Want faster #LLM inference without sacrificing accuracy? 🚀. Introducing SD², a novel method using Self-Distilled Sparse Drafters to accelerate speculative decoding. We show that self-data distillation combined #sparsity can be used to train low-latency, well-aligned drafters.🧵

RT @DAlistarh: Contributors:. - QuTLASS is led by @RobertoL_Castro .- FP-Quant contributors @black_samorez @AshkboosSaleh @_EldarKurtic @m….

We will be presenting Self-Distilled Sparse Drafters at #ICML this afternoon at the Efficient Systems for Foundation Models workshop. Come chat with us about acclerating speculative decoding! 🚀. @CerebrasSystems @UCalgaryML

RT @joyce_xxz: Having ideas on backdoor attack, functional&representational similarity, and concept-based explainability? I am looking forw….

RT @utkuevci: It has been a while since I last gave a talk. I gave two lectures on compression and efficient finetuning this April at The….

RT @adnan_ahmad1306: [1/2] 🧵.Presenting our work on Understanding Normalization Layers for Sparse Training today at the HiLD Workshop, ICML….

RT @yanii: We are presenting this poster at #ICML2025 today (Tues. July 15) in the first poster session 📆 11:00-13:30 in East Exhibition H….

RT @yanii: @UCalgaryML will be at #ICML2025 in Vancouver🇨🇦 next week: our lab has 6 different works being presented by 5 students across bo….

RT @sukjun_hwang: Tokenization has been the final barrier to truly end-to-end language models. We developed the H-Net: a hierarchical netw….

RT @WentaoGuo7: 🦆🚀QuACK🦆🚀: new SOL mem-bound kernel library without a single line of CUDA C++ all straight in Python thanks to CuTe-DSL. On….

RT @joyce_xxz: I am excited to share that I will present two of my works at #ICML2025 workshops!. If you are interested in AI security and….

RT @adnan_ahmad1306: Excited to be presenting our work at ICML next week! If you're interested in loss landscapes, weight symmetries, or sp….

RT @CerebrasSystems: Featured Paper at @icmlconf - The Internationall Conference on Machine Learning: . SD² - Self-Distilled Sparse Drafte….

RT @Rexhaif: Looks like OpenReview had enough of these reviewers and decided to lay down :)

"Accept reality as it is, try not to regret the past, and try to improve the situation.". "The challenge that AI poses is the greatest challenge of humanity ever. And overcoming will also bring the greatest reward. And in some sense, whether you like it or not, your life is going.

RT @InfiniAILab: 🥳 Happy to share our new work –  Kinetics: Rethinking Test-Time Scaling Laws. 🤔How to effectively build a powerful reasoni….

RT @LysandreJik: I have bittersweet news to share. Yesterday we merged a PR deprecating TensorFlow and Flax support in transformers. Goin….

RT @openreviewnet: Google Cloud Storage is down and PDF files are temporally unavailable through the OpenReview API. .

RT @vaiter: Singular Value Decomposition is a matrix factorization that expresses a matrix M as UΣVᵀ, where U and V are orthogonal matrices….

*Correction, special thanks to the @CerebrasSystems team.

RT @WenhuChen: 🚨 New Paper Alert 🚨. We found that Supervised Fine-tuning on ONE problem can achieve similar performance gain as RL on ONE p….