11 papers
Uni-LaDiR: Latent Diffusion Unifies Multimodal Reasoning
Haoqiang Kang, Yizhe Zhang, Nikki Lijing Kuang +3
Multimodal models increasingly think with different modalities such as images, 3D point clouds, and robot states, not just text. Yet each modality is still encoded into its own rep…
Reinforcement Learning without Ground-Truth Solutions can Improve LLMs
Yingyu Lin, Qiyue Gao, Nikki Lijing Kuang +6
Reinforcement learning with verifiable rewards (RLVR) for training LLMs typically rely on ground-truth answers to assign rewards, limiting their applicability to tasks where the gr…
Residual Skill Optimization for Text-to-SQL Ensembles
Jiongli Zhu, Haoquan Guan, Parjanya Prajakta Prashant +8
Text-to-SQL ensembles improve over single-candidate generation by drawing multiple SQL candidates and selecting one, but their effectiveness is bounded by Pass@K, the probability t…
LaDi-RL: Latent Diffusion Reasoning Prevents Entropy Collapse in Reinforcement Learning
Haoqiang Kang, Yizhe Zhang, Nikki Lijing Kuang +2
Reinforcement learning has become a central paradigm for improving LLM reasoning, but most existing methods optimize policies over discrete token sequences. This creates a mismatch…
LaDiR: Latent Diffusion Enhances LLMs for Text Reasoning
Haoqiang Kang, Yizhe Zhang, Nikki Lijing Kuang +4
Large Language Models (LLMs) demonstrate their reasoning ability through chain-of-thought (CoT) generation. However, LLM's autoregressive decoding may limit the ability to revisit…
Almost Linear Convergence under Minimal Score Assumptions: Quantized Transition Diffusion
Xunpeng Huang, Yingyu Lin, Nikki Lijing Kuang +4
Continuous diffusion models have demonstrated remarkable performance in data generation across various domains, yet their efficiency remains constrained by two critical limitations…
Log-concave Sampling from a Convex Body with a Barrier: a Robust and Unified Dikin Walk
Yuzhou Gu, Nikki Lijing Kuang, Yi-An Ma +2
We consider the problem of sampling from a -dimensional log-concave distribution for -Lipschitz , constrained to a convex body with an efficient…
Diffusion-BBO: Diffusion-Based Inverse Modeling for Online Black-Box Optimization
Dongxia Wu, Nikki Lijing Kuang, Ruijia Niu +2
Online black-box optimization (BBO) aims to optimize an objective function by iteratively querying a black-box oracle in a sample-efficient way. While prior studies focus on forwar…
Posterior Sampling with Delayed Feedback for Reinforcement Learning with Linear Function Approximation
Nikki Lijing Kuang, Ming Yin, Mengdi Wang +2
Recent studies in reinforcement learning (RL) have made significant progress by leveraging function approximation to alleviate the sample complexity hurdle for better performance.…
Langevin Thompson Sampling with Logarithmic Communication: Bandits and Reinforcement Learning
Amin Karbasi, Nikki Lijing Kuang, Yi-An Ma +1
Thompson sampling (TS) is widely used in sequential decision making due to its ease of use and appealing empirical performance. However, many existing analytical and empirical resu…
Statistical and Computational Trade-offs in Variational Inference: A Case Study in Inferential Model Selection
Kush Bhatia, Nikki Lijing Kuang, Yi-An Ma +1
Variational inference has recently emerged as a popular alternative to the classical Markov chain Monte Carlo (MCMC) in large-scale Bayesian inference. The core idea is to trade st…