8 papers
Smaller Models are Natural Explorers for Policy-Level Diversity in GRPO
Yiming Ren, Yiran Xu, Zicheng Lin +8
We identify a new dimension for enhancing rollout diversity in Group Relative Policy Optimization (GRPO) for LLMs. While GRPO relies on diverse rollouts, prevailing strategies prim…
OmniVerifier-M1: Multimodal Meta-Verifier with Explicit Structured Recalibration
Xinchen Zhang, Bowei Liu, Jiale Liu +7
Visual outcomes are increasingly central to multimodal large language models, making reliable and fine-grained verification essential for scaling generalist foundation models. In t…
HaLoRA: Hardware-aware Low-Rank Adaptation for Large Language Models Based on Hybrid Compute-in-Memory Architecture
Taiqiang Wu, Chenchen Ding, Wenyong Zhou +7
Low-rank adaptation (LoRA) is a predominant parameter-efficient finetuning method for adapting large language models (LLMs) to downstream tasks. Meanwhile, Compute-in-Memory (CIM)…
From Narrow to Panoramic Vision: Attention-Guided Cold-Start Reshapes Multimodal Reasoning
Ruilin Luo, Chufan Shi, Yizhen Zhang +10
The cold-start initialization stage plays a pivotal role in training Multimodal Large Reasoning Models (MLRMs), yet its mechanisms remain insufficiently understood. To analyze this…
Unlocking Multimodal Mathematical Reasoning via Process Reward Model
Ruilin Luo, Zhuofan Zheng, Yifan Wang +9
Process Reward Models (PRMs) have shown promise in enhancing the mathematical reasoning capabilities of Large Language Models (LLMs) through Test-Time Scaling (TTS). However, their…
LLM2: Let Large Language Models Harness System 2 Reasoning
Cheng Yang, Chufan Shi, Siheng Li +3
Large language models (LLMs) have exhibited impressive capabilities across a myriad of tasks, yet they occasionally yield undesirable outputs. We posit that these limitations are r…