8 papers
Orchestrating Tokens and Sequences: Dynamic Hybrid Policy Optimization for RLVR
Zijun Min, Bingshuai Liu, Ante Wang +4
Reinforcement Learning with Verifiable Rewards (RLVR) offers a promising framework for optimizing large language models in reasoning tasks. However, existing RLVR algorithms focus…
Can LLMs Track Their Output Length? A Dynamic Feedback Mechanism for Precise Length Regulation
Meiman Xiao, Ante Wang, Qingguo Hu +5
Precisely controlling the length of generated text is a common requirement in real-world applications. However, despite significant advancements in following human instructions, La…
BioPro: Towards Difference-Aware Gender Fairness for Vision-Language Models
Yujie Lin, Jiayao Ma, Qingguo Hu +4
Vision-Language Models (VLMs) inherit significant social biases from their training data, notably in gender representation. Current fairness interventions often adopt a difference-…
LLM-OREF: An Open Relation Extraction Framework Based on Large Language Models
Hongyao Tu, Liang Zhang, Yujie Lin +4
The goal of open relation extraction (OpenRE) is to develop an RE model that can generalize to new relations not encountered during training. Existing studies primarily formulate O…
SPEC-RL: Accelerating On-Policy Reinforcement Learning with Speculative Rollouts
Bingshuai Liu, Ante Wang, Zijun Min +7
Large Language Models (LLMs) increasingly rely on reinforcement learning with verifiable rewards (RLVR) to elicit reliable chain-of-thought reasoning. However, the training process…
Boosting Visual Knowledge-Intensive Training for LVLMs Through Causality-Driven Visual Object Completion
Qingguo Hu, Ante Wang, Jia Song +3
Large Vision-Language Models (LVLMs) have experienced significant advancements in recent years. However, their performance still falls short in tasks requiring deep visual percepti…
Beyond Passive Critical Thinking: Fostering Proactive Questioning to Enhance Human-AI Collaboration
Ante Wang, Yujie Lin, Jingyao Liu +4
Critical thinking is essential for building robust AI systems, preventing them from blindly accepting flawed data or biased reasoning. However, prior work has primarily focused on…
Investigating Inference-time Scaling for Chain of Multi-modal Thought: A Preliminary Study
Yujie Lin, Ante Wang, Moye Chen +4
Recently, inference-time scaling of chain-of-thought (CoT) has been demonstrated as a promising approach for addressing multi-modal reasoning tasks. While existing studies have pre…