RSPO interprets reward advantages as targets for relative log-ratios in dLLMs, calibrating noisy estimates to stabilize RLVR training and achieve strong gains on planning tasks with competitive math reasoning performance.
Title resolution pending
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
citation-role summary
method 1
citation-polarity summary
years
2026 6roles
method 1polarities
use method 1representative citing papers
HINT-SD improves long-horizon LLM agent training by using hindsight to target self-distillation on failure-relevant action spans, delivering up to 18.8% higher performance and 2.26x lower time per step than dense per-turn feedback.
A co-evolutionary VLM-VGM loop on 500 unlabeled images raises planner success by 30 points and simulator success by 48 percent while beating fully supervised baselines.
OGLS-SD improves on-policy self-distillation stability and math reasoning performance by constructing an outcome-discriminative steering direction from contrasts between successful and failed teacher logits.
Small LLMs under 2B parameters achieve better economic break-even, energy efficiency, and hardware density than larger models on legacy GPUs for industrial tasks.
By restricting token mixing to rank-1 decayed matrices, the same model trains in parallel but generates recurrently with constant memory, yielding large throughput gains in compute-matched benchmarks.
citing papers explorer
-
Relative Score Policy Optimization for Diffusion Language Models
RSPO interprets reward advantages as targets for relative log-ratios in dLLMs, calibrating noisy estimates to stabilize RLVR training and achieve strong gains on planning tasks with competitive math reasoning performance.
-
HINT-SD: Targeted Hindsight Self-Distillation for Long-Horizon Agents
HINT-SD improves long-horizon LLM agent training by using hindsight to target self-distillation on failure-relevant action spans, delivering up to 18.8% higher performance and 2.26x lower time per step than dense per-turn feedback.
-
RoboEvolve: Co-Evolving Planner-Simulator for Robotic Manipulation with Limited Data
A co-evolutionary VLM-VGM loop on 500 unlabeled images raises planner success by 30 points and simulator success by 48 percent while beating fully supervised baselines.
-
OGLS-SD: On-Policy Self-Distillation with Outcome-Guided Logit Steering for LLM Reasoning
OGLS-SD improves on-policy self-distillation stability and math reasoning performance by constructing an outcome-discriminative steering direction from contrasts between successful and failed teacher logits.
-
Are Large Language Models Economically Viable for Industry Deployment?
Small LLMs under 2B parameters achieve better economic break-even, energy efficiency, and hardware density than larger models on legacy GPUs for industrial tasks.
-
Structured Recurrent Mixers for Massively Parallelized Sequence Generation
By restricting token mixing to rank-1 decayed matrices, the same model trains in parallel but generates recurrently with constant memory, yielding large throughput gains in compute-matched benchmarks.