9 papers
PAWBench: How Far Are We from Probabilistically Aligned World Modeling?
Yuandong Pu, Le Zhuo, Sayak Paul +11
Recent video generation models are increasingly framed as world models. Many physical processes can unfold in more than one valid way. Therefore, a world model should reproduce not…
Intern-S2-Preview: Scientific Agentic Foundation Model
Lei Bai, Jiaqi Cao, Chiyu Chen +121
Scientific discovery increasingly requires AI systems that can reason over scientific evidence of heterogeneous modalities, interact with scientific tools and environments, and sus…
SIVA-RL: Sensitivity-Invariance Visual Alignment for Multimodal Reinforcement Learning
Cheng Tang, Junzhi Ning, Min Cen +9
Reinforcement learning with verifiable rewards (RLVR) drives multimodal reasoning, but answer-level correctness does not guarantee that a vision-language model grounds its predicti…
EvoGraph-R1: Self-Evolving Multimodal Knowledge Hypergraphs for Agentic Retrieval
Jiashi Lin, Changhong Jiang, Xiangru Lin +12
Retrieval-augmented generation (RAG) has emerged as a critical paradigm for grounding Multimodal Large Language Models (MLLMs) in external knowledge. Recent GraphRAG methods introd…
A First-Principles Derivation of LLM Policy Optimization: From Expected Reward to GRPO and Its Structural Extensions
Jianghan Shen, Siqi Luo, Yue Li +9
Policy gradient algorithms for language models optimize the same objective , which has exactly two factors: the trajectory probability $p_θ(…
Sketch Then Paint: Hierarchical Reinforcement Learning for Diffusion Multi-Modal Large Language Models
Siqi Luo, Jianghan Shen, Yi Xin +9
Diffusion Multi-Modal Large Language Models (dMLLMs) are powerful for image generation, but optimizing them through reinforcement learning (RL) remains a major challenge. One prima…
CuSearch: Curriculum Rollout Sampling via Search Depth for Agentic RAG
Jianghan Shen, Siqi Luo, Xinyu Cheng +6
Reinforcement Learning with Verifiable Rewards (RLVR) has emerged as a promising paradigm for training agentic retrieval-augmented generation (RAG) systems from outcome-only superv…
MedQ-Deg: A Multidimensional Benchmark for Evaluating MLLMs Across Medical Image Quality Degradations
Jiyao Liu, Junzhi Ning, Chenglong Ma +14
Despite impressive performance on standard benchmarks, multimodal large language models (MLLMs) face critical challenges in real-world clinical environments where medical images in…
dMLLM-TTS: Self-Verified and Efficient Test-Time Scaling for Diffusion Multi-Modal Large Language Models
Yi Xin, Siqi Luo, Tianxiang Xu +13
Diffusion Multi-modal Large Language Models (dMLLMs) have recently emerged as a novel architecture unifying image generation and understanding. However, developing effective and ef…