1 citations · 1 across the 20 of their papers we have counts for
21 papers
WorldCast: Exploring Intelligent Visual Generation in World State Prediction
Wenhao Yan, Haodong Li, Xiaotong Li +9
Humans interpret multimodal observations of the world and forecast how it will evolve. Recent multimodal generative systems have demonstrated similar capabilities: they can integra…
LongCat Sparse Attention: Taming the Lightning via Streaming-aware Hierarchical Cross-Layer Indexing
Wen Zan, Jiaqi Zhang, Jianchao Tan +11
DeepSeek Sparse Attention (DSA) enables efficient long-context modeling through its Lightning Indexer. However, practical deployment remains constrained by the indexer's expensive…
EvoCUA-1.5: Online Reinforcement Learning for Multi-turn Computer-Use Agents
Mianqiu Huang, Taofeng Xue, Chong Peng +13
Computer-use agents must solve long-horizon tasks through repeated interaction with partially observable, multimodal desktop environments. Although imitation learning and offline t…
LongCat-Flash-Prover: Advancing Native Formal Reasoning via Agentic Tool-Integrated Reinforcement Learning
Jianing Wang, Jianfei Zhang, Qi Guo +24
We introduce LongCat-Flash-Prover, a flagship 560-billion-parameter open-source Mixture-of- Experts (MoE) model that advances Native Formal Reasoning in Lean4 through agentic tool-…
Scaling Embeddings Outperforms Scaling Experts in Language Models
Hong Liu, Jiaqi Zhang, Chao Wang +13
While Mixture-of-Experts (MoE) architectures have become the standard for sparsity scaling in large language models, they increasingly face diminishing returns and system-level bot…
LongCat-Flash-Thinking-2601 Technical Report
Meituan LongCat Team, Anchun Gui, Bei Li +162
We introduce LongCat-Flash-Thinking-2601, a 560-billion-parameter open-source Mixture-of-Experts (MoE) reasoning model with superior agentic reasoning capability. LongCat-Flash-Thi…
EvoCUA: Evolving Computer Use Agents via Learning from Scalable Synthetic Experience
Taofeng Xue, Chong Peng, Mianqiu Huang +13
The development of native computer-use agents (CUA) represents a significant leap in multimodal AI. However, their potential is currently bottlenecked by the constraints of static…
SpanNorm: Reconciling Training Stability and Performance in Deep Transformers
Chao Wang, Bei Li, Jiaqi Zhang +8
The success of Large Language Models (LLMs) hinges on the stable training of deep Transformer architectures. A critical design choice is the placement of normalization layers, lead…
Exploring Reasoning Reward Model for Agents
Kaixuan Fan, Kaituo Feng, Manyuan Zhang +7
Agentic Reinforcement Learning (Agentic RL) has achieved notable success in enabling agents to perform complex reasoning and tool use. However, most methods still relies on sparse…
GIFT: Reconciling Post-Training Objectives via Variational Finite-Temperature Gibbs Initialization
Zhengyang Zhao, Lu Ma, Yizhen Jiang +7
The prevailing post-training paradigm for Large Reasoning Models (LRMs)---Supervised Fine-Tuning (SFT) followed by Reinforcement Learning (RL)-suffers from an intrinsic optimizatio…
OpenSubject: Leveraging Video-Derived Identity and Diversity Priors for Subject-driven Image Generation and Manipulation
Yexin Liu, Manyuan Zhang, Yueze Wang +8
Despite the promising progress in subject-driven image generation, current models often deviate from the reference identities and struggle in complex scenes with multiple subjects.…
EditThinker: Unlocking Iterative Reasoning for Any Image Editor
Hongyu Li, Manyuan Zhang, Dian Zheng +11
Instruction-based image editing has emerged as a prominent research area, which, benefiting from image generation foundation models, have achieved high aesthetic quality, making in…
OneThinker: All-in-one Reasoning Model for Image and Video
Kaituo Feng, Manyuan Zhang, Hongyu Li +11
Reinforcement learning (RL) has recently achieved remarkable success in eliciting visual reasoning within Multimodal Large Language Models (MLLMs). However, existing approaches typ…
Thinking-while-Generating: Interleaving Textual Reasoning throughout Visual Generation
Ziyu Guo, Renrui Zhang, Hongyu Li +6
Recent advances in visual generation have increasingly explored the integration of reasoning capabilities. They incorporate textual reasoning, i.e., think, either before (as pre-pl…
AIA: Rethinking Architecture Decoupling Strategy In Unified Multimodal Model
Dian Zheng, Manyuan Zhang, Hongyu Li +7
Unified multimodal models for image generation and understanding represent a significant step toward AGI and have attracted widespread attention from researchers. The main challeng…
CodePlot-CoT: Mathematical Visual Reasoning by Thinking with Code-Driven Images
Chengqi Duan, Kaiyue Sun, Rongyao Fang +10
Recent advances in Large Language Models (LLMs) and Vision Language Models (VLMs) have shown significant progress in mathematical reasoning, yet they still face a critical bottlene…
Think with 3D: Geometric Imagination Grounded Spatial Reasoning from Limited Views
Zhangquan Chen, Manyuan Zhang, Xinlei Yu +8
Though recent advances in vision-language models (VLMs) have achieved remarkable progress across a wide range of multimodal tasks, understanding 3D spatial relationships from limit…
LongCat-Flash Technical Report
Meituan LongCat Team, Bayan, Bei Li +179
We introduce LongCat-Flash, a 560-billion-parameter Mixture-of-Experts (MoE) language model designed for both computational efficiency and advanced agentic capabilities. Stemming f…
Introducing LongCat-Flash-Thinking: A Technical Report
Meituan LongCat Team, Anchun Gui, Bei Li +122
We present LongCat-Flash-Thinking, an efficient 560-billion-parameter open-source Mixture-of-Experts (MoE) reasoning model. Its advanced capabilities are cultivated through a metic…
MoTE: Mixture of Ternary Experts for Memory-efficient Large Multimodal Models
Hongyu Wang, Jiayu Xu, Ruiping Wang +5
Large multimodal Mixture-of-Experts (MoEs) effectively scale the model size to boost performance while maintaining fixed active parameters. However, previous works primarily utiliz…
GradPower: Powering Gradients for Faster Language Model Pre-Training
Jinbo Wang, Mingze Wang, Jiaqi Zhang +5
We propose GradPower, a lightweight gradient-transformation technique for accelerating language model pre-training. Given a gradient vector , GradPower first applies the…