4 papers
Beyond the Capability Boundary: Zeroth-Order Optimization for Self-Evolving LLM Agents
Bingzhen Liu, Xiaomeng Fan, Yuwei Wu +4
Self-evolving methods improve the capabilities of LLM agents by sampling trajectories from the underlying LLMs and learning from these trajectories. However, these methods struggle…
A Causality-aware Infer-diagnose-refine Framework for Test-time Modality Adaptation in VLA Models
Haoyu Zhang, Yuwei Wu, Jin Chen +6
Vision-language-action (VLA) models predict sequential actions to execute tasks specified by language instructions, conditioned on visual observations and proprioceptive states. Ho…
Reliability-Prioritized Fine-Grained Generation in Multimodal Large
Xiaomeng Fan, Wei Wu, Yuwei Wu +9
Multimodal large language models (MLLMs) are increasingly expected to generate fine-grained descriptions of visual content. However, we observe and theoretically show that generati…
Bridging Modality Disconnect in Self-Reflection via Closed-Loop Visually Grounded Verification
Haoyu Zhang, Yuwei Wu, Pengxiang Li +6
In the era of Vision-Language Models (VLMs), enhancing multimodal reasoning capabilities remains a critical challenge, particularly in handling ambiguous or complex visual inputs,…