Assessing adaptive world models in machines with novel games

Emotional Support with LLM-based Empathetic Dialogue Generation

DrafterBench: Benchmarking Large Language Models for Tasks Automation in Civil Engineering

SWE-Perf: Can Language Models Optimize Code Performance on Real-World Repositories?

MOSPA: Human Motion Generation Driven by Spatial Audio

MMHU: A Massive-Scale Multimodal Benchmark for Human Behavior Understanding

PhysX: Physical-Grounded 3D Asset Generation

Towards Agentic RAG with Deep Reasoning: A Survey of RAG-Reasoning Systems in LLMs

La-Proteina: Atomistic Protein Generation via Partially Latent Flow Matching

SUICA: Learning Super-high Dimensional Sparse Implicit Neural Representations for Spatial Transcriptomics

XiChen: An observation-scalable fully AI-driven global weather forecasting system with 4D variational knowledge

AgentsNet: Coordination and Collaborative Reasoning in Multi-Agent LLMs

Can Multimodal Foundation Models Understand Schematic Diagrams? An Empirical Study on Information-Seeking QA over Scientific Papers

Scaling Laws for Optimal Data Mixtures

Subject-Consistent and Pose-Diverse Text-to-Image Generation

Vision-Language-Vision Auto-Encoder: Scalable Knowledge Distillation from Diffusion Models

DuetGraph: Coarse-to-Fine Knowledge Graph Reasoning with Dual-Pathway Global-Local Fusion

CogDDN: A Cognitive Demand-Driven Navigation with Decision Optimization and Dual-Process Thinking

LayerCake: Token-Aware Contrastive Decoding within Large Language Model Layers

Mixture-of-Recursions: Learning Dynamic Recursive Depths for Adaptive Token-Level Computation

REST: Stress Testing Large Reasoning Models by Asking Multiple Problems at Once

EmbRACE-3K: Embodied Reasoning and Action in Complex Environments

Reasoning or Memorization? Unreliable Results of Reinforcement Learning Due to Data Contamination

SpeakerVid-5M: A Large-Scale High-Quality Dataset for Audio-Visual Dyadic Interactive Human Generation

VerifyBench: A Systematic Benchmark for Evaluating Reasoning Verifiers Across Domains

Sidechain conditioning and modeling for full-atom protein sequence design with FAMPNN

One Token to Fool LLM-as-a-Judge

From One to More: Contextual Part Latents for 3D Generation

Open Vision Reasoner: Transferring Linguistic Cognitive Behavior for Visual Reasoning

Lumos-1: On Autoregressive Video Generation from a Unified Model Perspective

Assessing adaptive world models in machines with novel games

Emotional Support with LLM-based Empathetic Dialogue Generation

DrafterBench: Benchmarking Large Language Models for Tasks Automation in Civil Engineering

SWE-Perf: Can Language Models Optimize Code Performance on Real-World Repositories?

MOSPA: Human Motion Generation Driven by Spatial Audio

MMHU: A Massive-Scale Multimodal Benchmark for Human Behavior Understanding

PhysX: Physical-Grounded 3D Asset Generation

Towards Agentic RAG with Deep Reasoning: A Survey of RAG-Reasoning Systems in LLMs

La-Proteina: Atomistic Protein Generation via Partially Latent Flow Matching

SUICA: Learning Super-high Dimensional Sparse Implicit Neural Representations for Spatial Transcriptomics

XiChen: An observation-scalable fully AI-driven global weather forecasting system with 4D variational knowledge

AgentsNet: Coordination and Collaborative Reasoning in Multi-Agent LLMs

Can Multimodal Foundation Models Understand Schematic Diagrams? An Empirical Study on Information-Seeking QA over Scientific Papers

Scaling Laws for Optimal Data Mixtures

Subject-Consistent and Pose-Diverse Text-to-Image Generation

Vision-Language-Vision Auto-Encoder: Scalable Knowledge Distillation from Diffusion Models

DuetGraph: Coarse-to-Fine Knowledge Graph Reasoning with Dual-Pathway Global-Local Fusion

CogDDN: A Cognitive Demand-Driven Navigation with Decision Optimization and Dual-Process Thinking

LayerCake: Token-Aware Contrastive Decoding within Large Language Model Layers

Mixture-of-Recursions: Learning Dynamic Recursive Depths for Adaptive Token-Level Computation

REST: Stress Testing Large Reasoning Models by Asking Multiple Problems at Once

EmbRACE-3K: Embodied Reasoning and Action in Complex Environments

Reasoning or Memorization? Unreliable Results of Reinforcement Learning Due to Data Contamination

SpeakerVid-5M: A Large-Scale High-Quality Dataset for Audio-Visual Dyadic Interactive Human Generation

VerifyBench: A Systematic Benchmark for Evaluating Reasoning Verifiers Across Domains

Sidechain conditioning and modeling for full-atom protein sequence design with FAMPNN

One Token to Fool LLM-as-a-Judge

From One to More: Contextual Part Latents for 3D Generation

Open Vision Reasoner: Transferring Linguistic Cognitive Behavior for Visual Reasoning

Lumos-1: On Autoregressive Video Generation from a Unified Model Perspective