ProtoCycle improves text-guided protein design by coupling an LLM planner with tool feedback and reflection to achieve better language alignment and foldability than direct generation.
Advancing multimodal reasoning via reinforcement learning with cold start
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3representative citing papers
SCOLAR fixes information gain collapse in latent visual reasoning by generating independent auxiliary visual tokens via a detransformer, extending acceptable CoT length over 30x and delivering +14.12% gains on reasoning benchmarks.
citing papers explorer
-
ProtoCycle: Reflective Tool-Augmented Planning for Text-Guided Protein Design
ProtoCycle improves text-guided protein design by coupling an LLM planner with tool feedback and reflection to achieve better language alignment and foldability than direct generation.
-
Self-Consistent Latent Reasoning: Long Latent Sequence Reasoning for Vision-Language Model
SCOLAR fixes information gain collapse in latent visual reasoning by generating independent auxiliary visual tokens via a detransformer, extending acceptable CoT length over 30x and delivering +14.12% gains on reasoning benchmarks.
- Vision-OPD: Learning to See Fine Details for Multimodal LLMs via On-Policy Self-Distillation