5 citations · 5 across the 12 of their papers we have counts for
12 papers
When the Agent Becomes the Kernel: A Systematization of Security on the Path to AI-Native Operating Systems
Li Zhang, Yang Sun, Jie Shi
Large language model agents are now privileged principals that take consequential actions: editing code repositories, operating inboxes, completing purchases. Their authority is ke…
Long-Horizon Agent Trajectory Attribution: A Unified Benchmark and Fine-Grained Annotation Framework
Jing Chen, Yang Sun, Li Zhang +2
Large language model (LLM) agents increasingly operate through long-horizon trajectories involving user instructions, tool use, external observations, and memory. Existing benchmar…
Discern Truth from Falsehood: Reducing Over-Refusal via Contrastive Refinement
Yuxiao Lu, Lin Xu, Yang Sun +2
Large language models (LLMs) aligned for safety often suffer from over-refusal, the tendency to reject seemingly toxic or benign prompts by misclassifying them as toxic. This behav…
AInsteinBench: Benchmarking Coding Agents on Scientific Repositories
Titouan Duston, Shuo Xin, Yang Sun +26
We introduce AInsteinBench, a large-scale benchmark for evaluating whether large language model (LLM) agents can operate as scientific computing development agents within real rese…
Causal-Guided Detoxify Backdoor Attack of Open-Weight LoRA Models
Linzhi Chen, Yang Sun, Hongru Wei +1
Low-Rank Adaptation (LoRA) has emerged as an efficient method for fine-tuning large language models (LLMs) and is widely adopted within the open-source community. However, the dece…
Beyond Real Data: Synthetic Data through the Lens of Regularization
Amitis Shidani, Tyler Farghly, Yang Sun +2
Synthetic data can improve generalization when real data is scarce, but excessive reliance may introduce distributional mismatches that degrade performance. In this paper, we prese…
LFD: Layer Fused Decoding to Exploit External Knowledge in Retrieval-Augmented Generation
Yang Sun, Zhiyong Xie, Lixin Zou +7
Retrieval-augmented generation (RAG) incorporates external knowledge into large language models (LLMs), improving their adaptability to downstream tasks and enabling information up…
CodeContests+: High-Quality Test Case Generation for Competitive Programming
Zihan Wang, Siyao Liu, Yang Sun +2
Competitive programming, due to its high reasoning difficulty and precise correctness feedback, has become a key task for both training and evaluating the reasoning capabilities of…
Open set label noise learning with robust sample selection and margin-guided module
Yuandi Zhao, Qianxi Xia, Yang Sun +3
In recent years, the remarkable success of deep neural networks (DNNs) in computer vision is largely due to large-scale, high-quality labeled datasets. Training directly on real-wo…
Overview of AI-Debater 2023: The Challenges of Argument Generation Tasks
Jiayu Lin, Guanrong Chen, Bojun Jin +26
In this paper we present the results of the AI-Debater 2023 Challenge held by the Chinese Conference on Affect Computing (CCAC 2023), and introduce the related datasets. We organiz…
OVD-Explorer: Optimism Should Not Be the Sole Pursuit of Exploration in Noisy Environments
Jinyi Liu, Zhi Wang, Yan Zheng +6
In reinforcement learning, the optimism in the face of uncertainty (OFU) is a mainstream principle for directing exploration towards less explored areas, characterized by higher un…
FNAS: Uncertainty-Aware Fast Neural Architecture Search
Jihao Liu, Ming Zhang, Yangting Sun +4
Reinforcement learning (RL)-based neural architecture search (NAS) generally guarantees better convergence yet suffers from the requirement of huge computational resources compared…