Niv Eckhaus
@niveckhaus
CS MSc Student @nlphuji
🚨 New Paper: "Time to Talk"! 🕵️ We built an LLM agent that doesn't just decide WHAT to say, but also WHEN to say it! Introducing "Time to Talk" - LLM agents for asynchronous group communication, tested in real Mafia games with human players. 🌐niveck.github.io/Time-to-Talk 🧵1/7
🚨 Introducing IGCS, accepted to #TACL! Instruction Guided Content Selection (IGCS) unifies many tasks such as extractive summarization, evidence retrieval and argument mining under one scheme for selecting extractive spans in given sources. arxiv.org/abs/2507.16922 @biunlp (1/n)
Thrilled that our paper on Confidence-Informed Self-Consistency (CISC) has been accepted to #ACL2025 Findings! 🎉 Paper: arxiv.org/abs/2502.06233 (1/2)
🧵 Excited (really!) to share our new paper "Modeling Fair Play in Detective Stories with Language Models"! w/ @AbendOmri, @RKeydar Paper: arxiv.org/abs/2507.13841 #NLP #MachineLearning #DetectiveFiction #Storytelling #AI (1/15)
🤔 When are 𝐞𝐧𝐬𝐞𝐦𝐛𝐥𝐞𝐬 interpretable and when are they 𝑢𝑛-interpretable? In our new #ICML2025 paper (presenting 𝐭𝐨𝐝𝐚𝐲!), we provide a mathematical theory 😲 based on computational complexity 🧠 to answer this question! And the answers might surprise you!
🚨 New #ICML2025 paper! 𝐄𝐱𝐩𝐥𝐚𝐢𝐧𝐢𝐧𝐠, 𝐅𝐚𝐬𝐭 𝐚𝐧𝐝 𝐒𝐥𝐨𝐰 We generate explanations for neural networks 𝑒𝑓𝑓𝑖𝑐𝑖𝑒𝑛𝑡𝑙𝑦 and 𝑤𝑖𝑡ℎ 𝑝𝑟𝑜𝑣𝑎𝑏𝑙𝑒 𝑔𝑢𝑎𝑟𝑎𝑛𝑡𝑒𝑒𝑠 by pruning to a much smaller model and gradually expand it to ensure provable guarantees.
Happy to announce that our paper “EditInspector: A Benchmark for Evaluation of Text-Guided Image Edits” was accepted to #ACL2025 🎉 📄 arxiv.org/abs/2506.09988 🌐 editinspector.github.io
🚨 New paper alert! PAST: phonetic-acoustic speech tokenizer – just got accepted to Interspeech 2025 🎉 It learns phonetic + acoustic tokens jointly, with no SSL babysitter or external vocoder. 🔗pages.cs.huji.ac.il/adiyoss-lab/PA… 👇 If you’re into speech LMs, keep reading!
Exciting news from #ICML2025 & #ICCV2025 🥳 - 🥇 VideoJAM accepted as *oral* at #ICML2025 (top 1%) - Two talks at #ICCV2025 ☝️interpretability in the generative era ✌️video customization - Organizing two #ICCV2025 workshops ☝️structural priors for vision ✌️long video gen 🧵👇
VideoJAM is our new framework for improved motion generation from @AIatMeta We show that video generators struggle with motion because the training objective favors appearance over dynamics. VideoJAM directly adresses this **without any extra data or scaling** 👇🧵
@karpathy Thanks for the inspiring talk (as always!). I'm the author of the Model Atlas. I'm delighted you liked our work, seeing the figure in your slides felt like an "achievement unlocked"🙌Would really appreciate a link to our work in your slides/tweet arxiv.org/abs/2503.10633
Nice - my AI startup school talk is now up! Chapters: 0:00 Imo fair to say that software is changing quite fundamentally again. LLMs are a new kind of computer, and you program them *in English*. Hence I think they are well deserving of a major version upgrade in terms of…
Click2Mask demos are live! 🎯 Glad to share that demos for our paper Click2Mask are now live: 🤗 HF: huggingface.co/spaces/omerege… (give it a ❤️ if you like it!) 📓 Colab: colab.research.google.com/github/omerege… Paper with @OmriAvr & @DaniLischinski #AI #MachineLearning #GenerativeAI #AAAI25
🎵💬 If you are interested in Audio Tokenisers, you should check out our new work! We empirically analysed existing tokenisers from every way - reconstruction, downstream, LMs and more. Grab yourself a ☕/🍺 and sit down for a read!
Which modeling to choose for text-to-music generation? We run a head-to-head comparison to figure it out. Same data, same architecture - AR vs FM. 👇 If you care about fidelity, speed, control, or editing see this thread. 🔗huggingface.co/spaces/ortal16… 📄arxiv.org/abs/2506.08570 1/6
🔔 New Paper! We propose a challenging new benchmark for LLM judges: Evaluating debate speeches. Are they comparable to humans? Well... it’s debatable. 🤔 noy-sternlicht.github.io/Debatable-Inte… 👇 Here are our findings: