Diagram-to-graph topology extraction aims to extract a graph of entities and their connections from a structural diagram. This task remains challenging for current vision-language models because it requires both fine-grained perceptual grounding and topology-aware reasoning with global consistency. We present TopoBench...
Bang-Wei Guo, Xujiang Zhao, Yan-Chi Liu et al.· 0 citations
Structural diagrams are widely used to represent complex systems and relational information across scientific, engineering, procedural, and spatial domains. Recent vision-language models (VLMs) have become increasingly capable of recognizing diagram elements and reasoning about their content, while complete diagram top...
Bang-Wei Guo, Xu-Jiang Zhao, Sheng-Yu Chen et al.· 0 citations
Multimodal large language models (MLLMs) have shown strong visual reasoning abilities, but knowledge-intensive visual question answering often requires external textual evidence beyond the image and the model's parametric knowledge. Existing multimodal RAG systems commonly rely on Top-$K$ retrieval or reranking, which...
Hang Gao, Wu-Jiang Xu, Zhixing Zhang et al.· 0 citations
Opera is presented, a verbal critic framework that treats each correction as a persistent note, followed until the diagnosed problem is resolved, and achieves the highest mean resolve rate among competitive critic baselines on all three benchmarks.
Kai Mei, Zhi-Yuan Hu, Yu-Tong Dai et al.· 0 citations
Conditional Progressive Pruning (CPP) is proposed, a lightweight pruning framework that fully exploits multi-round MAD and is the first to fully outperform consistency methods.
Ruo-Song Ye, Caiqi Zhang, Jia-Hao Li et al.· 0 citations
This study provides new mechanistic insights into how LLMs internalize OOD challenges, and designs Sparsity-Guided Curriculum In-Context Learning (SG-ICL), a strategy that explicitly uses representation sparsity to schedule few-shot demonstrations, leading to considerable performance enhancements.
SPACE induces two-level programmatic skills from successful trajectories, where subskill boundaries serve as direct chunk-boundary supervision from trajectory-induced programmatic skills, and distilled into a primitive-chunk policy via hybrid on-/off-policy optimization.
Yan-Ting Yang, Can Jin, Jin-Man Zhao et al.· 1 citation
This work presents OpenPM, an auditable point-in-time evaluation framework for LLM portfolio-management agents, and builds a reference agent named the tiered allocator, where typed analysts score candidates, a constructor LLM proposes weights, and a deterministic critic guarantees feasibility.
Xinying Cai, Ming-Hao Guo, Jiahe Liu et al.· 1 citation
Energy-Shaped Visual Prompting (ES-VP), a novel approach that generates image-specific prompts using low-rank initialization and energy-guided dynamic adaptation, achieving superior performance with fewer parameters compared to single-prompt methods, thereby establishing a new benchmark for efficient and generalizable...
Can Jin, Ying Li, Jingchen Sun et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
