6 papers
Reward-Free Evolving Agents via Pairwise Validator
Minghao Liu, Yu Wang, Jiayun Wang +1
A self-evolving agentic loop repeatedly proposes a tweaked version of an agent (its prompt template or program) and accepts or rejects the change based on a per-iteration quality s…
JetViT: Efficient High-Resolution Vision Transformer with Post-Training Attention Search
Dongyun Zou, Zhuoyang Zhang, Junyu Chen +8
We introduce JetViT, a novel family of hybrid-architecture Vision Transformer (ViT) models that match the accuracy of state-of-the-art full-attention vision foundation models while…
Inference Time Optimization with Confidence Dynamics
Yu Wang, Minghao Liu, Jiayun Wang +3
Inference time optimization techniques, such as repeated sampling, have significantly advanced the reasoning capabilities of Large Language Models (LLMs). However, the critical rol…
UniVL: Unified Vision-Language Embedding for Spatially Grounded Contextual Image Generation
Jiayun Wang, Yu Wang, Weijie Gan +2
We introduce spatially grounded contextual image generation, a controllable image generation task that reframes the conditioning paradigm. Instead of supplying a reference image an…
DiP-GO: A Diffusion Pruner via Few-step Gradient Optimization
Haowei Zhu, Dehua Tang, Ji Liu +12
Diffusion models have achieved remarkable progress in the field of image generation due to their outstanding capabilities. However, these models require substantial computing resou…
UPDP: A Unified Progressive Depth Pruner for CNN and Vision Transformer
Ji Liu, Dehua Tang, Yuanxian Huang +9
Traditional channel-wise pruning methods by reducing network channels struggle to effectively prune efficient CNN models with depth-wise convolutional layers and certain efficient…