Publications (14)
Representations of loop groups as factorization module categories
Lin Chen, Yuchen Fu, Dennis Gaitsgory +1
We show that the (2-)category of categorical representations of the loop group embeds fully faithfully into the (2-)category of factorization module categories with respect to the…
XALPHA: A Memory-Driven AI Quant Researcher for Hypothesis-to-Code Alpha Discovery
Fengyuan Liu, Yuchen Fu, Yuqi Wang +1
XAlpha is a memory‑driven AI system that automates the full hypothesis‑to‑code loop for discovering trading alphas, integrating financial knowledge, generating factor code, and lea…
Factors Enabling Delocalized Charge-Carriers in Pnictogen-Based Solar Absorbers: In-depth Investigation into CuSbSe2
Yuchen Fu, Hugh Lohan, Marcello Righetto +14
Inorganic semiconductors based on heavy pnictogen cations (Sb3+ and Bi3+) have gained significant attention as potential nontoxic and stable alternatives to lead-halide perovskites…
Surface mobility of a glass-forming polymer in an ionic liquid
Xinyu Zhang, Christian Pedersen, Haoqi Zhu +6
The free surface of glassy polymers exhibits enhanced segmental dynamics compared to the bulk, forming a liquid-like layer that lowers the glass transition temperature (Tg) in nano…
An Extension of the Kazhdan-Lusztig Equivalence
Lin Chen, Yuchen Fu
We prove a tamely ramified version of the Kazhdan-Lusztig equivalence using factorization algebras. More precisely, we establish an equivalence between the DG category of Iwahori-i…
Token Prepending: A Training-Free Approach for Eliciting Better Sentence Embeddings from LLMs
Yuchen Fu, Zifeng Cheng, Zhiwei Jiang +4
Extracting sentence embeddings from large language models (LLMs) is a promising direction, as LLMs have demonstrated stronger semantic understanding capabilities. Previous studies…
Additive engineering for SbS indoor photovoltaics with efficiency exceeding 17%
Xiao Chen, Xiaoxuan Shu, Jiangcheng Zhou +11
Indoor photovoltaics (IPVs) have attracted increasing attention for sustainably powering Internet of Things (IoT) electronics. SbS is a promising IPV candidate material wit…
Probing Scientific General Intelligence of LLMs with Scientist-Aligned Workflows
Wanghan Xu, Yuhao Zhou, Yifan Zhou +104
Despite advances in scientific AI, a coherent framework for Scientific General Intelligence (SGI)-the ability to autonomously conceive, investigate, and reason across scientific do…
Chem3DLLM: 3D Multimodal Large Language Models for Chemistry
Lei Jiang, Shuzhou Sun, Biqing Qi +5
In the real world, a molecule is a 3D geometric structure. Compared to 1D SMILES sequences and 2D molecular graphs, 3D molecules represent the most informative molecular modality.…
The Conley-Zehnder Index of Brownian Paths on Sp(2, R)
Yuchen Fu
We investigate the probability distribution of Conley-Zehnder indices associated with Brownian random paths on Sp(2n, R) that start at the identity. In the case of n = 1, we prove…
Steering When Necessary: Flexible Steering Large Language Models with Backtracking
Zifeng Cheng, Jinwei Gan, Zhiwei Jiang +5
Large language models (LLMs) have achieved remarkable performance across many generation tasks. Nevertheless, effectively aligning them with desired behaviors remains a significant…
A Family of Finite-Dimensional Representations of Generalized Double Affine Hecke Algebras of Higher Rank
Yuchen Fu, Seth Shelley-Abrahamson
We give explicit constructions of some finite-dimensional representations of generalized double affine Hecke algebras (GDAHA) of higher rank using -matrices for $U_q(\mathfrak{s…
RegionMarker: A Region-Triggered Semantic Watermarking Framework for Embedding-as-a-Service Copyright Protection
Shufan Yang, Zifeng Cheng, Zhiwei Jiang +5
Embedding-as-a-Service (EaaS) is an effective and convenient deployment solution for addressing various NLP tasks. Nevertheless, recent research has shown that EaaS is vulnerable t…
Contrastive Prompting Enhances Sentence Embeddings in LLMs through Inference-Time Steering
Zifeng Cheng, Zhonghui Wang, Yuchen Fu +4
Extracting sentence embeddings from large language models (LLMs) is a practical direction, as it requires neither additional data nor fine-tuning. Previous studies usually focus on…