DeltaPrompts generates 200k synthetic high-divergence reasoning prompts to escape zero-delta saturation in multimodal distillation, yielding up to 15% relative gains on chart, document, and perception benchmarks across multiple settings.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.LG 2years
2026 2verdicts
UNVERDICTED 2roles
background 1polarities
background 1representative citing papers
GLM-5 is a foundation model that claims state-of-the-art results on coding benchmarks and superior performance on end-to-end software engineering tasks via new asynchronous RL methods and cost-saving DSA.
citing papers explorer
-
DeltaPrompts: Escaping the Zero-Delta Trap in Multimodal Distillation
DeltaPrompts generates 200k synthetic high-divergence reasoning prompts to escape zero-delta saturation in multimodal distillation, yielding up to 15% relative gains on chart, document, and perception benchmarks across multiple settings.
-
GLM-5: from Vibe Coding to Agentic Engineering
GLM-5 is a foundation model that claims state-of-the-art results on coding benchmarks and superior performance on end-to-end software engineering tasks via new asynchronous RL methods and cost-saving DSA.