11 citations · 13 across the 17 of their papers we have counts for
17 papers
SMCEvolve: Principled Scientific Discovery via Sequential Monte Carlo Evolution
Jiachen Jiang, Huminhao Zhu, Zhihui Zhu
LLM-driven program evolution has emerged as a powerful tool for automated scientific discovery, yet existing frameworks offer no principled guide for designing their individual com…
LLMs Struggle with Abstract Meaning Comprehension More Than Expected
Hamoud Alhazmi, Jiachen Jiang
Understanding abstract meanings is crucial for advanced language comprehension. Despite extensive research, abstract words remain challenging due to their non-concrete, high-level…
Learning to Adapt: In-Context Learning Beyond Stationarity
Zhen Qin, Jiachen Jiang, Zhihui Zhu
Transformer models have become foundational across a wide range of scientific and engineering domains due to their strong empirical performance. A key capability underlying their s…
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…
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…
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…
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…
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…
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…
Analyzing Fine-Grained Alignment and Enhancing Vision Understanding in Multimodal Language Models
Jiachen Jiang, Jinxin Zhou, Bo Peng +2
Achieving better alignment between vision embeddings and Large Language Models (LLMs) is crucial for enhancing the abilities of Multimodal LLMs (MLLMs), particularly for recent mod…
From Compression to Expression: A Layerwise Analysis of In-Context Learning
Jiachen Jiang, Yuxin Dong, Jinxin Zhou +1
In-context learning (ICL) enables large language models (LLMs) to adapt to new tasks without weight updates by learning from demonstration sequences. While ICL shows strong empiric…
Learning Where and What to Restore for Composite Image Restoration
Jiachen Jiang, Tianyu Ding, Ke Zhang +5
Real-world degraded images often contain multiple co-occurring degradation types, making composite image restoration fundamentally different from the single-degradation setting ass…
Analysis of the Causes of Car Accidents in the United States of America in 2023: Gauge People Understanding of Data Visualisation
Hamoud Alhazmi, Marcelo Morales, Jiachen Jiang +2
This paper presents a comprehensive examination of interactive data visualization tools and their efficacy in the context of United States car accident data for the year 2023. We d…
Tracing Representation Progression: Analyzing and Enhancing Layer-Wise Similarity
Jiachen Jiang, Jinxin Zhou, Zhihui Zhu
Analyzing the similarity of internal representations has been an important technique for understanding the behavior of deep neural networks. Most existing methods for analyzing the…
The Efficiency Spectrum of Large Language Models: An Algorithmic Survey
Tianyu Ding, Tianyi Chen, Haidong Zhu +7
The rapid growth of Large Language Models (LLMs) has been a driving force in transforming various domains, reshaping the artificial general intelligence landscape. However, the inc…
DREAM: Diffusion Rectification and Estimation-Adaptive Models
Jinxin Zhou, Tianyu Ding, Tianyi Chen +4
We present DREAM, a novel training framework representing Diffusion Rectification and Estimation Adaptive Models, requiring minimal code changes (just three lines) yet significantl…
Generalized Neural Collapse for a Large Number of Classes
Jiachen Jiang, Jinxin Zhou, Peng Wang +4
Neural collapse provides an elegant mathematical characterization of learned last layer representations (a.k.a. features) and classifier weights in deep classification models. Such…