Parishad BehnamGhader
@ParishadBehnam
NLP PhD student at @Mila_Quebec and @mcgillu
The video is online now! 3min speed science talk on "From a soup of raw pixels to abstract meaning" youtu.be/AHsoMYG2Vqk?si…
Turns out condensing your research into 3min is very hard but also teaches you a lot
"Build the web for agents, not agents for the web" This position paper argues that rather than forcing web agents to adapt to UIs designed for humans, we should develop a new interface optimized for web agents, which we call Agentic Web Interface (AWI).
Current KL estimation practices in RLHF can generate high variance and even negative values! We propose a provably better estimator that only takes a few lines of code to implement.🧵👇 w/ @xtimv and Ryan Cotterell code: arxiv.org/pdf/2504.10637 paper: github.com/rycolab/kl-rb
Excited to be part of this panel today at the WiML social, 12:30 PM - 2:00 PM, Hall 1 Apex
We are honored to be joined by 4 amazing women in ML on the "Papers, Patents, or Products?" panel: - @ReyhaneAskari (FAIR) - @nouhadziri (AI2) - @vernadec (U Tübingen) - Katherine Driscoll (Graph Therapeutics)
AgentRewardBench: Evaluating Automatic Evaluations of Web Agent Trajectories We are releasing the first benchmark to evaluate how well automatic evaluators, such as LLM judges, can evaluate web agent trajectories. We find that rule-based evals underreport success rates, and…
Introducing nanoAhaMoment: Karpathy-style, single file RL for LLM library (<700 lines) - super hackable - no TRL / Verl, no abstraction💆♂️ - Single GPU, full param tuning, 3B LLM - Efficient (R1-zero countdown < 10h) comes with a from-scratch, fully spelled out YT video [1/n]
Talking about "DeepSeek-R1 Thoughtology: Let’s <think> about LLM reasoning" Going live at 11am PDT (i.e., 20 mins). Last minute change of plans. You might be able to see live here: youtube.com/watch?v=aO_cTI…
I will be giving a talk about this work @SimonsInstitute tomorrow (Apr 2nd 3PM PT). Join us, both in-person or virtually. simons.berkeley.edu/workshops/futu…
Models like DeepSeek-R1 🐋 mark a fundamental shift in how LLMs approach complex problems. In our preprint on R1 Thoughtology, we study R1’s reasoning chains across a variety of tasks; investigating its capabilities, limitations, and behaviour. 🔗: mcgill-nlp.github.io/thoughtology/
me when I see Promptriever has the highest score in some columns
Instruction-following retrievers can efficiently and accurately search for harmful and sensitive information on the internet! 🌐💣 Retrievers need to be aligned too! 🚨🚨🚨 Work done with the wonderful @ncmeade and @sivareddyg 🔗 mcgill-nlp.github.io/malicious-ir/ Thread: 🧵👇
Agents like OpenAI Operator can solve complex computer tasks, but what happens when users use them to cause harm, e.g. automate hate speech and spread misinformation? To find out, we introduce SafeArena (safearena.github.io), a benchmark to assess the capabilities of web…
📢New Paper Alert!🚀 Human alignment balances social expectations, economic incentives, and legal frameworks. What if LLM alignment worked the same way?🤔 Our latest work explores how social, economic, and contractual alignment can address incomplete contracts in LLM alignment🧵
🚀 New Paper Alert! Can we generate informative synthetic data that truly helps a downstream learner? Introducing Deliberate Practice for Synthetic Data (DP)—a dynamic framework that focuses on where the model struggles most to generate useful synthetic training examples. 🔥…
Presenting ✨ 𝐂𝐇𝐀𝐒𝐄: 𝐆𝐞𝐧𝐞𝐫𝐚𝐭𝐢𝐧𝐠 𝐜𝐡𝐚𝐥𝐥𝐞𝐧𝐠𝐢𝐧𝐠 𝐬𝐲𝐧𝐭𝐡𝐞𝐭𝐢𝐜 𝐝𝐚𝐭𝐚 𝐟𝐨𝐫 𝐞𝐯𝐚𝐥𝐮𝐚𝐭𝐢𝐨𝐧 ✨ Work w/ fantastic advisors @DBahdanau and @sivareddyg Thread 🧵: