Yu Cheng
- Papers
- 81
Cite
Notes
Only stored in your browser.
Authored papers
81MiMo-V2-Flash Technical Report
arXiv 2026
AdaReasoner: Dynamic Tool Orchestration for Iterative Visual Reasoning
arXiv 2026
GEMS: Agent-Native Multimodal Generation with Memory and Skills
arXiv 2026
A Survey of Large Audio Language Models: Generalization, Trustworthiness, and Outlook
arXiv 2026
TEMPO: Scaling Test-time Training for Large Reasoning Models
arXiv 2026
Persistent Visual Memory: Sustaining Perception for Deep Generation in LVLMs
arXiv 2026
TabEmbed: Benchmarking and Learning Generalist Embeddings for Tabular Understanding
arXiv 2026
P1-VL: Bridging Visual Perception and Scientific Reasoning in Physics Olympiads
arXiv 2026
How Do Decoder-Only LLMs Perceive Users? Rethinking Attention Masking for User Representation Learning
arXiv 2026
DrawMotion: Generating 3D Human Motions by Freehand Drawing
arXiv 2026
Unify-Agent: A Unified Multimodal Agent for World-Grounded Image Synthesis
arXiv 2026
π-Bench: Evaluating Proactive Personal Assistant Agents in Long-Horizon Workflows
arXiv 2026
Memory Intelligence Agent
arXiv 2026
LatentMem: Customizing Latent Memory for Multi-Agent Systems
arXiv 2026
Think Longer to Explore Deeper: Learn to Explore In-Context via Length-Incentivized Reinforcement Learning
arXiv 2026
Query as Anchor: Scenario-Adaptive User Representation via Large Language Model
arXiv 2026
The Entropy Mechanism of Reinforcement Learning for Reasoning Language Models
arXiv 2025
Learning to Reason under Off-Policy Guidance
arXiv 2025
VideoREPA: Learning Physics for Video Generation through Relational Alignment with Foundation Models
arXiv 2025
Process Reinforcement through Implicit Rewards
arXiv 2025
SeerAttention-R: Sparse Attention Adaptation for Long Reasoning
arXiv 2025
Linear-MoE: Linear Sequence Modeling Meets Mixture-of-Experts
arXiv 2025
OpenThinkIMG: Learning to Think with Images via Visual Tool Reinforcement Learning
arXiv 2025
Make LoRA Great Again: Boosting LoRA with Adaptive Singular Values and Mixture-of-Experts Optimization Alignment
arXiv 2025
Divide and Conquer: Grounding LLMs as Efficient Decision-Making Agents via Offline Hierarchical Reinforcement Learning
arXiv 2025
Text-to-Decision Agent: Learning Generalist Policies from Natural Language Supervision
arXiv 2025
SATORI-R1: Incentivizing Multimodal Reasoning with Spatial Grounding and Verifiable Rewards
arXiv 2025
DiffThinker: Towards Generative Multimodal Reasoning with Diffusion Models
arXiv 2025
ExGRPO: Learning to Reason from Experience
arXiv 2025
Speed Always Wins: A Survey on Efficient Architectures for Large Language Models
arXiv 2025
Spotlight on Token Perception for Multimodal Reinforcement Learning
arXiv 2025
Scaling Reasoning, Losing Control: Evaluating Instruction Following in Large Reasoning Models
arXiv 2025
Test-Time Preference Optimization: On-the-Fly Alignment via Iterative Textual Feedback
arXiv 2025
Liger: Linearizing Large Language Models to Gated Recurrent Structures
arXiv 2025
UltraIF: Advancing Instruction Following from the Wild
arXiv 2025
Visually Interpretable Subtask Reasoning for Visual Question Answering
arXiv 2025
Native Hybrid Attention for Efficient Sequence Modeling
arXiv 2025
Thinking with Images for Multimodal Reasoning: Foundations, Methods, and Future Frontiers
arXiv 2025
VideoSSR: Video Self-Supervised Reinforcement Learning
arXiv 2025
P1: Mastering Physics Olympiads with Reinforcement Learning
arXiv 2025
ThinkMorph: Emergent Properties in Multimodal Interleaved Chain-of-Thought Reasoning
arXiv 2025
TiViBench: Benchmarking Think-in-Video Reasoning for Video Generative Models
arXiv 2025
Interleaving Reasoning for Better Text-to-Image Generation
arXiv 2025
FrameThinker: Learning to Think with Long Videos via Multi-Turn Frame Spotlighting
arXiv 2025
From AI for Science to Agentic Science: A Survey on Autonomous Scientific Discovery
arXiv 2025
FullFront: Benchmarking MLLMs Across the Full Front-End Engineering Workflow
arXiv 2025
A Survey of Efficient Reasoning for Large Reasoning Models: Language, Multimodality, and Beyond
arXiv 2025
Extrapolating and Decoupling Image-to-Video Generation Models: Motion Modeling is Easier Than You Think
CVPR 2025 1
Reasoning over Boundaries: Enhancing Specification Alignment via Test-time Deliberation
arXiv 2025
From Drafts to Answers: Unlocking LLM Potential via Aggregation Fine-Tuning
arXiv 2025
Advancing Multimodal Reasoning: From Optimized Cold Start to Staged Reinforcement Learning
arXiv 2025
LLaMA-MoE: Building Mixture-of-Experts from LLaMA with Continual Pre-training
arXiv 2024
CLIP-MoE: Towards Building Mixture of Experts for CLIP with Diversified Multiplet Upcycling
arXiv 2024
LLaMA-MoE v2: Exploring Sparsity of LLaMA from Perspective of Mixture-of-Experts with Post-Training
arXiv 2024
Grounded-VideoLLM: Sharpening Fine-grained Temporal Grounding in Video Large Language Models
arXiv 2024
Towards World Simulator: Crafting Physical Commonsense-Based Benchmark for Video Generation
arXiv 2024
ConflictBank: A Benchmark for Evaluating the Influence of Knowledge Conflicts in LLM
arXiv 2024
Dynamic Data Mixing Maximizes Instruction Tuning for Mixture-of-Experts
arXiv 2024
Timo: Towards Better Temporal Reasoning for Language Models
arXiv 2024
Look, Compare, Decide: Alleviating Hallucination in Large Vision-Language Models via Multi-View Multi-Path Reasoning
arXiv 2024
Learning the Unlearned: Mitigating Feature Suppression in Contrastive Learning
arXiv 2024
What makes your model a low-empathy or warmth person: Exploring the Origins of Personality in LLMs
arXiv 2024
SURf: Teaching Large Vision-Language Models to Selectively Utilize Retrieved Information
arXiv 2024
MAGIS: LLM-Based Multi-Agent Framework for GitHub Issue Resolution
arXiv 2024
Continuous Speech Tokenizer in Text To Speech
arXiv 2024
Twin-Merging: Dynamic Integration of Modular Expertise in Model Merging
arXiv 2024
Towards Stabilized and Efficient Diffusion Transformers through Long-Skip-Connections with Spectral Constraints
ICCV 2025
A Survey of Reasoning with Foundation Models
arXiv 2023
AdaLoRA: Adaptive Budget Allocation for Parameter-Efficient Fine-Tuning
arXiv 2023
Enhancing Low-Resource Relation Representations through Multi-View Decoupling
arXiv 2023
Merge, Then Compress: Demystify Efficient SMoE with Hints from Its Routing Policy
arXiv 2023
Hiding Data Helps: On the Benefits of Masking for Sparse Coding
arXiv 2023
M$^3$ViT: Mixture-of-Experts Vision Transformer for Efficient Multi-task Learning with Model-Accelerator Co-design
arXiv 2022
RASAT: Integrating Relational Structures into Pretrained Seq2Seq Model for Text-to-SQL
arXiv 2022
Local Byte Fusion for Neural Machine Translation
arXiv 2022
DSEE: Dually Sparsity-embedded Efficient Tuning of Pre-trained Language Models
dsee-dually-sparsity-embedded-efficient
VIOLIN: A Large-Scale Dataset for Video-and-Language Inference
violin-a-large-scale-dataset-for-video-and-1
Graph Optimal Transport for Cross-Domain Alignment
ICML 2020 1
HERO: Hierarchical Encoder for Video+Language Omni-representation Pre-training
EMNLP 2020 11
UNITER: UNiversal Image-TExt Representation Learning
ECCV 2020 8
EnlightenGAN: Deep Light Enhancement without Paired Supervision
arXiv 2019
Affiliations
Frequent co-authors
10from 81 papers