Scaling Language-Centric Omnimodal Representation Learning

DITING: A Multi-Agent Evaluation Framework for Benchmarking Web Novel Translation

Advancing End-to-End Pixel Space Generative Modeling via Self-supervised Pre-training

Spatial Forcing: Implicit Spatial Representation Alignment for Vision-language-action Model

Asking Clarifying Questions for Preference Elicitation With Large Language Models

CTRL-Rec: Controlling Recommender Systems With Natural Language

RLFR: Extending Reinforcement Learning for LLMs with Flow Environment

Latent Refinement Decoding: Enhancing Diffusion-Based Language Models by Refining Belief States

OmniVideoBench: Towards Audio-Visual Understanding Evaluation for Omni MLLMs

BEAR: Benchmarking and Enhancing Multimodal Language Models for Atomic Embodied Capabilities

Diffusion Transformers with Representation Autoencoders

QeRL: Beyond Efficiency -- Quantization-enhanced Reinforcement Learning for LLMs

Inverse-Free Wilson Loops for Transformers: A Practical Diagnostic for Invariance and Order Sensitivity

TUMIX: Multi-Agent Test-Time Scaling with Tool-Use Mixture

R-Horizon: How Far Can Your Large Reasoning Model Really Go in Breadth and Depth?

AutoPR: Let's Automate Your Academic Promotion!

Multimodal Prompt Optimization: Why Not Leverage Multiple Modalities for MLLMs

TAG:Tangential Amplifying Guidance for Hallucination-Resistant Diffusion Sampling

Thinking with Camera: A Unified Multimodal Model for Camera-Centric Understanding and Generation

D2E: Scaling Vision-Action Pretraining on Desktop Data for Transfer to Embodied AI

Code2Video: A Code-centric Paradigm for Educational Video Generation

Dr. Bias: Social Disparities in AI-Powered Medical Guidance

The Potential of Second-Order Optimization for LLMs: A Study with Full Gauss-Newton

Meta-Awareness Enhances Reasoning Models: Self-Alignment Reinforcement Learning

From What to Why: A Multi-Agent System for Evidence-based Chemical Reaction Condition Reasoning

DreamOmni2: Multimodal Instruction-based Editing and Generation

VideoCanvas: Unified Video Completion from Arbitrary Spatiotemporal Patches via In-Context Conditioning

UniVideo: Unified Understanding, Generation, and Editing for Videos

MemMamba: Rethinking Memory Patterns in State Space Model

MM-HELIX: Boosting Multimodal Long-Chain Reflective Reasoning with Holistic Platform and Adaptive Hybrid Policy Optimization

Scaling Language-Centric Omnimodal Representation Learning

DITING: A Multi-Agent Evaluation Framework for Benchmarking Web Novel Translation

Advancing End-to-End Pixel Space Generative Modeling via Self-supervised Pre-training

Spatial Forcing: Implicit Spatial Representation Alignment for Vision-language-action Model

Asking Clarifying Questions for Preference Elicitation With Large Language Models

CTRL-Rec: Controlling Recommender Systems With Natural Language

RLFR: Extending Reinforcement Learning for LLMs with Flow Environment

Latent Refinement Decoding: Enhancing Diffusion-Based Language Models by Refining Belief States

OmniVideoBench: Towards Audio-Visual Understanding Evaluation for Omni MLLMs

BEAR: Benchmarking and Enhancing Multimodal Language Models for Atomic Embodied Capabilities

Diffusion Transformers with Representation Autoencoders

QeRL: Beyond Efficiency -- Quantization-enhanced Reinforcement Learning for LLMs

Inverse-Free Wilson Loops for Transformers: A Practical Diagnostic for Invariance and Order Sensitivity

TUMIX: Multi-Agent Test-Time Scaling with Tool-Use Mixture

R-Horizon: How Far Can Your Large Reasoning Model Really Go in Breadth and Depth?

AutoPR: Let's Automate Your Academic Promotion!

Multimodal Prompt Optimization: Why Not Leverage Multiple Modalities for MLLMs

TAG:Tangential Amplifying Guidance for Hallucination-Resistant Diffusion Sampling

Thinking with Camera: A Unified Multimodal Model for Camera-Centric Understanding and Generation

D2E: Scaling Vision-Action Pretraining on Desktop Data for Transfer to Embodied AI

Code2Video: A Code-centric Paradigm for Educational Video Generation

Dr. Bias: Social Disparities in AI-Powered Medical Guidance

The Potential of Second-Order Optimization for LLMs: A Study with Full Gauss-Newton

Meta-Awareness Enhances Reasoning Models: Self-Alignment Reinforcement Learning

From What to Why: A Multi-Agent System for Evidence-based Chemical Reaction Condition Reasoning

DreamOmni2: Multimodal Instruction-based Editing and Generation

VideoCanvas: Unified Video Completion from Arbitrary Spatiotemporal Patches via In-Context Conditioning

UniVideo: Unified Understanding, Generation, and Editing for Videos

MemMamba: Rethinking Memory Patterns in State Space Model

MM-HELIX: Boosting Multimodal Long-Chain Reflective Reasoning with Holistic Platform and Adaptive Hybrid Policy Optimization