2 citations · 4 across the 13 of their papers we have counts for
13 papers
Code as Agent Harness
Xuying Ning, Katherine Tieu, Dongqi Fu +39
Recent large language models (LLMs) have demonstrated strong capabilities in understanding and generating code, from competitive programming to repository-level software engineerin…
RubricEM: Meta-RL with Rubric-guided Policy Decomposition beyond Verifiable Rewards
Gaotang Li, Bhavana Dalvi Mishra, Zifeng Wang +9
Deep research agents plan, search, evaluate evidence, and synthesize long-form reports. Training these agents with reinforcement learning (RL) is challenging because they operate o…
Graph homophily booster: Reimagining the role of discrete features in heterophilic graph learning
Ruizhong Qiu, Ting-Wei Li, Gaotang Li +1
Graph neural networks (GNNs) have emerged as a powerful tool for modeling graph-structured data. However, existing GNNs often struggle with heterophilic graphs, where connected nod…
Do VLMs Have a Moral Backbone? A Study on the Fragile Morality of Vision-Language Models
Zhining Liu, Tianyi Wang, Xiao Lin +9
Despite substantial efforts toward improving the moral alignment of Vision-Language Models (VLMs), it remains unclear whether their ethical judgments are stable in realistic settin…
A Survey of Agentic Reasoning for Large Language Models: Towards Recursively Self-Improving and Collective Agents
Tianxin Wei, Ting-Wei Li, Zhining Liu +26
Reasoning is a fundamental cognitive process underlying inference, problem-solving, and decision-making. While large language models (LLMs) demonstrate strong reasoning capabilitie…
ALERT: Zero-shot LLM Jailbreak Detection via Internal Discrepancy Amplification
Xiao Lin, Philip Li, Zhichen Zeng +6
Despite rich safety alignment strategies, large language models (LLMs) remain highly susceptible to jailbreak attacks, which compromise safety guardrails and pose serious security…
Latent Collaboration in Multi-Agent Systems
Jiaru Zou, Ruizhong Qiu, Gaotang Li +10
Multi-agent systems (MAS) extend large language models (LLMs) from independent single-model reasoning to coordinative system-level intelligence. While existing LLM agents depend on…
Beyond Log Likelihood: Probability-Based Objectives for Supervised Fine-Tuning across the Model Capability Continuum
Gaotang Li, Ruizhong Qiu, Xiusi Chen +2
Supervised fine-tuning (SFT) is the standard approach for post-training large language models (LLMs), yet it often shows limited generalization. We trace this limitation to its def…
Graph Homophily Booster: Rethinking the Role of Discrete Features on Heterophilic Graphs
Ruizhong Qiu, Ting-Wei Li, Gaotang Li +1
Graph neural networks (GNNs) have emerged as a powerful tool for modeling graph-structured data. However, existing GNNs often struggle with heterophilic graphs, where connected nod…
Saffron-1: Safety Inference Scaling
Ruizhong Qiu, Gaotang Li, Tianxin Wei +2
Existing safety assurance research has primarily focused on training-phase alignment to instill safe behaviors into LLMs. However, recent studies have exposed these methods' suscep…
MORALISE: A Structured Benchmark for Moral Alignment in Visual Language Models
Xiao Lin, Zhining Liu, Ze Yang +10
Warning: This paper contains examples of harmful language and images. Reader discretion is advised. Recently, vision-language models have demonstrated increasing influence in moral…
RM-R1: Reward Modeling as Reasoning
Xiusi Chen, Gaotang Li, Ziqi Wang +9
Reward modeling is essential for aligning large language models with human preferences through reinforcement learning. To provide accurate reward signals, a reward model (RM) shoul…
Taming Knowledge Conflicts in Language Models
Gaotang Li, Yuzhong Chen, Hanghang Tong
Language Models (LMs) often encounter knowledge conflicts when parametric memory contradicts contextual knowledge. Previous works attribute this conflict to the interplay between "…