Weighted InfoNCE objectives realize specific target geometries in embedding space, with SupCon producing size-dependent inter-class similarities under imbalance while Soft SupCon and certain continuous variants preserve regular simplex or unique optima.
Advances in neural information processing systems , volume=
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
years
2026 6verdicts
UNVERDICTED 6representative citing papers
MemCoE learns memory organization guidelines via contrastive feedback and then trains a guideline-aligned RL policy for memory updates, yielding consistent gains on personalization benchmarks.
HAGE proposes a trainable weighted graph memory framework with LLM intent classification, dynamic edge modulation, and RL optimization that improves long-horizon reasoning accuracy in agentic LLMs over static baselines.
LLMs show mixed results on authorship verification, post generation, and attribute inference from Twitter data, with new frameworks and user studies establishing benchmarks for these analytics tasks.
LLMs prompted with few-shot examples and rationales generate better reasoned distractors for MCQs than fine-tuned contrastive models across six benchmarks.
RADAR generates query-adaptive multi-agent communication structures via conditional discrete graph diffusion guided by effective graph size, outperforming baselines on accuracy and token consumption across six benchmarks.
citing papers explorer
No citing papers match the current filters.