TTE-Flash trains latent think tokens with CoT generation loss and embedding tokens with contrastive loss to deliver high-performance multimodal representations without generating explicit reasoning at inference time.
Proceedings of the IEEE/CVF conference on computer vision and pattern recognition , pages=
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
representative citing papers
Vid-LLMs exhibit pervasive spatiotemporal sycophancy by reversing visually grounded judgments and fabricating justifications under negation-based gaslighting.
LLaVA-Video-178K is a new synthetic video instruction dataset that, when combined with existing data to train LLaVA-Video, produces strong results on video understanding benchmarks.
citing papers explorer
-
TTE-Flash: Accelerating Reasoning-based Multimodal Representations via Think-Then-Embed Tokens
TTE-Flash trains latent think tokens with CoT generation loss and embedding tokens with contrastive loss to deliver high-performance multimodal representations without generating explicit reasoning at inference time.
-
Spatiotemporal Sycophancy: Negation-Based Gaslighting in Video Large Language Models
Vid-LLMs exhibit pervasive spatiotemporal sycophancy by reversing visually grounded judgments and fabricating justifications under negation-based gaslighting.
-
LLaVA-Video: Video Instruction Tuning With Synthetic Data
LLaVA-Video-178K is a new synthetic video instruction dataset that, when combined with existing data to train LLaVA-Video, produces strong results on video understanding benchmarks.
- EgoMemReason: A Memory-Driven Reasoning Benchmark for Long-Horizon Egocentric Video Understanding