Qwen-Image-Layered: Towards Inherent Editability via Layer Decomposition

RoboSafe: Safeguarding Embodied Agents via Executable Safety Logic

A Real-World Evaluation of LLM Medication Safety Reviews in NHS Primary Care

Multi-LLM Thematic Analysis with Dual Reliability Metrics: Combining Cohen's Kappa and Semantic Similarity for Qualitative Research Validation

Active Intelligence in Video Avatars via Closed-loop World Modeling

FaithLens: Detecting and Explaining Faithfulness Hallucination

SAM Audio: Segment Anything in Audio

Step-DeepResearch Technical Report

SpatialTree: How Spatial Abilities Branch Out in MLLMs

SemanticGen: Video Generation in Semantic Space

Automated stereotactic radiosurgery planning using a human-in-the-loop reasoning large language model agent

LongVideoAgent: Multi-Agent Reasoning with Long Videos

GenEnv: Difficulty-Aligned Co-Evolution Between LLM Agents and Environment Simulators

WorldWarp: Propagating 3D Geometry with Asynchronous Video Diffusion

LoGoPlanner: Localization Grounded Navigation Policy with Metric-aware Visual Geometry

Can LLMs Estimate Student Struggles? Human-AI Difficulty Alignment with Proficiency Simulation for Item Difficulty Prediction

QuCo-RAG: Quantifying Uncertainty from the Pre-training Corpus for Dynamic Retrieval-Augmented Generation

The Prism Hypothesis: Harmonizing Semantic and Pixel Representations via Unified Autoencoding

Med-Banana-50K: A Cross-modality Large-Scale Dataset for Text-guided Medical Image Editing

Kascade: A Practical Sparse Attention Method for Long-Context LLM Inference

GLM-4.5: Agentic, Reasoning, and Coding (ARC) Foundation Models

GroundingME: Exposing the Visual Grounding Gap in MLLMs through Multi-Dimensional Evaluation

Both Semantics and Reconstruction Matter: Making Representation Encoders Ready for Text-to-Image Generation and Editing

4D-RGPT: Toward Region-level 4D Understanding via Perceptual Distillation

Seed-Prover 1.5: Mastering Undergraduate-Level Theorem Proving via Learning from Experience

When Reasoning Meets Its Laws

Probing Scientific General Intelligence of LLMs with Scientist-Aligned Workflows

K2-V2: A 360-Open, Reasoning-Enhanced LLM

VenusBench-GD: A Comprehensive Multi-Platform GUI Benchmark for Diverse Grounding Tasks

MCIF: Multimodal Crosslingual Instruction-Following Benchmark from Scientific Talks

Qwen-Image-Layered: Towards Inherent Editability via Layer Decomposition

RoboSafe: Safeguarding Embodied Agents via Executable Safety Logic

A Real-World Evaluation of LLM Medication Safety Reviews in NHS Primary Care

Multi-LLM Thematic Analysis with Dual Reliability Metrics: Combining Cohen's Kappa and Semantic Similarity for Qualitative Research Validation

Active Intelligence in Video Avatars via Closed-loop World Modeling

FaithLens: Detecting and Explaining Faithfulness Hallucination

SAM Audio: Segment Anything in Audio

Step-DeepResearch Technical Report

SpatialTree: How Spatial Abilities Branch Out in MLLMs

SemanticGen: Video Generation in Semantic Space

Automated stereotactic radiosurgery planning using a human-in-the-loop reasoning large language model agent

LongVideoAgent: Multi-Agent Reasoning with Long Videos

GenEnv: Difficulty-Aligned Co-Evolution Between LLM Agents and Environment Simulators

WorldWarp: Propagating 3D Geometry with Asynchronous Video Diffusion

LoGoPlanner: Localization Grounded Navigation Policy with Metric-aware Visual Geometry

Can LLMs Estimate Student Struggles? Human-AI Difficulty Alignment with Proficiency Simulation for Item Difficulty Prediction

QuCo-RAG: Quantifying Uncertainty from the Pre-training Corpus for Dynamic Retrieval-Augmented Generation

The Prism Hypothesis: Harmonizing Semantic and Pixel Representations via Unified Autoencoding

Med-Banana-50K: A Cross-modality Large-Scale Dataset for Text-guided Medical Image Editing

Kascade: A Practical Sparse Attention Method for Long-Context LLM Inference

GLM-4.5: Agentic, Reasoning, and Coding (ARC) Foundation Models

GroundingME: Exposing the Visual Grounding Gap in MLLMs through Multi-Dimensional Evaluation

Both Semantics and Reconstruction Matter: Making Representation Encoders Ready for Text-to-Image Generation and Editing

4D-RGPT: Toward Region-level 4D Understanding via Perceptual Distillation

Seed-Prover 1.5: Mastering Undergraduate-Level Theorem Proving via Learning from Experience

When Reasoning Meets Its Laws

Probing Scientific General Intelligence of LLMs with Scientist-Aligned Workflows

K2-V2: A 360-Open, Reasoning-Enhanced LLM

VenusBench-GD: A Comprehensive Multi-Platform GUI Benchmark for Diverse Grounding Tasks

MCIF: Multimodal Crosslingual Instruction-Following Benchmark from Scientific Talks