On-policy self-distillation
PulseAugur coverage of On-policy self-distillation — every cluster mentioning On-policy self-distillation across labs, papers, and developer communities, ranked by signal.
4 day(s) with sentiment data
-
Visual Contrastive Self-Distillation Improves Qwen VL Models
Researchers have developed Visual Contrastive Self-Distillation (VCSD), a novel method for improving Vision-Language Models (VLMs) without requiring external teachers or privileged information. VCSD works by comparing a…
-
New distillation method trains LLMs efficiently with soft prompts
Researchers have developed a new method called Multi-Task On-Policy Distillation via Soft-Prompt Privileged Context ("method") to train large language models. This technique uses a teacher model that differs from the st…
-
New research identifies decoding collapse in AI agent self-distillation
Researchers have identified a failure mode in feedback-augmented self-distillation for retrieval-interleaved search agents, termed decoding collapse. This occurs when models generate diverse-looking but input-agnostic r…
-
New H$^2$SD framework boosts LLM reasoning via hybrid self-distillation
Researchers have developed H$^2$SD, a novel hybrid hindsight self-distillation framework designed to enhance the reasoning abilities of large language models. This method addresses limitations in existing reinforcement …
-
New research tackles pathologies in On-Policy Distillation for LLMs
Researchers have identified and proposed solutions for two key pathologies in On-Policy Distillation (OPD), a technique used in large language model post-training. The first pathology, Student-Teacher Mismatch, occurs w…
-
New research challenges on-policy self-distillation for LLMs, proposing refined methods · 10 sources tracked
Recent research papers explore the limitations and potential improvements of on-policy self-distillation (OPSD) for training large language models (LLMs). Studies indicate that standard OPSD can lead to rote memorizatio…
-
New methods enhance VLM accuracy for GUI grounding tasks · 2 papers
Two new research papers introduce novel methods for improving the accuracy and reliability of vision-language models (VLMs) in GUI grounding tasks. The first paper, "Trust the Right Teacher," proposes quality-aware self…
-
New Trajectory-Refined Distillation improves LLM training
Researchers have introduced Trajectory-Refined Distillation (TRD), a new method to improve the post-training process for large language models. TRD addresses a problem called "prefix failure" in on-policy distillation, …
-
New distillation method enhances AI safety without sacrificing reasoning
Researchers have developed a new method called Constitutional On-Policy Safe Distillation (COPSD) to improve the safety and helpfulness of AI models. Existing on-policy self-distillation techniques can lead to a collaps…