Loopholing Discrete Diffusion: Deterministic Bypass of the Sampling Wall Paper • 2510.19304 • Published Oct 22, 2025 • 24
Partition Generative Modeling: Masked Modeling Without Masks Paper • 2505.18883 • Published May 24, 2025
QLLM: Accurate and Efficient Low-Bitwidth Quantization for Large Language Models Paper • 2310.08041 • Published Oct 12, 2023 • 1
Lossy and Lossless (L$^2$) Post-training Model Size Compression Paper • 2308.04269 • Published Aug 8, 2023
From Markov to Laplace: How Mamba In-Context Learns Markov Chains Paper • 2502.10178 • Published Feb 14, 2025
Building on Efficient Foundations: Effectively Training LLMs with Structured Feedforward Layers Paper • 2406.16450 • Published Jun 24, 2024
Beyond Autoregression: Fast LLMs via Self-Distillation Through Time Paper • 2410.21035 • Published Oct 28, 2024
Unpacking SDXL Turbo: Interpreting Text-to-Image Models with Sparse Autoencoders Paper • 2410.22366 • Published Oct 28, 2024 • 84
Going beyond Compositions, DDPMs Can Produce Zero-Shot Interpolations Paper • 2405.19201 • Published May 29, 2024
Maximum Independent Set: Self-Training through Dynamic Programming Paper • 2310.18672 • Published Oct 28, 2023 • 1