3 papers
cs.CV2026
Beyond Binary Contrast: Modeling Continuous Skeleton Action Spaces with Transitional Anchors
Yingjie Feng, Yi Wang, Jiaze Wang +2
Self-supervised contrastive learning has emerged as a powerful paradigm for skeleton-based action recognition by enforcing consistency in the embedding space. However, existing met…
cs.AI2026
Evolutionary Negative Module Pruning for Better LoRA Merging
Anda Cao, Zhuo Gou, Yi Wang +5
Merging multiple Low-Rank Adaptation (LoRA) experts into a single backbone is a promising approach for efficient multi-task deployment. While existing methods strive to alleviate i…
cs.AI2026
LLaTiSA: Towards Difficulty-Stratified Time Series Reasoning from Visual Perception to Semantics
Yueyang Ding, HaoPeng Zhang, Rui Dai +4
Comprehensive understanding of time series remains a significant challenge for Large Language Models (LLMs). Current research is hindered by fragmented task definitions and benchma…