6 papers
More: Mode-Optimized Reasoning with Self-Adaptive Effort for Self-Evolving Agents
Dianxing Shi, Dingjie Fu, Tianyu Lei +1
Self-evolving training improves the performance of agents on difficult tasks through verifiable feedback, but it often applies costly deliberation uniformly across tasks. To addres…
VPRune: Efficient Training-free Pre-LLM Visual Token Pruning
Guangchuan Lv, Dianxing Shi, Dingjie Fu
Visual token pruning is a promising approach to reducing the inference cost of large vision-language models (LVLMs), yet aggressive token reduction often causes substantial perform…
Reconstructing Is Not Acting: Action-Centric Latent Dynamics Modeling
Dingjie Fu, Dianxing Shi, Yangyang Xu +1
Latent action models (LAMs) learn action representations from unlabeled videos by inferring latent actions from visual transitions and reconstructing future states. However, we ide…
ANCHOR: An External LLM-Driven Supervisory Module Facilitating Healthy Evolution in Self-Evolving Systems
Dianxing Shi, Bowen Wang, Junqi He +2
Self-evolving agents improve through continual self-play and self-generated learning signals, but their internally generated tasks and verifier signals provide limited coverage of…
Can Synthetic Images Serve as Effective and Efficient Class Prototypes?
Dianxing Shi, Dingjie Fu, Yuqiao Liu +1
Vision-Language Models (VLMs) have shown strong performance in zero-shot image classification tasks. However, existing methods, including Contrastive Language-Image Pre-training (C…
"You Are Rejected!": An Empirical Study of Large Language Models Taking Hiring Evaluations
Dingjie Fu, Dianxing Shi
With the proliferation of the internet and the rapid advancement of Artificial Intelligence, leading technology companies face an urgent annual demand for a considerable number of…