#EfficientInference

🚀 Excited to share that our paper "Speculative Decoding with a Speculative Vocabulary" has been accepted at ACL 2026 Findings! Congrats Miles, @ruiruiliii, @kouris_a, and @SIVenieris! Paper: #ACL2026 #SpeculativeDecoding #EfficientInference #LLM

Decentralized KYC is possible with AI running on blockchain, ensuring video-person match with documents. AI on phones for inference is efficient. #DecentralizedKYC #AIonBlockchain #EfficientInference #ICP #InternetComputer #DFINITY #BlockchainRevolution #FutureTech #PowerfulAI

Our pick of the week by @mgaido91 : "FlexiSLM: A Dynamic and Controllable Frame Rate Spoken Language Model" by Jiaqi Li, Chaoren Wang, Xiaohai Tian, Mingjie Chen, Xinyu Liang, Xu Li, Yufan Lin, Junwen Qiu, Jun Zhang, Lu Lu, Haizhou Li and @drwuz #SLM #EfficientInference

Cool to see a work that adaptively chooses at inference how much to compress the input speech sequence, to control inference costs and quality based on the input, without enforcing a global trade-off to each segment: @fbk_mt

Lowkey goated when #EfficientInference is the vibe! Check out FP8 vs INT8 for inference by @Labardan_, @mnagel87 & more. 🤓🤩

#scalablefoundationmodel #efficientinference #efficientfinetuning #SSMs #MoE #selfattention #SCOPEICLR2025 #ICLRworkshop ⏰⏰To honor the overwhelming requests and interests in submission, the deadline of SCOPE-ICLR workshop 2025 submission is finalized to Feb 09, 2025 AoE. This is the final submission deadline. 🚀As per the guidelines of ICLR 2025, we do have a short/tiny paper submission track, with a page limit of up to 2-page+ref. Please consider submitting your late breaking and preliminary promising findings here. 📌📌We have a packed schedule at the venue: Room Peridot 204 - 205, Singapore Expo, 📅Save the date: April 28 2025! 📌Link: @ayazdanb @BeidiChen @eiclab @TianlongChen4 @Shiwei_Liu66 @haizhong_zheng @thisissouvikk