Multi-Crit: Benchmarking Multimodal Judges on Pluralistic Criteria-Following

MIRA: Multimodal Iterative Reasoning Agent for Image Editing

ENACT: Evaluating Embodied Cognition with World Modeling of Egocentric Interaction

Canvas-to-Image: Compositional Image Generation with Multimodal Controls

Video Generation Models Are Good Latent Reward Models

DeepSeekMath-V2: Towards Self-Verifiable Mathematical Reasoning

ToolOrchestra: Elevating Intelligence via Efficient Model and Tool Orchestration

Think Visually, Reason Textually: Vision-Language Synergy in ARC

Harmony: Harmonizing Audio and Video Generation through Cross-Task Synergy

Inferix: A Block-Diffusion based Next-Generation Inference Engine for World Simulation

Latent Collaboration in Multi-Agent Systems

Multimodal Evaluation of Russian-language Architectures

ROOT: Robust Orthogonalized Optimizer for Neural Network Training

Superposition Yields Robust Neural Scaling

Optimal Mistake Bounds for Transductive Online Learning

Does Reinforcement Learning Really Incentivize Reasoning Capacity in LLMs Beyond the Base Model?

Why Diffusion Models Don’t Memorize: The Role of Implicit Dynamical Regularization in Training

1000 Layer Networks for Self-Supervised RL: Scaling Depth Can Enable New Goal-Reaching Capabilities

Gated Attention for Large Language Models: Non-linearity, Sparsity, and Attention-Sink-Free

Artificial Hivemind: The Open-Ended Homogeneity of Language Models (and Beyond)

Evolution Strategies at the Hyperscale

Does Understanding Inform Generation in Unified Multimodal Models? From Analysis to Path Forward

iMontage: Unified, Versatile, Highly Dynamic Many-to-many Image Generation

Agent0-VL: Exploring Self-Evolving Agent for Tool-Integrated Vision-Language Reasoning

MedSAM3: Delving into Segment Anything with Medical Concepts

SteadyDancer: Harmonized and Coherent Human Image Animation with First-Frame Preservation

GigaEvo: An Open Source Optimization Framework Powered By LLMs And Evolution Algorithms

Fidelity-Aware Recommendation Explanations via Stochastic Path Integration

Extracting Interaction-Aware Monosemantic Concepts in Recommender Systems

MSRNet: A Multi-Scale Recursive Network for Camouflaged Object Detection

Multi-Crit: Benchmarking Multimodal Judges on Pluralistic Criteria-Following

MIRA: Multimodal Iterative Reasoning Agent for Image Editing

ENACT: Evaluating Embodied Cognition with World Modeling of Egocentric Interaction

Canvas-to-Image: Compositional Image Generation with Multimodal Controls

Video Generation Models Are Good Latent Reward Models

DeepSeekMath-V2: Towards Self-Verifiable Mathematical Reasoning

ToolOrchestra: Elevating Intelligence via Efficient Model and Tool Orchestration

Think Visually, Reason Textually: Vision-Language Synergy in ARC

Harmony: Harmonizing Audio and Video Generation through Cross-Task Synergy

Inferix: A Block-Diffusion based Next-Generation Inference Engine for World Simulation

Latent Collaboration in Multi-Agent Systems

Multimodal Evaluation of Russian-language Architectures

ROOT: Robust Orthogonalized Optimizer for Neural Network Training

Superposition Yields Robust Neural Scaling

Optimal Mistake Bounds for Transductive Online Learning

Does Reinforcement Learning Really Incentivize Reasoning Capacity in LLMs Beyond the Base Model?

Why Diffusion Models Don’t Memorize: The Role of Implicit Dynamical Regularization in Training

1000 Layer Networks for Self-Supervised RL: Scaling Depth Can Enable New Goal-Reaching Capabilities

Gated Attention for Large Language Models: Non-linearity, Sparsity, and Attention-Sink-Free

Artificial Hivemind: The Open-Ended Homogeneity of Language Models (and Beyond)

Evolution Strategies at the Hyperscale

Does Understanding Inform Generation in Unified Multimodal Models? From Analysis to Path Forward

iMontage: Unified, Versatile, Highly Dynamic Many-to-many Image Generation

Agent0-VL: Exploring Self-Evolving Agent for Tool-Integrated Vision-Language Reasoning

MedSAM3: Delving into Segment Anything with Medical Concepts

SteadyDancer: Harmonized and Coherent Human Image Animation with First-Frame Preservation

GigaEvo: An Open Source Optimization Framework Powered By LLMs And Evolution Algorithms

Fidelity-Aware Recommendation Explanations via Stochastic Path Integration

Extracting Interaction-Aware Monosemantic Concepts in Recommender Systems

MSRNet: A Multi-Scale Recursive Network for Camouflaged Object Detection