt as user needs evolve. This creates a tension between the need for continuous service and the nec...
2026-03-2023 minDaily Tech Feed: From the Labs
Daily Tech Feed: From the LabsSkillRL: Don't Give Agents Memories, Give Them SkillsEpisode 008: SkillRL — Teaching AI Agents to Learn Skills, Not Memories Why it matters. LLM agents that learn from experience typically store raw trajectories — verbose logs of every action taken. This is like studying for an exam by memorizing every page of the textbook instead of extracting key concepts. "SkillRL: Evolving Agents via Recursive Skill-Augmented Reinforcement Learning" introduces a framework that distills experience into compact, reusable skills and evolves them through reinforcement learning. Using Qwen 2.5 at just 7 billion parameters, SkillRL achieves 89.9% on ALFWorld — beating GPT-4o by 41.9 points and Gemini 2.5 Pro by 29.6 points — while compressing knowledge 10–20× compared to raw traject...
2026-02-1819 minDaily Paper Cast
Daily Paper CastWhen Visualizing is the First Step to Reasoning: MIRA, a Benchmark for Visual Chain-of-Thought 🤗 Upvotes: 42 | cs.CV Authors: Yiyang Zhou, Haoqin Tu, Zijun Wang, Zeyu Wang, Niklas Muennighoff, Fan Nie, Yejin Choi, James Zou, Chaorui Deng, Shen Yan, Haoqi Fan, Cihang Xie, Huaxiu Yao, Qinghao Ye Title: When Visualizing is the First Step to Reasoning: MIRA, a Benchmark for Visual Chain-of-Thought Arxiv: http://arxiv.org/abs/2511.02779v1 Abstract: We propose MIRA, a new benchmark designed to evaluate models in scenarios where generating intermediate visual images is essential for successful reasoning. Unlike traditional CoT methods that rely solely on text, tasks in MIR...
2025-11-0624 minNature Breaking
Nature BreakingWhat is Green Hydrogen? An Important But Complex Climate Solution, ExplainedWhat is green hydrogen? In short, it's hydrogen produced using entirely renewable electricity, which can then be used for industrial processes like creating cement or steel, among other things. That's important because those industrial processes are currently the third-largest source of greenhouse gases in the United States, after the transportation and electricity sectors. If we can power those processes with green hydrogen instead of fossil fuels, it could go a long way toward helping the US meet its climate goals. But getting there is pretty complicated. On today's episode, you'll hear from Cihang Yuan, WWF's Senior Program Officer for...
2024-02-0628 minBreak A Wish
Break A WishPinocchio (1940)We are joins by Cihang Ma and Griffin Toplitsky to discuss Pinocchio (1940) and as a result the economics of turning boys into donkeys. Brought to you By: The Sonar Network
2021-02-2245 minThe Pen Is Mightier
The Pen Is MightierEpisode 2 - CooperationFeaturing Clare Blackwood (The Beaverton), Maddox Campbell (Break A Wish, Caverns & Comedians), and Cihang Ma (Bob Curry Fellowship, Second City Toronto). This week the panel discusses what makes the most effective compliment, how much of the population...The post Episode 2 – Cooperation appeared first on PodCavern.
2020-12-0553 minPodCavern
PodCavernEpisode 2 - CooperationFeaturing Clare Blackwood (The Beaverton), Maddox Campbell (Break A Wish, Caverns & Comedians), and Cihang Ma (Bob Curry Fellowship, Second City Toronto). This week the panel discusses what makes the most effective compliment,... The post Episode 2 – Cooperation appeared first on PodCavern.
2020-12-0553 minThe Pen Is Mightier
The Pen Is MightierEpisode 2 - CooperationFeaturing Clare Blackwood (The Beaverton), Maddox Campbell (Break A Wish, Caverns & Comedians), and Cihang Ma (Bob Curry Fellowship, Second City Toronto). This week the panel discusses what makes the most effective compliment,... The post Episode 2 – Cooperation appeared first on PodCavern.
2020-12-0553 minpodcavern\'s podcast
podcavern's podcastEpisode 2 - CooperationFeaturing Clare Blackwood (The Beaverton), Maddox Campbell (Break A Wish, Caverns & Comedians), and Cihang Ma (Bob Curry Fellowship, Second City Toronto). This week the panel discusses what makes the most effective compliment,... The post Episode 2 – Cooperation appeared first on PodCavern.
2020-12-0553 minBreak A Wish
Break A WishMr Destiny (1990)In this episode I’m joined by Anne McMaster and Cihang Ma to break down “Mr Destiny” (1990) the film the universe forgot existed. Brought to you By: The Sonar Network
2020-10-2544 minThe Liquid Courage Podcast
The Liquid Courage PodcastEp. 16 - Cihang MaIn today’s episode, Amanda sits down over a hot cup of black coffee with actor and improvisor Cihang Ma (Roses & Thorns, Carpe Into My DMs, A Christmas Carol) to discuss anger, our skincare routines, and the importance of feeling seen (both on stage/screen and by the people around you!). Cihang is a current cast member of the Bad Dog Theatre’s Featured Players: Season 7, an alumna of the Second City Bob Curry Fellowship Program, and the recipient of the Tim Sims Encouragement Fund Award…no big deal. Catch Cihang performing on a variety of comedy shows on Bad Do...
2020-08-202h 01Personal Best
Personal BestKnow More, Carry LessCihang is afraid of running out of things to say. She wishes for a database of interesting tidbits to pull from at parties.
2019-06-0436 min