most citedAnalyzing Fine-Grained Alignment and Enhancing Vision Understanding in Multimodal Language Models

1 citations · 2 across the 7 of their papers we have counts for

collaborators

9 papers

cs.AI2026

DeltaEvolve: Accelerating Scientific Discovery through Momentum-Driven Evolution

Jiachen Jiang, Tianyu Ding, Zhihui Zhu

LLM-driven evolutionary systems have shown promise for automated science discovery, yet existing approaches such as AlphaEvolve rely on full-code histories that are context-ineffic…

cs.CV2025

Improving Visual Discriminability of CLIP for Training-Free Open-Vocabulary Semantic Segmentation

Jinxin Zhou, Jiachen Jiang, Zhihui Zhu

Extending CLIP models to semantic segmentation remains challenging due to the misalignment between their image-level pre-training objectives and the pixel-level visual understandin…

cs.LG2025

In-Context Learning for Non-Stationary MIMO Equalization

Jiachen Jiang, Zhen Qin, Zhihui Zhu

Channel equalization is fundamental for mitigating distortions such as frequency-selective fading and inter-symbol interference. Unlike standard supervised learning approaches that…

cs.LG20251 cited

From Emergence to Control: Probing and Modulating Self-Reflection in Language Models

Xudong Zhu, Jiachen Jiang, Mohammad Mahdi Khalili +1

Self-reflection -- the ability of a large language model (LLM) to revisit, evaluate, and revise its own reasoning -- has recently emerged as a powerful behavior enabled by reinforc…

cs.LG2025

Understanding Task Vectors in In-Context Learning: Emergence, Functionality, and Limitations

Yuxin Dong, Jiachen Jiang, Zhihui Zhu +1

Task vectors offer a compelling mechanism for accelerating inference in in-context learning (ICL) by distilling task-specific information into a single, reusable representation. De…

cs.CV2025

ProCrop: Learning Aesthetic Image Cropping from Professional Compositions

Ke Zhang, Tianyu Ding, Jiachen Jiang +4

Image cropping is crucial for enhancing the visual appeal and narrative impact of photographs, yet existing rule-based and data-driven approaches often lack diversity or require an…