JetSpec

community

https://jetspec-project.github.io/jetspec-web/

AI & ML interests

JetSpec: Breaking the Scaling Ceiling of Speculative Decoding with Causal Parallel Tree Drafting

Recent Activity

Snyhlx authored a paper 3 days ago

JetSpec: Breaking the Scaling Ceiling of Speculative Decoding with Parallel Tree Drafting

Snyhlx authored a paper 3 days ago

d3LLM: Ultra-Fast Diffusion LLM using Pseudo-Trajectory Distillation

Snyhlx submitted a paper about 2 months ago

JetSpec: Breaking the Scaling Ceiling of Speculative Decoding with Parallel Tree Drafting

View all activity

authored 2 papers 3 days ago

JetSpec: Breaking the Scaling Ceiling of Speculative Decoding with Parallel Tree Drafting

Paper • 2606.18394 • Published Jun 25 • 35

d3LLM: Ultra-Fast Diffusion LLM using Pseudo-Trajectory Distillation

Paper • 2601.07568 • Published Jan 12 • 2

submitted a paper to Daily Papers about 2 months ago

JetSpec: Breaking the Scaling Ceiling of Speculative Decoding with Parallel Tree Drafting

Paper • 2606.18394 • Published Jun 25 • 35

updated 2 models 2 months ago

JetSpec/jetspec-Qwen3.6-35B-A3B

0.5B • Updated Jun 17 • 36 • 9

JetSpec/jetspec-gemma4-26B-A4B0-it

0.3B • Updated Jun 17 • 17 • 2

published a model 2 months ago

JetSpec/jetspec-Qwen3.6-35B-A3B

0.5B • Updated Jun 17 • 36 • 9

updated a model 2 months ago

JetSpec/jetspec-gpt-oss-20b

0.9B • Updated Jun 17 • 13 • 2

published 4 models 2 months ago

JetSpec/jetspec-gemma4-26B-A4B0-it

0.3B • Updated Jun 17 • 17 • 2

JetSpec/jetspec-gpt-oss-20b

0.9B • Updated Jun 17 • 13 • 2

JetSpec/jetspec-Step-3.7-Flash

0.9B • Updated Jun 15 • 12 • 3

JetSpec/jetspec-qwen3-30b-a3b

0.5B • Updated Jun 11 • 18

updated 2 models 2 months ago

JetSpec/jetspec-Step-3.7-Flash

0.9B • Updated Jun 15 • 12 • 3

JetSpec/jetspec-qwen3-30b-a3b

0.5B • Updated Jun 11 • 18

authored a paper 3 months ago

MetaAgent-X : Breaking the Ceiling of Automatic Multi-Agent Systems via End-to-End Reinforcement Learning

Paper • 2605.14212 • Published May 14 • 19

authored a paper 3 months ago

AMA-Bench: Evaluating Long-Horizon Memory for Agentic Applications

Paper • 2602.22769 • Published Feb 26 • 10

authored 2 papers 8 months ago

Benchmarking Scientific Understanding and Reasoning for Video Generation using VideoScience-Bench

Paper • 2512.02942 • Published Dec 2, 2025 • 5

Fast and Accurate Causal Parallel Decoding using Jacobi Forcing

Paper • 2512.14681 • Published Dec 16, 2025 • 44

submitted a paper to Daily Papers 8 months ago

Fast and Accurate Causal Parallel Decoding using Jacobi Forcing

Paper • 2512.14681 • Published Dec 16, 2025 • 44

authored a paper 10 months ago

Stronger Together: On-Policy Reinforcement Learning for Collaborative LLMs

Paper • 2510.11062 • Published Oct 13, 2025 • 29

authored a paper over 1 year ago

lmgame-Bench: How Good are LLMs at Playing Games?

Paper • 2505.15146 • Published May 21, 2025 • 20