1 citations · 1 across the 19 of their papers we have counts for
20 papers
Progress-Aware Distillation for Mitigating Stagnation in Small Language Model Agents
Yuanpu Cao, Saket Sathe, Hanyu Wang +3
While LLM-based agent systems have demonstrated remarkable proficiency in reasoning and solving complex real-world tasks, they also come with substantial token consumption and infe…
From Narrative to Auditable Forecasts: A Structured Scaffold for Agentic Forecasting
Yuanpu Cao, Yongkang Du, Yurui Chang +2
LLM agents are increasingly used for live forecasting, where they retrieve up-to-date information and produce estimates for unresolved future events. However, current agentic forec…
Can Factual Opinions Be Edited (Manipulated) in Large Language Models?
Yuanpu Cao, Ziyi Yin, Fenglong Ma +1
Large Language Models (LLMs) are increasingly integrated into various domains, making knowledge editing techniques crucial yet potentially hazardous. Current editing methods primar…
Looped Transformers with Layer Normalization Provably Learn the Power Method
Lyumin Wu, Chenyang Zhang, Yuan Cao
Transformers have achieved remarkable success across a wide range of applications, and a growing body of work suggests that part of their strength comes from their ability to learn…
ForecastCompass: Guiding Agentic Forecasting with Adaptive Factor Memory
Yurui Chang, Yongkang Du, Yuanpu Cao +2
Agentic forecasting is important for decision-making in dynamic environments, but it remains challenging because agents must reason from incomplete, time-limited evidence and produ…
Restoring the Sweet Spot: Pass-Rate Weighted Self-Distillation for LLM Reasoning
Zehao Liu, Yuanpu Cao, Jinghui Chen +1
Self-Distillation Policy Optimization (SDPO) provides dense token-level credit assignment for reinforcement learning with large language models by leveraging the model's own feedba…
The Illusion of Reasoning: Exposing Evasive Data Contamination in LLMs via Zero-CoT Truncation
Yifan Lan, Yuanpu Cao, Hanyu Wang +2
Large language models (LLMs) have demonstrated impressive reasoning abilities across a wide range of tasks, but data contamination undermines the objective evaluation of these capa…
PreFlect: From Retrospective to Prospective Reflection in Large Language Model Agents
Hanyu Wang, Yuanpu Cao, Lu Lin +1
Advanced large language model agents typically adopt self-reflection for improving performance, where agents iteratively analyze past actions to correct errors. However, existing r…
ParaBlock: Communication-Computation Parallel Block Coordinate Federated Learning for Large Language Models
Yujia Wang, Yuanpu Cao, Jinghui Chen
Federated learning (FL) has been extensively studied as a privacy-preserving training paradigm. Recently, federated block coordinate descent scheme has become a popular option in t…
You Can't Steal Nothing: Mitigating Prompt Leakages in LLMs via System Vectors
Bochuan Cao, Changjiang Li, Yuanpu Cao +3
Large language models (LLMs) have been widely adopted across various applications, leveraging customized system prompts for diverse tasks. Facing potential system prompt leakage ri…
Phi: Preference Hijacking in Multi-modal Large Language Models at Inference Time
Yifan Lan, Yuanpu Cao, Weitong Zhang +2
Recently, Multimodal Large Language Models (MLLMs) have gained significant attention across various domains. However, their widespread adoption has also raised serious safety conce…
GuardDoor: Safeguarding Against Malicious Diffusion Editing via Protective Backdoors
Yaopei Zeng, Yuanpu Cao, Lu Lin
The growing accessibility of diffusion models has revolutionized image editing but also raised significant concerns about unauthorized modifications, such as misinformation and pla…
TruthFlow: Truthful LLM Generation via Representation Flow Correction
Hanyu Wang, Bochuan Cao, Yuanpu Cao +1
Large language models (LLMs) are known to struggle with consistently generating truthful responses. While various representation intervention techniques have been proposed, these m…
Towards Robust Multimodal Large Language Models Against Jailbreak Attacks
Ziyi Yin, Yuanpu Cao, Han Liu +3
While multimodal large language models (MLLMs) have achieved remarkable success in recent advancements, their susceptibility to jailbreak attacks has come to light. In such attacks…
AdvI2I: Adversarial Image Attack on Image-to-Image Diffusion models
Yaopei Zeng, Yuanpu Cao, Bochuan Cao +3
Recent advances in diffusion models have significantly enhanced the quality of image synthesis, yet they have also introduced serious safety concerns, particularly the generation o…
Adversarially Robust Industrial Anomaly Detection Through Diffusion Model
Yuanpu Cao, Lu Lin, Jinghui Chen
Deep learning-based industrial anomaly detection models have achieved remarkably high accuracy on commonly used benchmark datasets. However, the robustness of those models may not…
Personalized Steering of Large Language Models: Versatile Steering Vectors Through Bi-directional Preference Optimization
Yuanpu Cao, Tianrong Zhang, Bochuan Cao +4
Researchers have been studying approaches to steer the behavior of Large Language Models (LLMs) and build personalized LLMs tailored for various applications. While fine-tuning see…
WordGame: Efficient & Effective LLM Jailbreak via Simultaneous Obfuscation in Query and Response
Tianrong Zhang, Bochuan Cao, Yuanpu Cao +3
The recent breakthrough in large language models (LLMs) such as ChatGPT has revolutionized production processes at an unprecedented pace. Alongside this progress also comes mountin…
Federated Learning with Projected Trajectory Regularization
Tiejin Chen, Yuanpu Cao, Yujia Wang +2
Federated learning enables joint training of machine learning models from distributed clients without sharing their local data. One key challenge in federated learning is to handle…
Stealthy and Persistent Unalignment on Large Language Models via Backdoor Injections
Yuanpu Cao, Bochuan Cao, Jinghui Chen
Recent developments in Large Language Models (LLMs) have manifested significant advancements. To facilitate safeguards against malicious exploitation, a body of research has concen…