10 papers
EvoCodeBench: A Human-Performance Benchmark for Self-Evolving LLM-Driven Coding Systems
Wentao Zhang, Jianfeng Wang, Liheng Liang +3
As large language models (LLMs) continue to advance in programming tasks, LLM-driven coding systems have evolved from one-shot code generation into complex systems capable of itera…
PlaM: Training-Free Plateau-Guided Model Merging for Better Visual Grounding in MLLMs
Zijing Wang, Yongkang Liu, Mingyang Wang +8
Multimodal Large Language Models (MLLMs) rely on strong linguistic reasoning inherited from their base language models. However, multimodal instruction fine-tuning paradoxically de…
CARPE: Context-Aware Image Representation Prioritization via Ensemble for Large Vision-Language Models
Donghee Lee, Rui Cai, Zhe Zhao
Large vision-language models (LVLMs) are typically trained using autoregressive language modeling objectives, which align visual representations with linguistic space. While effect…
Path to Intelligence: Measuring Similarity between Human Brain and Large Language Model Beyond Language Task
Doai Ngo, Mingxuan Sun, Zhengji Zhang +3
Large language models (LLMs) have demonstrated human-like abilities in language-based tasks. While language is a defining feature of human intelligence, it emerges from more fundam…
VITA: Vision-to-Action Flow Matching Policy
Dechen Gao, Boqi Zhao, Andrew Lee +6
Conventional flow matching and diffusion-based policies sample via iterative denoising from standard noise distributions (e.g., Gaussian), and require conditioning modules to repea…
REACT: Representation Extraction And Controllable Tuning to Overcome Overfitting in LLM Knowledge Editing
Haitian Zhong, Yuhuan Liu, Ziyang Xu +6
Large language model editing methods frequently suffer from overfitting, wherein factual updates can propagate beyond their intended scope, overemphasizing the edited target even w…