4 citations · 5 across the 17 of their papers we have counts for
10 papers · 1 filter
RRPO: Reference-Relative Policy Optimization with Stratified Conditional Rollouts
Yuxin Xiong, Xunyi Jiang, Rohan Surana +8
Group Relative Policy Optimization (GRPO) has shown strong effectiveness in reinforcement learning from verifiable feedback, where sampled rollouts can be compared within a group u…
Generate, Filter, Control, Replay: A Comprehensive Survey of Rollout Strategies for LLM Reinforcement Learning
Rohan Surana, Gagan Mundada, Xunyi Jiang +19
Reinforcement learning (RL) has become a central post-training tool for improving the reasoning abilities of large language models (LLMs). In these systems, the rollout, the trajec…
WS-GRPO: Weakly-Supervised Group-Relative Policy Optimization for Rollout-Efficient Reasoning
Gagan Mundada, Zihan Huang, Rohan Surana +8
Group Relative Policy Optimization (GRPO) is effective for training language models on complex reasoning. However, since the objective is defined relative to a group of sampled tra…
AMPS: Adaptive Modality Preference Steering via Functional Entropy
Zihan Huang, Xintong Li, Rohan Surana +5
Multimodal Large Language Models (MLLMs) often exhibit significant modality preference, which is a tendency to favor one modality over another. Depending on the input, they may ove…
CTRLS: Chain-of-Thought Reasoning via Latent State-Transition
Junda Wu, Yuxin Xiong, Xintong Li +7
Chain-of-thought (CoT) reasoning enables large language models (LLMs) to break down complex problems into interpretable intermediate steps, significantly enhancing model transparen…
Active Learning for Direct Preference Optimization
Branislav Kveton, Xintong Li, Julian McAuley +4
Direct preference optimization (DPO) is a form of reinforcement learning from human feedback (RLHF) where the policy is learned directly from preferential feedback. Although many m…
Mitigating Visual Knowledge Forgetting in MLLM Instruction-tuning via Modality-decoupled Gradient Descent
Junda Wu, Yuxin Xiong, Xintong Li +9
Recent MLLMs have shown emerging visual understanding and reasoning abilities after being pre-trained on large-scale multimodal datasets. Unlike pre-training, where MLLMs receive r…
OCEAN: Offline Chain-of-thought Evaluation and Alignment in Large Language Models
Junda Wu, Xintong Li, Ruoyu Wang +9
Offline evaluation of LLMs is crucial in understanding their capacities, though current methods remain underexplored in existing research. In this work, we focus on the offline eva…
Visual Prompting in Multimodal Large Language Models: A Survey
Junda Wu, Zhehao Zhang, Yu Xia +12
Multimodal large language models (MLLMs) equip pre-trained large-language models (LLMs) with visual capabilities. While textual prompting in LLMs has been widely studied, visual pr…
CoMMIT: Coordinated Multimodal Instruction Tuning
Xintong Li, Junda Wu, Tong Yu +6
Instruction tuning in multimodal large language models (MLLMs) generally involves cooperative learning between a backbone LLM and a feature encoder of non-text input modalities. Th…