Bo Liu (Benjamin Liu)
@Benjamin_eecs
Followers
602
Following
3K
Media
13
Statuses
206
RL PhD @NUSingapore | Intern @AIatMeta FAIR | Undergrad @PKU1898 | Building autonomous decision making system | Prev @deepseek_ai | DeepSeek-V2/VL/Prover SPIRAL
New York
Joined February 2022
We've always been excited about self-play unlocking continuously improving agents. Our insight: RL selects generalizable CoT patterns from pretrained LLMs. Games provide perfect testing grounds with cheap, verifiable rewards. Self-play automatically discovers and reinforces
4
51
274
RT @ZhiSu22: 🏓🤖 Our humanoid robot can now rally over 100 consecutive shots against a human in real table tennis — fully autonomous, sub-se….
0
537
0
RT @willccbb: we’ll be @ neurips throwing a multi-turn party! come hang. there’s still time to speedrun a workshop paper this weekend 👀.
0
2
0
RT @mti_neurips: 📢 4 days left to submit to the Workshop on Multi-Turn Interaction for LLMs at #NeurIPS2025!. Exciting updates: .🥂 We're pa….
0
14
0
RT @PrimeIntellect: Introducing the Environments Hub. RL environments are the key bottleneck to the next wave of AI progress, but big labs….
0
387
0
RT @zzlccc: Environment Hub by prime-intellect is awesome with its GUIs!.Scaling environments is key—they provide the signals RL agents lea….
0
18
0
RT @AnthropicAI: We’ve developed Claude for Chrome, where Claude works directly in your browser and takes actions on your behalf. We’re re….
0
973
0
RT @RichardSSutton: I was happy to give a more technical talk on how we might create an AI at RLC-2025 and AGI-2025 (video below). The Oak….
0
100
0
RT @_rockt: Here is @GoogleDeepMind's Sima agent following different instructions inside a world generated by Genie 3. .
0
23
0
RT @shi_weiyan: Thanks @Meta for sponsoring our workshop! . 🩷15 free tickets for students! .🩷 Deadline extended to 9/1/2025, a few more day….
0
5
0
RT @mti_neurips: 🚀 Another exciting news! We're thrilled to announce our second sponsor: @Meta! Thank you for the generous support of our M….
0
10
0
RT @Xidong_Feng: @AlexGDimakis Thanks for mentioning us!. This will be the diff between learning from experience and traditional RL. The sc….
0
1
0
RT @mti_neurips: 🚀 Still have a chance to submit to @NeurIPSConf for our Multi-Turn Workshop! . 🏆 Best Paper Awards .🎓 10-15 Registration W….
0
15
0
RT @tesatory: @lchen915 Nice work! I just wanted to point out that Asymmetric Self-Play was first introduced in 2017, and later improved in….
arxiv.org
We describe a simple scheme that allows an agent to learn about its environment in an unsupervised manner. Our scheme pits two versions of the same agent, Alice and Bob, against one another. Alice...
0
1
0
RT @_rockt: Made in real-time with @GoogleDeepMind's Genie 3. Oh, and it's action-controllable! 😉
0
197
0
RT @demishassabis: One word: relentless. just in the past two weeks, we’ve shipped:. 🌐 Genie 3 - the most advanced world simulator ever.🤔 G….
0
1K
0
RT @jaseweston: . is today a good day for new paper posts? .🤖Learning to Reason for Factuality 🤖.📝: - New reward f….
0
49
0
RT @jparkerholder: Genie 3 feels like a watershed moment for world models 🌐: we can now generate multi-minute, real-time interactive simula….
0
559
0