Yixuan Ding

This paper proposes SV-GCN, a single-stream multi-feature fusion framework with temporal invariance, and introduces intra-frame relative motion features to eliminate frame-rate sensitivity and embed heterogeneous cues at shallow layers, enabling early fusion without multi-stream complexity.

LayerRecall boosts long-range video generation consistency by intelligently routing historical context to specific model layers, outperforming traditional methods without sacrificing local detail.

LLMs struggle with statistical analysis, achieving only 68.6% accuracy on a new benchmark designed to rigorously test their capabilities.

Advanced image editing models may look good but often miss the mark on logical consistency, revealing a critical gap in current AI capabilities.