Drop a paper. Get a podcast. ResearchPod transforms any academic PDF into an engaging conversation—so you can finally understand what the researchers are saying
Joined February 2018
- Tweets 98
- Following 61
- Followers 2,829
- Likes 300
7 Photos and videos
ResearchPod retweeted
Jun 14
This is cool. A podcast summary of our new web agent paper. Thanks @researchpodapp for sharing the work.
2
2
4
186
ResearchPod retweeted
Jun 11
These days, paper visibility feels really hard, especially for us unknowns. Happy to see the community building more ways to help. Just learned about @HuggingPapers and submitted a short paper there. Many thanks to @researchpodapp for noticing it and turning it into a brilliant podcast with a sleek UI design, and to @NielsRogge for reminding me to release pretrained checkpoints for my previous two papers, as well as direct help with improving the model cards.
Attaching this short paper here to see whether anyone is interested. Main takeaway: instead of focusing only on improving inference sparsity methods, we can also design upstream architectures that are inherently more capable of handling sparse inference.
4
10
35
5,338
May 18
Experimenting with a social media feed like interface to discover new papers 👀
1
5
537
Feb 23
We turned "What Language is This? Ask Your Tokenizer." into a podcast by @clara__meister, Ahmetcan Yavuz, Pietro Lesci & @tpimentelms
researchpod-web.vercel.app/e…
4
261
Feb 22
We turned "Fast KV Compaction via Attention Matching" into a podcast by @linluqiu, Xinghong Fu, Han Guo & Yoon Jung Kim
researchpod-web.vercel.app/e…
3
246
Feb 14
We turned "Moderated estimation of fold change and dispersion for RNA-seq data with DESeq2" into a podcast by @mikelove & @wolfgangkhuber
researchpod-web.vercel.app/e…
3
117
Feb 12
We turned "F-GRPO: Don’t Let Your Policy Learn the Obvious and Forget the Rare" into a podcast
by Daniil Plyusov, @kefirski, Boris Shaposhnikov & 3 others
researchpod-web.vercel.app/e…
2
119
Feb 12
We turned "Bootstrapping Life-Inspired Machine Intelligence: The Biological Route from Chemistry to Cognition and Creativity" into a podcast
by @GiovanniPezzulo & @drmichaellevin
researchpod-web.vercel.app/e…
2
63
Feb 7
Big congrats to @FahimTajwar10, @guanningzeng, @Yueer_Zhou, @yus167, @amuseddaman , @yidingjiang, Jeff Schneider, @rsalakhu, @HavenFeng , @Zanette_ai and the team on MaxRL – a simple one-line change that interpolates between REINFORCE and full maximum likelihood, delivering Pareto-superior performance on reasoning and navigation tasks. 🎉
1
1
8
1,261
Feb 7
Quick insights:
- MaxRL upweights hard examples more aggressively than GRPO by normalizing advantages only over successful samples, preserving strong gradients on low-pass-rate prompts where others wash out.
- It achieves up to 20× test-time scaling efficiency gains with perfect verifiers and Pareto-dominates GRPO across MATH, GSM8K, and maze benchmarks by better utilizing pass@k information.
- In data-scarce regimes MaxRL resists overfitting and converges higher; in infinite-data settings it scales dramatically better with compute while sharpening distributions more effectively.
1
2
156
Feb 7
We turned the paper into a 10-min podcast episode so you can absorb it on the go 🎙️
🔗 Listen: researchpod-share.vercel.app…
📄 Paper: arxiv.org/abs/2602.02710
💻 Code: zanette-labs.github.io/MaxRL…
2
143
ResearchPod retweeted
Feb 5
🚀 Just launched ResearchPod on @trylaunchai!
Research papers, now in your ears.
Check it out and show some love 👇
trylaunch.ai/launch/research…
2
2
2
169
ResearchPod retweeted
Feb 2
Anyone out there reading research papers and would have 20 min to have a chat with me?
I am looking to build a product in this space and would appreciate any insight!
1
2
90
Jan 29
Grad students & researchers: Do you ever wish you could listen to papers while commuting/gym instead of staring at PDFs? Building ResearchPod (papers → podcasts). Looking for 15-min chats to improve it.
54
ResearchPod retweeted
Jan 25
every time i try to have an original research idea but Zhang et al. already published it 3 years ago
283
9,219
62,124
1,724,664
Jan 26
85% dark chocolate (30g/day) reduced negative emotions in just 3 weeks — potentially by boosting gut microbiome diversity 🍫🦠
This 2022 RCT found higher cocoa polyphenols linked to lower irritability/guilt more Blautia obeum.
We turned the full paper into a 5-min podcast episode .
Listen here: researchpod-share.vercel.app…
1
1
78
Jan 23
🚀 Code Sandbox Unlocks Emergent General Agentic Intelligence in LLMs — No Extra Training Needed!
Massive congrats to @DaixuanC45443, Shaohan Huang, Yuxian Gu, Huatong Song, Guoxin Chen, Li Dong, Wayne Xin Zhao, Ji-Rong Wen & Furu Wei on LLM-in-Sandbox – Giving LLMs a virtual computer environment elicits powerful agentic behaviors for non-code tasks. 🎉
1
2
112
Jan 23
Quick insights:
- Strong LLMs spontaneously exploit sandbox tools (file I/O, code execution, external access) to handle long contexts, fetch knowledge, and meet formatting needs without any agent-specific training.
- Reinforcement learning on purely non-agentic data further boosts sandbox exploration, enabling robust generalization across math, physics, chemistry, biomedicine, long-context, and instruction following.
- Delivers major efficiency gains — up to 8× fewer tokens during deployment — making it practical for real-world agentic systems.
1
1
52
Jan 23
We turned the paper into a 20-min podcast episode so you can absorb it on the go 🎙️
🔗 Listen: researchpod-share.vercel.app…
📄 Paper: arxiv.org/abs/2601.16206
💻 Code: github.com/llm-in-sandbox/ll…
1
56