SL
Sicong Leng
cs.CVcs.AIcs.CLcs.ROcs.LGcs.IRcs.SE
On Valency
published · living versionsW_qvfzh65g·v1 · currentpublished
RynnUnify: Towards Unified Embodied Brain
with Minghao Zhu, Bohan Hou, Kun Xiang, Zixuan Wang +18
1 version
Preprints & journals
28 papers in the corpus · 2021–2026Offline-Online Curriculum RL for Multimodal Reasoning2607.23700v1 · Wendi Deng, Hang Du, Guoshun Nan et al.2026 · 0 citationsarXiv
RynnBrain 1.1: Towards More Capable and Generalizable Embodied Foundation Model2607.17977v2 · Kehan Li, Bohan Hou, Minghao Zhu et al.2026 · 0 citationsarXiv
Vesta: A Generalist Embodied Reasoning Model2606.20905v1 · Johan Bjorck, Zhiqi Li, Yunze Man et al.2026 · 0 citationsarXiv
See First, Answer Later: Visual Evidence Pre-Alignment via Sufficiency-Driven RL2606.17678v1 · Yilian Liu, Sicong Leng, Guoshun Nan et al.2026 · 0 citationsarXiv
LDDR: Linear-DPP Dynamic-Resolution Frame Sampling for Video MLLMs2605.11477v2 · Jingfeng Chen, Jiawen Qian, Wendi Deng et al.2026 · 0 citationsarXiv
InterLV-Search: Benchmarking Interleaved Multimodal Agentic Search2605.07510v1 · Bohan Hou, Jiuning Gu, Jiayan Guo et al.2026 · 0 citationsarXiv
Visual Generation in the New Era: An Evolution from Atomic Mapping to Agentic World Modeling2604.28185v2 · Keming Wu, Zuhao Yang, Kaichen Zhang et al.2026 · 0 citationsarXiv
World Model for Robot Learning: A Comprehensive Survey2605.00080v1 · Bohan Hou, Gen Li, Jindou Jia et al.2026 · 1 citationarXiv
RynnBrain: Open Embodied Foundation Models2602.14979v1 · Ronghao Dang, Jiayan Guo, Bohan Hou et al.2026 · 0 citationsarXiv
LongVT: Incentivizing "Thinking with Long Videos" via Native Tool Calling2511.20785v3 · Zuhao Yang, Sudong Wang, Kaichen Zhang et al.2025 · 0 citationsarXiv
MMR1: Enhancing Multimodal Reasoning with Variance-Aware Sampling and Open Resources2509.21268v1 · Sicong Leng, Jing Wang, Jiaxi Li et al.2025 · 0 citationsarXiv
From Easy to Hard: The MIR Benchmark for Progressive Interleaved Multi-Image Reasoning2509.17040v2 · Hang Du, Jiayang Zhang, Guoshun Nan et al.2025 · 1 citationarXiv
RynnVLA-001: Using Human Demonstrations to Improve Robot Manipulation2509.15212v1 · Yuming Jiang, Siteng Huang, Shengke Xue et al.2025 · 0 citationsarXiv
VL-Cogito: Progressive Curriculum Reinforcement Learning for Advanced Multimodal Reasoning2507.22607v2 · Ruifeng Yuan, Chenghao Xiao, Sicong Leng et al.2025 · 0 citationsarXiv
Two Is Better Than One: Rotations Scale LoRAs2505.23184v1 · Hongcan Guo, Guoshun Nan, Yuan Yang et al.2025 · 0 citationsarXiv
Refining Positive and Toxic Samples for Dual Safety Self-Alignment of LLMs with Minimal Human Interventions2502.08657v1 · Jingxin Xu, Guoshun Nan, Sheng Guan et al.2025 · 0 citationsarXiv
VideoLLaMA 3: Frontier Multimodal Foundation Models for Image and Video Understanding2501.13106v4 · Boqiang Zhang, Kehan Li, Zesen Cheng et al.2025 · 5 citationsarXiv
BenchX: A Unified Benchmark Framework for Medical Vision-Language Pretraining on Chest X-Rays2410.21969v1 · Yang Zhou, Tan Li Hui Faith, Yanyu Xu et al.2024 · 3 citationsarXiv
Breaking the Memory Barrier: Near Infinite Batch Size Scaling for Contrastive Loss2410.17243v1 · Zesen Cheng, Hang Zhang, Kehan Li et al.2024 · 0 citationsarXiv
The Curse of Multi-Modalities: Evaluating Hallucinations of Large Multimodal Models across Language, Visual, and Audio2410.12787v1 · Sicong Leng, Yun Xing, Zesen Cheng et al.2024 · 1 citationarXiv
Mitigating Object Hallucinations in Large Vision-Language Models with Assembly of Global and Local Attention2406.12718v3 · Wenbin An, Feng Tian, Sicong Leng et al.2024 · 21 citationsarXiv
VideoLLaMA 2: Advancing Spatial-Temporal Modeling and Audio Understanding in Video-LLMs2406.07476v3 · Zesen Cheng, Sicong Leng, Hang Zhang et al.2024 · 11 citationsarXiv
Uncovering What, Why and How: A Comprehensive Benchmark for Causation Understanding of Video Anomaly2405.00181v3 · Hang Du, Sicheng Zhang, Binzhu Xie et al.2024 · 29 citationsarXiv
Constrained Layout Generation with Factor Graphs2404.00385v1 · Mohammed Haroon Dupty, Yanfei Dong, Sicong Leng et al.2024 · 7 citationsarXiv
Mitigating Object Hallucinations in Large Vision-Language Models through Visual Contrastive Decoding2311.16922v1 · Sicong Leng, Hang Zhang, Guanzheng Chen et al.2023 · 199 citationsarXiv
Tell2Design: A Dataset for Language-Guided Floor Plan Generation2311.15941v1 · Sicong Leng, Yang Zhou, Mohammed Haroon Dupty et al.2023 · 30 citationsarXiv
Speaker-Oriented Latent Structures for Dialogue-Based Relation Extraction2109.05182v2 · Guoshun Nan, Guoqing Luo, Sicong Leng et al.2021 · 6 citationsarXiv
Interventional Video Grounding with Dual Contrastive Learning2106.11013v2 · Guoshun Nan, Rui Qiao, Yao Xiao et al.2021 · 149 citationsarXiv
Career total: 32 works. 28 are in this corpus.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.