14 papers
Exact Risk Certificates for Pairwise-Judged Reranking
Xinyu Wang, Jingrui Tian, Sicheng Lyu +4
Pairwise relevance judgments constrain both the loss numerator and the ideal-ranking denominator of nDCG. We characterize the exact worst-case loss of replacing a ranking with a fi…
Measuring the Task Value of Precision Upgrades in Closed-Loop Agents
Sicheng Lyu, Xinyu Wang, Yu Gu +3
A low-precision agent can call its full-precision (BF16) model at selected decisions as a fallback. A learned precision router chooses where to call it from the disagreement betwee…
A Refresh Interval Does Not Fully Specify a Refresh Schedule: Learning-Rate-Dependent Placement in Kronecker-Preconditioned Language Model Training
Xinyu Wang, Zhiwei Zhai, Yu Gu +6
Kronecker-preconditioned optimizers recompute a cached curvature eigendecomposition only periodically, and implementations and adaptive methods control this through the refresh fre…
JARQ: Joint Alternating Refinement for Quantization
Xinyu Wang, Sicheng Lyu, Xiao-Wen Chang
Group-wise post-training quantizers for large language models round weights onto a grid that is not refit to the resulting integer codes. We show that this leaves accuracy on the t…
FINSKILLOPS: A Self-Evolving Multi-Agent System for SEC Filing QA
Yanzhang Ma, Zhenghan Tai, Hanwei Wu +25
Financial QA systems are typically improved before deployment through better retrieval, prompting, or agent coordination, leaving their reliability behavior fixed thereafter. In pr…
FinSAgent: Corpus-Aligned Multi-Agent RAG Framework for Evidence-Grounded SEC Filing Question Answering
Jijun Chi, Zhenghan Tai, Hanwei Wu +21
Financial question answering over U.S. Securities and Exchange Commission (SEC) filings requires retrieving and synthesizing heterogeneous evidence dispersed across long, standardi…
SafeRx-Agent: A Knowledge-Grounded Multi-Agent Framework for Safe and Explainable Medication Recommendation
Xinyu Wang, Hanwei Wu, Zhenghan Tai +7
Medication recommendation predicts medications for patient visits, but existing methods still face two key challenges. At the model level, traditional drug recommendation methods o…
HoloQ-VLA: Uniform W4A4 Quantization of Vision-Language-Action Models
Xinyu Wang, Mingze Li, Sicheng Lyu +6
Vision-Language-Action (VLA) models unify perception, reasoning, and control in a single policy, but their multi-billion-parameter backbones and diffusion-based action heads make o…
Beyond Hard Writes and Rigid Preservation: Soft Recursive Least-Squares for Lifelong LLM Editing
Xinyu Wang, Sicheng Lyu, Yu Gu +4
Model editing updates a pre-trained LLM with new facts or rules without retraining while preserving unrelated behavior. In real deployment, edits arrive as long streams, creating a…
: A Route-to-Rerank Post-Training Framework for Multi-Domain Decoder-Only Rerankers
Xinyu Wang, Hanwei Wu, Qingchen Hu +13
Decoder-only rerankers are central to Retrieval-Augmented Generation (RAG). However, generalist models miss domain-specific nuances in high-stakes fields like finance and law, and…
VeritasFi: An Adaptable, Multi-tiered RAG Framework for Multi-modal Financial Question Answering
Zhenghan Tai, Hanwei Wu, Qingchen Hu +24
Retrieval-Augmented Generation (RAG) is becoming increasingly essential for Question Answering (QA) in the financial sector, where accurate and contextually grounded insights from…
EvoEdit: Evolving Null-space Alignment for Robust and Efficient Knowledge Editing
Sicheng Lyu, Yu Gu, Xinyu Wang +5
Large language models (LLMs) require continual updates to rectify outdated or erroneous knowledge. Model editing has emerged as a compelling paradigm for introducing targeted modif…
RL Fine-Tuning Heals OOD Forgetting in SFT
Hangzhan Jin, Sitao Luan, Tianwei Ni +5
Supervised Fine-Tuning (SFT) followed by Reinforcement Learning (RL) is a standard post-training recipe for improving Large Language Models (LLM) reasoning, but why it works remain…
SNAP: Stopping Catastrophic Forgetting in Hebbian Learning with Sigmoidal Neuronal Adaptive Plasticity
Tianyi Xu, Patrick Zheng, Shiyan Liu +2
Artificial Neural Networks (ANNs) suffer from catastrophic forgetting, where the learning of new tasks causes the catastrophic forgetting of old tasks. Existing Machine Learning (M…