8 papers
Transformers Can Learn Posterior Predictive Distributions In-Context
Gyeonghun Kang, Changwoo J. Lee, Xiang Cheng
Prior-data fitted networks (PFNs) have recently emerged as a powerful approach for Bayesian prediction tasks, approximating the posterior predictive distribution (PPD) through in-c…
From Generic Correlation to Input-Specific Credit in On-Policy Self Distillation
Guobin Shen, Lei Huang, Xiang Cheng +4
On-policy self-distillation has emerged as a promising paradigm for post-training language models, in which the model conditions on environment feedback to serve as its own teacher…
Anti-Self-Distillation for Reasoning RL via Pointwise Mutual Information
Guobin Shen, Xiang Cheng, Chenxiao Zhao +4
On-policy self-distillation, where a student is pulled toward a copy of itself conditioned on privileged context (e.g., a verified solution or feedback), offers a promising directi…
One for All: A Non-Linear Transformer can Enable Cross-Domain Generalization for In-Context Reinforcement Learning
Bowen He, Juncheng Dong, Lin Lin +1
A central challenge in reinforcement learning (RL) is to learn models that generalize beyond the tasks on which they are trained, a goal traditionally pursued through multi-task an…
ChemVLR: Prioritizing Reasoning in Perception for Chemical Vision-Language Understanding
Xuanle Zhao, Xinyuan Cai, Xiang Cheng +2
While Vision-Language Models (VLMs) have demonstrated significant potential in chemical visual understanding, current models are predominantly optimized for direct visual question-…
Bootstrapping Exploration with Group-Level Natural Language Feedback in Reinforcement Learning
Lei Huang, Xiang Cheng, Chenxiao Zhao +6
Large language models (LLMs) typically receive diverse natural language (NL) feedback through interaction with the environment. However, current reinforcement learning (RL) algorit…