20 papers
LoopVL: Recurrent Visual Intelligence
Zhe Qian, Ziyang Gong, Zhongxing Xu +13
We introduce LoopVL to study whether Loop Transformers can be effectively extended to vision- language models. LoopVL combines Module-Loop and Model-Loop computation to iteratively…
TriWorldBench: A Tri-View Consistency Perspective on Embodied World Models
Xuanyi Liu, Haofeng Wang, Ruiqi Li +9
Embodied world models predict the outcomes of robot actions to support learning and planning. For robots equipped with head and wrist cameras, this requires complementary views: th…
DisciplineGen-1M: A Large-Scale Dataset for Multidisciplinary Visual Generation and Editing
Zhaokai Wang, Mingxin Liu, Zirun Zhu +11
Recent image generation and editing models can produce visually appealing natural images, yet they remain unreliable when the target image is a knowledge-intensive diagram whose co…
FIRM-Video: Check Before You Score for Reliable Text-to-Video Reward Modeling
Peiyuan Zhang, Xiangyu Zhao, Hongbo Liu +8
Reliable reward models are essential for text-to-video evaluation and alignment. However, the trade-off between evaluation accuracy and inference efficiency places high demands on…
WorldScape Policy 2.0: Empowering Steerable World Action Modeling with Reasoning-Augmented Memory and In-Context Learning
Haisheng Su, Zongdai Liu, Xin Jin +13
World Action Models (WAMs) offer a promising paradigm for robotic manipulation by jointly modeling visual state transitions and robot actions. However, existing WAMs are constraine…
Ideas Have Genomes: Benchmarking Scientific Lineage Reasoning and Lineage-Grounded Idea Generation
Yifan Zhou, Qihao Yang, Yan Li +14
Scientific ideas rarely start from a blank page. They inherit mechanisms, repair known limitations, and recombine pieces of earlier work, much like biological genomes. Current benc…
ACE-Brain-0.5: A Unified Embodied Foundational Model for Physical Agentic AI
Brain Team, Ziyang Gong, Haoming Gu +28
Embodied AI is moving from isolated perception or action modules toward physical agents that understand, plan under goals, act through robot bodies, monitor progress, and improve f…
ACE: Pluggable Adaptive Context Elasticizer across Agents
Ning Liao, Zihao Long, Xiaoxing Wang +6
The increasing complexity of agentic tasks has led to rapidly growing trajectory lengths, which poses significant challenges for large language model (LLM) based agents with fixed…
MemEvoBench: Benchmarking Safety Risks from Memory Misevolution in LLM Agents
Weiwei Xie, Shaoxiong Guo, Fan Zhang +5
Equipping Large Language Models (LLMs) with persistent memory enhances interaction continuity and personalization but introduces new safety risks. Specifically, contaminated or bia…
Rethinking the Necessity of Adaptive Retrieval-Augmented Generation through the Lens of Adaptive Listwise Ranking
Jun Feng, Jiahui Tang, Zhicheng He +5
Adaptive Retrieval-Augmented Generation aims to mitigate the interference of extraneous noise by dynamically determining the necessity of retrieving supplementary passages. However…
GRADE: Benchmarking Discipline-Informed Reasoning in Image Editing
Mingxin Liu, Ziqian Fan, Zhaokai Wang +13
Unified multimodal models target joint understanding, reasoning, and generation, but current image editing benchmarks are largely confined to natural images and shallow commonsense…
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…
EvoTok: A Unified Image Tokenizer via Residual Latent Evolution for Visual Understanding and Generation
Yan Li, Ning Liao, Xiangyu Zhao +5
The development of unified multimodal large language models (MLLMs) is fundamentally challenged by the granularity gap between visual understanding and generation: understanding re…
CrossEarth-SAR: A SAR-Centric and Billion-Scale Geospatial Foundation Model for Domain Generalizable Semantic Segmentation
Ziqi Ye, Ziyang Gong, Ning Liao +10
Synthetic Aperture Radar (SAR) enables global, all-weather earth observation. However, owing to diverse imaging mechanisms, domain shifts across sensors and regions severely hinder…
MM-HELIX: Boosting Multimodal Long-Chain Reflective Reasoning with Holistic Platform and Adaptive Hybrid Policy Optimization
Xiangyu Zhao, Junming Lin, Tianhao Liang +11
While current Multimodal Large Language Models (MLLMs) have demonstrated proficiency in reasoning tasks such as mathematics and logic, their capacity for long-chain reflective reas…
Envisioning Beyond the Pixels: Benchmarking Reasoning-Informed Visual Editing
Xiangyu Zhao, Peiyuan Zhang, Kexian Tang +10
Large Multi-modality Models (LMMs) have made significant progress in visual understanding and generation, but they still face challenges in General Visual Editing, particularly in…
Learning Adaptive and Temporally Causal Video Tokenization in a 1D Latent Space
Yan Li, Changyao Tian, Renqiu Xia +7
We propose AdapTok, an adaptive temporal causal video tokenizer that can flexibly allocate tokens for different frames based on video content. AdapTok is equipped with a block-wise…
Raw2Drive: Reinforcement Learning with Aligned World Models for End-to-End Autonomous Driving (in CARLA v2)
Zhenjie Yang, Xiaosong Jia, Qifeng Li +3
Reinforcement Learning (RL) can mitigate the causal confusion and distribution shift inherent to imitation learning (IL). However, applying RL to end-to-end autonomous driving (E2E…
Interleave-VLA: Enhancing Robot Manipulation with Interleaved Image-Text Instructions
Cunxin Fan, Xiaosong Jia, Yihang Sun +8
The rise of foundation models paves the way for generalist robot policies in the physical world. Existing methods relying on text-only instructions often struggle to generalize to…
GenieBlue: Integrating both Linguistic and Multimodal Capabilities for Large Language Models on Mobile Devices
Xudong Lu, Yinghao Chen, Renshou Wu +10
Recent advancements in Multimodal Large Language Models (MLLMs) have enabled their deployment on mobile devices. However, challenges persist in maintaining strong language capabili…