arXiv AI
Early-Bird Decoding: Accelerating Diffusion LLMs with Learnable Block Sizes and Parallel Sampling
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv Computation and Language
Sep 21
Ripple-Pivot Search: Active Parallel Decoding for Diffusion Large Language Models
Ripple-Pivot Search (RPS) is a training‑free decoding method for Diffusion Large Language Models that identifies mid‑entropy pivot positions to reduce uncertainty across remaining masked tokens. By proactively committing these pivots and evaluating token assignments via lookahead, RPS enables more tokens to be unmasked in parallel, speeding up decoding. Experiments on three dLLMs and four reasoning/code‑generation benchmarks show 4–10× wall‑clock speedup over standard decoding, up to 18× with KV caching, while maintaining or improving generation quality.
arXiv AI
Aug 25
CAI-DLLM: Convergence Aware Inference for Diffusion Language Models
arXiv:2608.22646v1 Announce Type: new Abstract: Diffusion language models can generate many tokens in parallel, but they still require repeated denoising steps during inference. This makes generation...
arXiv AI
Jul 17
Polestar: Drift-Aware Cache Calibration and Token Commitment for Efficient Inference of Diffusion LLMs
arXiv:2607. 14107v1 Announce Type: cross Abstract: The inference efficiency of diffusion large language models (dLLMs) is constrained by two challenges: bidirectional attention precludes efficient KV-cache reuse, while increasing decoding parallelism with static confidence thresholds can compromise generation quality.
Hugging Face Trending Papers
Aug 12
Ripple-Pivot Search: Active Parallel Decoding for Diffusion Large Language Models
Diffusion Large Language Models (dLLMs) have emerged as a competitive alternative to autoregressive language models, offering the potential for substantially faster inference through parallel decoding. Existing parallel decoding schedulers typically commit positions only after they meet a per-position criterion, overlooking how early commitments may benefit subsequent decoding.
arXiv AI
Jun 2
BlockBatch: Multi-Scale Consensus Decoding for Efficient Diffusion Language Model Inference
arXiv:2605. 29233v2 Announce Type: replace-cross Abstract: Diffusion language models (dLLMs) generate text by iteratively denoising multiple token positions in parallel, offering an attractive alternative to strictly autoregressive decoding.
arXiv AI
Jun 3
Fast-dLLM++: Fr\'{e}chet Profile Decoding for Faster Diffusion LLM Inference
arXiv:2606. 02955v1 Announce Type: cross Abstract: Diffusion large language models promise parallel token generation, yet inference remains bottlenecked by deciding which masked tokens can be safely committed together.