Fine-tuning LLMs on Navya-Nyaya's six-phase reasoning structure yields 100% semantic correctness on held-out logical problems despite only 40% strict format adherence.
Revisiting group rel- ative policy optimization: Insights into on-policy and off- policy training
7 Pith papers cite this work. Polarity classification is still indexing.
7
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
roles
background 1polarities
background 1representative citing papers
Intent Projection decomposes literal and pragmatic signals in multimodal memes via orthogonal projection and contrastive objectives in LVLMs, outperforming baselines on six benchmarks especially for high-divergence posts.
Smaller models provide temporally correlated policy-level diversity that serves as structured exploration for training larger models in GRPO, yielding accuracy gains such as +8.8% on AIME 24 with reduced compute via the S2L-PO framework.
A group-revision paradigm for GRPO-based RL fine-tuning of VLMs converts failure responses into improvement signals that refine rewards and advantages, yielding gains on referring segmentation, REC, and counting benchmarks.
GXPO approximates longer local lookahead in GRPO training via gradient extrapolation from two optimizer steps using three backward passes total, improving pass@1 accuracy by 1.65-5.00 points over GRPO and delivering up to 4x step speedup.
PubSwap uses a small public dataset for selective off-policy response swapping in federated RLVR to improve coordination and performance over standard baselines on math and medical reasoning tasks.
POPI distills user preferences into reusable natural-language summaries via a shared inference model and conditions a generator on them, trained jointly with RL to improve personalization quality while cutting context length by up to 10x on benchmarks.
citing papers explorer
-
Pramana: Fine-Tuning Large Language Models for Epistemic Reasoning through Navya-Nyaya
Fine-tuning LLMs on Navya-Nyaya's six-phase reasoning structure yields 100% semantic correctness on held-out logical problems despite only 40% strict format adherence.