6 papers
GradCuit: Credit-Assigned Gradient Flow Enables Robust and Interpretable Test-Time Latent Reasoning
Zhaoxin Yu, Qi Shen, Hengli Li +4
Optimization-based latent reasoning improves large language model outputs by optimizing instance-specific continuous states at test time while keeping model parameters frozen. Exis…
Agent Q-Mix: Selecting the Right Action for LLM Multi-Agent Systems through Reinforcement Learning
Eric Hanchen Jiang, Levina Li, Rui Sun +9
Large Language Models (LLMs) have shown remarkable performance in completing various tasks. However, solving complex problems often requires the coordination of multiple agents, ra…
BEDA: Belief Estimation as Probabilistic Constraints for Performing Strategic Dialogue Acts
Hengli Li, Zhaoxin Yu, Qi Shen +8
Strategic dialogue requires agents to execute distinct dialogue acts, for which belief estimation is essential. While prior work often estimates beliefs accurately, it lacks a prin…
How to Synthesize Text Data without Model Collapse?
Xuekai Zhu, Daixuan Cheng, Hengli Li +7
Model collapse in synthetic data indicates that iterative training on self-generated data leads to a gradual decline in performance. With the proliferation of AI models, synthetic…
Discrete Markov Bridge
Hengli Li, Yuxuan Wang, Song-Chun Zhu +2
Discrete diffusion has recently emerged as a promising paradigm in discrete data modeling. However, existing methods typically rely on a fixed rate transition matrix during trainin…
Are the Values of LLMs Structurally Aligned with Humans? A Causal Perspective
Yipeng Kang, Junqi Wang, Yexin Li +8
As large language models (LLMs) become increasingly integrated into critical applications, aligning their behavior with human values presents significant challenges. Current method…