21 papers
Training One Model to Master Cross-Level Agentic Actions via Reinforcement Learning
Kaichen He, Zihao Wang, Muyao Li +2
The paradigm of agentic AI is shifting from engineered complex workflows to post-training native models. However, existing agents are typically confined to static, predefined actio…
Breaking the Factorization Barrier in Diffusion Language Models
Ian Li, Zilei Shao, Benjie Wang +3
Diffusion language models theoretically allow for efficient parallel generation but are practically hindered by the ``factorization barrier'': the assumption that simultaneously pr…
Zero-Variance Gradients for Variational Autoencoders
Zilei Shao, Anji Liu, Guy Van den Broeck
Training deep generative models like Variational Autoencoders (VAEs) requires propagating gradients through stochastic latent variables, which introduces estimation variance that c…
Learning Tractable Distributions Of Language Model Continuations
Gwen Yidou-Weng, Ian Li, Anji Liu +4
Controlled generation imposes sequence-level constraints (syntax, style, safety) that depend on future tokens, making exact conditioning of an autoregressive LM intractable. Tracta…
Lookahead Path Likelihood Optimization for Diffusion LLMs
Xuejie Liu, Yap Vit Chun, Yitao Liang +1
Diffusion Large Language Models (dLLMs) support arbitrary-order generation, yet their inference performance critically depends on the unmasking order. Existing strategies rely on h…
Scaling Tractable Probabilistic Circuits: A Systems Perspective
Anji Liu, Kareem Ahmed, Guy Van den Broeck
Probabilistic Circuits (PCs) are a general framework for tractable deep generative models, which support exact and efficient probabilistic inference on their learned distributions.…