OctoT2I uses a no-supervision PSEL loop to discover model capability frontiers and route T2I tasks, reaching 0.96 GenEval score with 90.3% speedup over Flow-GRPO.
Mahoney, Kurt Keutzer, and Amir Gholami
9 Pith papers cite this work. Polarity classification is still indexing.
9
Pith papers citing it
citation-role summary
background 1
baseline 1
citation-polarity summary
representative citing papers
SkCC introduces a typed intermediate representation and compiler pipeline to make LLM agent skills portable across frameworks and enforce security constraints before deployment.
RAH improves coding performance on Oolong-Synthetic from 71.75% to 81.36% with fixed GPT-5 backbone by spawning subagent harnesses via executable scripts.
SCALE is a DRL scheduler using cross-attention and SRR regularization that generalizes from 16 to 48 nodes without retraining and reduces response time by 8.9% at N=48 versus the unregularized version.
Slipstream uses asynchronous compaction with trajectory-grounded judge validation to improve long-horizon agent accuracy by up to 8.8 percentage points and reduce latency by up to 39.7%.
PlanCompiler uses a typed node registry, static validation, and deterministic compilation to reach 278/300 successes on structured LLM pipeline benchmarks, outperforming GPT-4.1 and Claude Sonnet baselines at lower cost.
Tree Training serializes tree trajectories via DFS and uses redundancy-free partitioning to compute weighted per-token losses exactly once per token, achieving up to 6.2x training speedup on dense and MoE models.
SGLang is a new system that speeds up structured LLM programs by up to 6.4x using RadixAttention for KV cache reuse and compressed finite state machines for output decoding.
Plan-and-Act trains a dedicated Planner on synthetic plan-annotated trajectories to generate high-level plans that an Executor follows, reaching 57.58% success on WebArena-Lite and 81.36% on WebVoyager.
citing papers explorer
-
SGLang: Efficient Execution of Structured Language Model Programs
SGLang is a new system that speeds up structured LLM programs by up to 6.4x using RadixAttention for KV cache reuse and compressed finite state machines for output decoding.