Reinforcement Learning with verifiable rewards (RLVR) has emerged as a primary learning paradigm for enhancing the reasoning capabilities of multi-modal large language models (MLLMs). However, during RL training, the enormous state space of MLLM and sparse rewards often leads to entropy collapse, policy degradation, or over-exploitation of suboptimal behaviors. This necessitates an exploration strategy that maintains productive stochasticity while avoiding the drawbacks of uncontrolled random sampling, yielding inefficient exploration. In this paper, we propose CalibRL, a hybrid-policy RLVR framework that supports controllable exploration with expert guidance, enabled by two key mechanisms. First, a distribution-aware advantage weighting scales updates by group rareness to calibrate the distribution, therefore preserving exploration. Meanwhile, the asymmetric activation function (LeakyReLU) leverages the expert knowledge as a calibration baseline to moderate overconfident updates while preserving their corrective direction. CalibRL increases policy entropy in a guided manner and clarifies the target distribution by estimating the on-policy distribution through online sampling. Updates are driven by these informative behaviors, avoiding convergence to erroneous patterns. Importantly, these designs help alleviate the distributional mismatch between the model's policy and expert trajectories, thereby achieving a more stable balance between exploration and exploitation. Extensive experiments across eight benchmarks, including both in-domain and out-of-domain settings, demonstrate consistent improvements, validating the effectiveness of our controllable hybrid-policy RLVR training. Code is available at https://github.com/zhh6425/CalibRL.
Enigmata: Scaling Logical Reasoning in Large Language Models with Synthetic Verifiable Puzzles
ByteDance Seed（字节跳动种子）；Fudan University（复旦大学）；Institute for AI Industry Research (AIR), Tsinghua University（人工智能产业研究院（AIR），清华大学）；Nanjing University（南京大学）；Shanghai Jiao Tong University（上海交通大学）；SIA-Lab of Tsinghua AIR and ByteDance Seed（清华大学AIR实验室和字节跳动种子）
FiLoRA: Focus-and-Ignore LoRA for Controllable Feature Reliance
University of Melbourne, Melbourne, Australia；Brain Science Institute, Korea Institute of Science；Department of Computer Science；Engineering, Korea University, Seoul, Republic of Korea；Division of Bio-Medical Science \& Technology, University of Science；Technology KIST School, Seoul, Republic of Korea
TASU2: Controllable CTC Simulation for Alignment and Low-Resource Adaptation of Speech LLMs
X-LANCE Lab, Department of Computer Science and Engineering, Shanghai Jiao Tong University（上海交通大学计算机科学与工程系X-LANCE实验室）；MoE Key Lab of Artificial Intelligence（教育部人工智能重点实验室）；Jiangsu Key Lab of Language Computing（江苏省语言计算重点实验室）；AISpeech Ltd（思必驰科技股份有限公司）；Nanjing University（南京大学）
ProcessThinker: Enhancing Multi-modal Large Language Models Reasoning via Rollout-based Process Reward
LMU Munich（慕尼黑大学）；Harvard University（哈佛大学）；University of Cambridge（剑桥大学）；Mina AI；Konrad Zuse School of Excellence in Reliable AI (relAI)（康拉德·楚泽可靠人工智能卓越学校（relAI））
When Modalities Conflict: How Unimodal Reasoning Uncertainty Governs Preference Dynamics in MLLMs
Peking University（北京大学）；Provable Responsible AI and Data Analytics (PRADA) Lab（可证明负责任的人工智能和数据分析实验室）；King Abdullah University of Science and Technology（卡布斯大学）；South China University of Technology（华南理工大学）；Tsinghua University（清华大学）；University of Georgia（佐治亚大学）；MBZUAI（马克斯·普朗克人工智能研究所）
PR-CAD: Progressive Refinement for Unified Controllable and Faithful Text-to-CAD Generation with Large Language Models
School of Information Science, Beijing Language and Culture University, China（北京语言大学信息学院）；School of Computer Science and Technology, Beijing Jiaotong University, China（北京交通大学计算机科学与技术学院）；School of Computer Science and Engineering, Northeastern University, China（东北大学计算机科学与工程学院）；Department of Computer Science and Technology, Tsinghua University, China（清华大学计算机科学与技术系）；School of Computer Science and Technology, Harbin Institute of Technology (Shenzhen), China（哈尔滨工业大学（深圳）计算机科学与技术学院）
CATCH: A Controllable Analysis Testbed for Reward Hacking in Coding RL
Tsinghua University（清华大学）；Beihang University（北京航空航天大学）；Southern University of Science and Technology（南方科技大学）；Renmin University of China（中国人民大学）；Shanghai University of Finance and Economics（上海财经大学）
Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China（中国科学院信息工程研究所）；School of Cyber Security, University of Chinese Academy of Sciences, Beijing, China（中国科学院大学网络安全学院）
Multi-Modal and Multi-Attribute Generation of Single Cells with CFGen
Helmholtz Munich（亥姆霍兹慕尼黑）；Technical University of Munich（慕尼黑工业大学）；Université de Montréal（蒙特利尔大学）；Mila（米拉计算科学研究所）；MPI for Intelligent Systems, Tübingen（图宾根马克斯·普朗克智能系统研究所）
BEAT: A Large-Scale Semantic and Emotional Multi-Modal Dataset for Conversational Gestures Synthesis
The University of Tokyo（东京大学）；Keio University（庆应义塾大学）；Huawei Technologies Japan K.K.（华为技术日本株式会社）；Japan Advanced Institute of Science and Technology（日本北陆先端科学技术大学院大学）；Huawei Turkey R&D Center（华为土耳其研发中心）
