1 citations · 1 across the 7 of their papers we have counts for
9 papers
Cortex: Consolidating Context into Parametric Memory
Jintian Zhang, Feng He, Xinnian Liang +5
Context can improve large language model performance, but these gains may be lost after context removal. Inspired by biological systems consolidation, we formulate Memory Consolida…
Tail-Likelihood Reinforcement Learning
Shrinivas Ramasubramanian, Daman Arora, Fahim Tajwar +11
Reinforcement learning typically optimizes average reward. For generative policies, the average can hide an important distinction: two policies can achieve the same mean reward whi…
Expanding the Capabilities of Reinforcement Learning via Text Feedback
Yuda Song, Lili Chen, Fahim Tajwar +5
The success of RL for LLM post-training stems from an unreasonably uninformative source: a single bit of information per rollout as binary reward or preference label. At the other…
Maximum Likelihood Reinforcement Learning
Fahim Tajwar, Guanning Zeng, Yueer Zhou +7
Reinforcement learning (RL) is the method of choice for training models in setups where the objective function can only be evaluated by sampling from the model. Our key observation…
Towards Scalable Pre-training of Visual Tokenizers for Generation
Jingfeng Yao, Yuda Song, Yucong Zhou +1
The quality of the latent space in visual tokenizers (e.g., VAEs) is crucial for modern generative models. However, the standard reconstruction-based training paradigm produces a l…
Outcome-based Exploration for LLM Reasoning
Yuda Song, Julia Kempe, Remi Munos
Reinforcement learning (RL) has emerged as a powerful method for improving the reasoning abilities of large language models (LLMs). Outcome-based RL, which rewards policies solely…
Accelerating Unbiased LLM Evaluation via Synthetic Feedback
Zhaoyi Zhou, Yuda Song, Andrea Zanette
When developing new large language models (LLMs), a key step is evaluating their final performance, often by computing the win-rate against a reference model based on external feed…
Rich-Observation Reinforcement Learning with Continuous Latent Dynamics
Yuda Song, Lili Wu, Dylan J. Foster +1
Sample-efficiency and reliability remain major bottlenecks toward wide adoption of reinforcement learning algorithms in continuous settings with high-dimensional perceptual inputs.…
SDXS: Real-Time One-Step Latent Diffusion Models with Image Conditions
Yuda Song, Zehao Sun, Xuanwu Yin
Recent advancements in diffusion models have positioned them at the forefront of image generation. Despite their superior performance, diffusion models are not without drawbacks; t…