🔥The 9th Round of Easy Loan, Earn $40 Reward is in progress❗️ ⏰ Promotion Period: January 15th - Feburary 15th, 2025 👉 Register now and check more details at gate.io/campaigns/358

I wrote a Colab tutorial on MaxEnt RL: colab.research.google.com/drive/1VkoRfg_… It implements the graphical model from Sergey Levine's "RL as Inference" tutorial for a simple chain environment. Play around with the reward function to learn different policies using the forward-backward algorithm!

Our new #emnlp2020 paper on PRover: An interpretable transformer-based model that emulates formal reasoning by jointly answering questions over *explicit knowledge* as facts+rules (in natural language) & generating corresp proof graphs. with Sayan Ghosh, Shashank Srivastava & Mohit Bansal 1/4

Congrats to @uncnlp+collaborators on these exciting #EMNLP2021 papers on explainability/fairness, composition/generalization, generation/summarization, story understanding+visualizn, groundedNLP. Join us for PhD/postdoc positions! cc Mohit Bansal Snigdha Chaturvedi Colin Raffel Shashank Srivastava

Here is the full program from @UNCNLP+collaborators at #EMNLP2021 this week ➡️ nlp.cs.unc.edu/emnlp2021/ We're also 𝗵𝗶𝗿𝗶𝗻𝗴 𝗣𝗼𝘀𝘁𝗱𝗼𝗰𝘀+𝗣𝗵𝗗 𝘀𝘁𝘂𝗱𝗲𝗻𝘁𝘀! Plz spread the word & ping faculty Mohit Bansal Snigdha Chaturvedi Colin Raffel Shashank Srivastava +students for any questions😀

Can we learn to classify purely from language explanations? Check out our #ACL2022 ACL 2025 paper: "CLUES: A Benchmark for Learning Classifiers from Language Explanations" arxiv.org/abs/2204.07142 Joint work w/ Sayan Ghosh and adv. Shashank Srivastava (1/6)

❓ Did you know you can fuse models to reduce unwanted knowledge like shortcuts and biases? 💡 Fused models keep shared knowledge and forget unshared. 🚨Fuse to Forget: Bias Reduction and Selective Memorization through Model Fusion 📄arxiv.org/abs/2311.07682 Leshem (Legend) Choshen 🤖🤗 Shashank Srivastava