24 papers
V-ICAL Bench: Evaluating Video In-Context Learning for Multimodal Agents in Interactive Environments
Ziqian Fan, Shibo Xu, Junjie Li +8
While In-Context Learning (ICL) enables models to adapt from exemplars without parameter updates, multimodal ICL remains largely underexplored, particularly regarding video demonst…
WorldReward: Reward Modeling for Camera-Conditioned World Models
Yibin Wang, Zehan Wang, Junshu Tang +13
Camera-conditioned world models generate interactive videos in which commanded actions should induce the expected scene changes while appearance, geometry, and temporal dynamics re…
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…
HPSD: Hybrid-Policy Self-Distillation for Text-Image-to-Video Diffusion Models
Jiazi Bu, Pengyang Ling, Yujie Zhou +10
Text-Image-to-Video (TI2V) models are an emerging unified architecture, where a single model simultaneously supports text-to-video (T2V) and image-to-video (I2V) generation. Given…
Beyond the Current Observation: Evaluating Multimodal Large Language Models in Controllable Non-Markov Games
Shengyuan Ding, Xilin Wei, Xinyu Fang +4
Deploying multimodal foundation models as closed-loop policies increasingly requires conditioning actions on observations that are no longer visible. However, existing benchmarks e…
SetCon: Towards Open-Ended Referring Segmentation via Set-Level Concept Prediction
Zhixiong Zhang, Yizhuo Li, Shuangrui Ding +6
Referring segmentation grounds natural-language queries to pixel-level masks, but extending it to complex scenarios with multiple instances, cross-category groups, or open-ended ta…
Beyond Mode Collapse: Distribution Matching for Diverse Reasoning
Xiaozhe Li, Yang Li, Xinyu Fang +10
On-policy reinforcement learning methods like GRPO suffer from mode collapse: they exhibit reduced solution diversity, concentrating probability mass on a single solution once disc…
WildClawBench: A Benchmark for Real-World, Long-Horizon Agent Evaluation
Shuangrui Ding, Xuanlang Dai, Long Xing +14
Large language and vision-language models increasingly power agents that act on a user's behalf through command-line interface (CLI) harnesses. However, most agent benchmarks still…
Forge: Quality-Aware Reinforcement Learning for NP-Hard Optimization in LLMs
Xiaozhe Li, Xinyu Fang, Shengyuan Ding +5
Large Language Models (LLMs) have achieved remarkable success on reasoning benchmarks through Reinforcement Learning with Verifiable Rewards (RLVR), excelling at tasks such as math…
OPT-BENCH: Evaluating the Iterative Self-Optimization of LLM Agents in Large-Scale Search Spaces
Xiaozhe Li, Jixuan Chen, Xinyu Fang +4
Large Language Models (LLMs) have demonstrated remarkable capabilities in reasoning and tool use. However, the fundamental cognitive faculties essential for problem solving, includ…
ClawMark: A Living-World Benchmark for Multi-Turn, Multi-Day, Multimodal Coworker Agents
Fanqing Meng, Lingxiao Du, Zijian Wu +46
Language-model agents are increasingly used as persistent coworkers that assist users across multiple working days. During such workflows, the surrounding environment may change in…
Intern-S1-Pro: Scientific Multimodal Foundation Model at Trillion Scale
Yicheng Zou, Dongsheng Zhu, Lin Zhu +174
We introduce Intern-S1-Pro, the first one-trillion-parameter scientific multimodal foundation model. Scaling to this unprecedented size, the model delivers a comprehensive enhancem…
Reliable Reasoning in SVG-LLMs via Multi-Task Multi-Reward Reinforcement Learning
Haomin Wang, Qi Wei, Qianli Ma +4
With the rapid advancement of vision-language models, an increasing number of studies have explored their potential for SVG generation tasks. Although existing approaches improve p…
Trust Your Critic: Robust Reward Modeling and Reinforcement Learning for Faithful Image Editing and Generation
Xiangyu Zhao, Peiyuan Zhang, Junming Lin +7
Reinforcement learning (RL) has emerged as a promising paradigm for enhancing image editing and text-to-image (T2I) generation. However, current reward models, which act as critics…
Visual-ERM: Reward Modeling for Visual Equivalence
Ziyu Liu, Shengyuan Ding, Xinyu Fang +7
Vision-to-code tasks require models to reconstruct structured visual inputs, such as charts, tables, and SVGs, into executable or structured representations with high visual fideli…
DeepGen 1.0: A Lightweight Unified Multimodal Model for Advancing Image Generation and Editing
Dianyi Wang, Ruihang Li, Feng Han +17
Current unified multimodal models for image generation and editing typically rely on massive parameter scales (e.g., >10B), entailing prohibitive training costs and deployment foot…
ARM-Thinker: Reinforcing Multimodal Generative Reward Models with Agentic Tool Use and Visual Reasoning
Shengyuan Ding, Xinyu Fang, Ziyu Liu +10
Reward models are critical for aligning vision-language systems with human preferences, yet current approaches suffer from hallucination, weak visual grounding, and an inability to…
NP-Engine: Empowering Optimization Reasoning in Large Language Models with Verifiable Synthetic NP Problems
Xiaozhe Li, Xinyu Fang, Shengyuan Ding +4
Large Language Models (LLMs) have shown strong reasoning capabilities, with models like OpenAI's O-series and DeepSeek R1 excelling at tasks such as mathematics, coding, logic, and…
SPARK: Synergistic Policy And Reward Co-Evolving Framework
Ziyu Liu, Yuhang Zang, Shengyuan Ding +5
Recent Large Language Models (LLMs) and Large Vision-Language Models (LVLMs) increasingly use Reinforcement Learning (RL) for post-pretraining, such as RL with Verifiable Rewards (…
OPT-BENCH: Evaluating LLM Agent on Large-Scale Search Spaces Optimization Problems
Xiaozhe Li, Jixuan Chen, Xinyu Fang +4
Large Language Models (LLMs) have shown remarkable capabilities in solving diverse tasks. However, their proficiency in iteratively optimizing complex solutions through learning fr…
MM-IFEngine: Towards Multimodal Instruction Following
Shengyuan Ding, Shenxi Wu, Xiangyu Zhao +7
The Instruction Following (IF) ability measures how well Multi-modal Large Language Models (MLLMs) understand exactly what users are telling them and whether they are doing it righ…
Creation-MMBench: Assessing Context-Aware Creative Intelligence in MLLM
Xinyu Fang, Zhijian Chen, Kai Lan +10
Creativity is a fundamental aspect of intelligence, involving the ability to generate novel and appropriate solutions across diverse contexts. While Large Language Models (LLMs) ha…
OmniAlign-V: Towards Enhanced Alignment of MLLMs with Human Preference
Xiangyu Zhao, Shengyuan Ding, Zicheng Zhang +10
Recent advancements in open-source multi-modal large language models (MLLMs) have primarily focused on enhancing foundational capabilities, leaving a significant gap in human prefe…
InternLM-XComposer2.5-Reward: A Simple Yet Effective Multi-Modal Reward Model
Yuhang Zang, Xiaoyi Dong, Pan Zhang +10
Despite the promising performance of Large Vision Language Models (LVLMs) in visual understanding, they occasionally generate incorrect outputs. While reward models (RMs) with rein…