A motion-only embedding trained on synthetic point tracks matches or beats large appearance-based video models on temporal tasks and improves them when combined.
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
PUMA detects reasoning-level semantic redundancy to enable early exit in chains of thought, achieving 26.2% average token reduction across five LRMs and five benchmarks while preserving accuracy and CoT quality.
SAGE adds duality consistency as an auxiliary reward in GRPO training with a dynamic operation pool to improve spatial reasoning robustness and generalization in VLMs.
citing papers explorer
-
The TIME Machine: On The Power of Motion for Efficient Perception
A motion-only embedding trained on synthetic point tracks matches or beats large appearance-based video models on temporal tasks and improves them when combined.
-
Stop When Reasoning Converges: Semantic-Preserving Early Exit for Reasoning Models
PUMA detects reasoning-level semantic redundancy to enable early exit in chains of thought, achieving 26.2% average token reduction across five LRMs and five benchmarks while preserving accuracy and CoT quality.
-
Self-Evolving Spatial Reasoning in Vision Language Models via Geometric Logic Consistency
SAGE adds duality consistency as an auxiliary reward in GRPO training with a dynamic operation pool to improve spatial reasoning robustness and generalization in VLMs.