Poster "autoregressive inference" Papers
3 papers found
Conference
CLOVER: Cross-Layer Orthogonal Vectors Pruning and Fine-Tuning
Fanxu Meng, Muhan Zhang
ICLR 2025arXiv:2411.17426
3
citations
Distributed Speculative Inference (DSI): Speculation Parallelism for Provably Faster Lossless Language Model Inference
Nadav Timor, Jonathan Mamou, Daniel Korat et al.
ICLR 2025arXiv:2405.14105
7
citations
The Pitfalls of Next-Token Prediction
Gregor Bachmann, Vaishnavh Nagarajan
ICML 2024arXiv:2403.06963
139
citations