A new benchmark (IG-Bench) reveals that LLM-based scientists fail at compositional lineage reasoning, with the best system reaching only 27.3% exact accuracy.
Learning transferable visual models from natural language supervision
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3representative citing papers
MAPO improves multimodal chain-of-thought reasoning by requiring explicit textual descriptions of visual tool results and using a novel advantage estimator that combines semantic alignment with task rewards.
TransConductor generates 3D conducting gestures from music via a Trans-Temporal Music Encoder and Gesture Decoder, outperforming baselines on retrieval-based alignment metrics with a new ConductorMotion dataset.
citing papers explorer
-
Ideas Have Genomes: Benchmarking Scientific Lineage Reasoning and Lineage-Grounded Idea Generation
A new benchmark (IG-Bench) reveals that LLM-based scientists fail at compositional lineage reasoning, with the best system reaching only 27.3% exact accuracy.
-
Walk the Talk: Bridging the Reasoning-Action Gap for Thinking with Images via Multimodal Agentic Policy Optimization
MAPO improves multimodal chain-of-thought reasoning by requiring explicit textual descriptions of visual tool results and using a novel advantage estimator that combines semantic alignment with task rewards.
-
MG-Former: A Transformer-Based Framework for Music-Driven 3D Conducting Gesture Generation
TransConductor generates 3D conducting gestures from music via a Trans-Temporal Music Encoder and Gesture Decoder, outperforming baselines on retrieval-based alignment metrics with a new ConductorMotion dataset.