5 papers
-MemEvo: Adaptive Cross-Task Memory Transfer for LLM Program Evolution
Aofan Liu, Shiyuan Song, Yiyan Qi
LLM-based program evolution systems such as FunSearch and AlphaEvolve have shown strong ability to discover novel algorithms, but typically optimize each task in isolation, discard…
Dual-Pathway Circuits of Object Hallucination in Vision-Language Models
Jiaxin Liu, Ding Zhong, Yue Wang +6
Vision-language models (VLMs) have demonstrated remarkable capabilities in bridging visual perception and natural language understanding, enabling a wide range of multimodal reason…
Paraphrase-Induced Output-Mode Collapse: When LLMs Break Character Under Semantically Equivalent Inputs
Aofan Liu, Jingxiang Meng
When the substantive content of a request is rewritten, do large language models still answer in the format the original task asked for? We find that they often do not, even at tem…
SupCLAP: Controlling Optimization Trajectory Drift in Audio-Text Contrastive Learning with Support Vector Regularization
Jiehui Luo, Yuguo Yin, Yuxin Xie +6
Contrastive language-audio pretraining, which aims to unify multimodal representations in a shared embedding space, serves as a cornerstone for building a wide range of application…
Quantization Meets Reasoning: Exploring and Mitigating Degradation of Low-Bit LLMs in Mathematical Reasoning
Zhen Li, Yupeng Su, Songmiao Wang +8
Low-bit post-training quantization (PTQ) is a practical route to deploy reasoning-capable LLMs under tight memory and latency budgets, yet it can markedly impair mathematical reaso…